writing Rankings

writing Model Rankings

Top performing AI models ranked by writing benchmark scores

Total Models

187

Providers

13

Avg Score

45.82

Updated

Sep 26, 2025

Access gemini-2.5-pro-preview through LangDB AI Gateway

Recommended

Integrate with google's gemini-2.5-pro-preview and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests
Rank
Model
Details
#1
gemini-2.5-pro-preview

Gemini 2.5 Pro Experimental is Google's state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.

Provider
gemini
Type
completions
Context
1M
Score
86.4
Pricing
In: $1.25 / 1M tokens
Out: $10 / 1M tokens
#2
deepseek-r1-0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.

Provider
deepinfra
Type
completions
Context
163840
Score
85
Pricing
In: $0.5 / 1M tokens
Out: $2.15 / 1M tokens
#3
deepseek-r1-0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.

Provider
parasail
Type
completions
Context
163840
Score
85
Pricing
In: $0.79 / 1M tokens
Out: $4 / 1M tokens
#4
grok-3-mini

Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand extensive domain knowledge, and shines in math-specific and quantitative use cases, such as solving challenging puzzles or math problems. Transparent "thinking" traces accessible. Defaults to low reasoning, can boost with setting `reasoning: { effort: "high" }` Note: That there are two xAI endpoints for this model. By default when using this model we will always route you to the base endpoint. If you want the fast endpoint you can add `provider: { sort: throughput}`, to sort by throughput instead.

Provider
xai
Type
completions
Context
131072
Score
84
Pricing
In: $0.3 / 1M tokens
Out: $0.5 / 1M tokens
#5
grok-3-mini-beta

A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.

Provider
openrouter
Type
completions
Context
131072
Score
84
Pricing
In: $0.45 / 1M tokens
Out: $2.25 / 1M tokens
#6
qwen3-235b-a22b-thinking-2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.

Provider
deepinfra
Type
completions
Context
262144
Score
83.16
Pricing
In: $0.13 / 1M tokens
Out: $0.6 / 1M tokens
#7
qwen3-235b-a22b-thinking-2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.

Provider
parasail
Type
completions
Context
262144
Score
83.16
Pricing
In: $0.65 / 1M tokens
Out: $3 / 1M tokens
#8
kimi-k2-instruct

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

Provider
fireworksai
Type
completions
Context
131072
Score
78.85
Pricing
In: $0.6 / 1M tokens
Out: $2.5 / 1M tokens
#9
gpt-5

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

Provider
openai
Type
completions
Context
400K
Score
74.41
Pricing
In: $1.25 / 1M tokens
Out: $10 / 1M tokens
#10
phi-4-reasoning-plus

Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer. While it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically ~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed.

Provider
deepinfra
Type
completions
Context
32768
Score
73.34
Pricing
In: $0.07 / 1M tokens
Out: $0.35 / 1M tokens
#11
gpt-5-mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.

Provider
openai
Type
completions
Context
400K
Score
71.16
Pricing
In: $0.25 / 1M tokens
Out: $2 / 1M tokens
#12
o3

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.

Provider
openai
Type
completions
Context
200K
Score
70.95
Pricing
In: $2 / 1M tokens
Out: $8 / 1M tokens
#13
grok-2

Grok-2 is an advanced AI model developed by xAI, designed to provide highly accurate and helpful responses to a wide range of questions, often with a unique perspective on humanity.

Provider
xai
Type
completions
Context
131072
Score
68.19
Pricing
In: $2 / 1M tokens
Out: $10 / 1M tokens
#14
magistral-small-2506

Magistral Small is a 24B parameter instruction-tuned model based on Mistral-Small-3.1 (2503), enhanced through supervised fine-tuning on traces from Magistral Medium and further refined via reinforcement learning. It is optimized for reasoning and supports a wide multilingual range, including over 20 languages.

Provider
openrouter
Type
completions
Context
40K
Score
68.18
Pricing
In: $0.5 / 1M tokens
Out: $1.5 / 1M tokens
#15
grok-4

Grok 4 is the latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades.

Provider
xai
Type
completions
Context
256K
Score
67.61
Pricing
In: $3 / 1M tokens
Out: $15 / 1M tokens
#16
o1

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).

Provider
openai
Type
completions
Context
200K
Score
66.5
Pricing
In: $15 / 1M tokens
Out: $60 / 1M tokens
#17
grok-3

Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Excels in structured tasks and benchmarks like GPQA, LCB, and MMLU-Pro where it outperforms Grok 3 Mini even on high thinking. Note: That there are two xAI endpoints for this model. By default when using this model we will always route you to the base endpoint. If you want the fast endpoint you can add `provider: { sort: throughput}`, to sort by throughput instead.

Provider
xai
Type
completions
Context
131072
Score
66.35
Pricing
In: $3 / 1M tokens
Out: $15 / 1M tokens
#18
claude-opus-4

Our most capable and intelligent model yet. Claude Opus 4 sets new standards in complex reasoning and advanced coding

Provider
anthropic
Type
completions
Context
200K
Score
65.75
Pricing
In: $15 / 1M tokens
Out: $75 / 1M tokens
#19
o4-mini

o4-mini is latest small o-series model. It's optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks.

Provider
openai
Type
completions
Context
200K
Score
65.46
Pricing
In: $1.1 / 1M tokens
Out: $4.4 / 1M tokens
#20
gpt-4.1-mini

GPT-4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.

Provider
openai
Type
completions
Context
1047576
Score
65
Pricing
In: $0.4 / 1M tokens
Out: $1.6 / 1M tokens
#21
gemini-2.5-pro

Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems.

Provider
gemini
Type
completions
Context
1M
Score
64.89
Pricing
In: $1.25 / 1M tokens
Out: $10 / 1M tokens
#22
o3-mini

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to "high", "medium", or "low" to control the thinking time of the model. The default is "medium". OpenRouter also offers the model slug `openai/o3-mini-high` to default the parameter to "high". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.

Provider
openai
Type
completions
Context
200K
Score
64.09
Pricing
In: $1.1 / 1M tokens
Out: $4.4 / 1M tokens
#23
gemini-2.0-flash-lite

Google's smallest and most cost effective model, built for at scale usage.

Provider
gemini
Type
completions
Context
1M
Score
64.06
Pricing
In: $0.07 / 1M tokens
Out: $0.3 / 1M tokens
#24
gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Provider
deepinfra
Type
completions
Context
131072
Score
63.85
Pricing
In: $0.09 / 1M tokens
Out: $0.45 / 1M tokens
#25
gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Provider
fireworksai
Type
completions
Context
131072
Score
63.85
Pricing
In: $0.15 / 1M tokens
Out: $0.6 / 1M tokens
#26
gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Provider
parasail
Type
completions
Context
131072
Score
63.85
Pricing
In: $0.15 / 1M tokens
Out: $0.6 / 1M tokens
#27
sonar-reasoning

Sonar Reasoning is a reasoning model provided by Perplexity based on [DeepSeek R1](/deepseek/deepseek-r1). It allows developers to utilize long chain of thought with built-in web search. Sonar Reasoning is uncensored and hosted in US datacenters.

Provider
openrouter
Type
completions
Context
127K
Score
62.3
Pricing
In: $1 / 1M tokens
Out: $5 / 1M tokens
#28
chatgpt-4o-latest

OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of [GPT-4o](/models/openai/gpt-4o) in that it has additional RLHF. It is intended for research and evaluation. OpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.

Provider
openai
Type
completions
Context
128K
Score
60.8
Pricing
In: $5 / 1M tokens
Out: $15 / 1M tokens
#29
dolphin3.0-mistral-24b

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases. Dolphin aims to be a general purpose instruct model, similar to the models behind ChatGPT, Claude, Gemini. Part of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3) Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)

Provider
openrouter
Type
completions
Context
32768
Score
59.75
Pricing
In: $0.04 / 1M tokens
Out: $0.15 / 1M tokens
#30
dolphin3.0-r1-mistral-24b

Dolphin 3.0 R1 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases. The R1 version has been trained for 3 epochs to reason using 800k reasoning traces from the Dolphin-R1 dataset. Dolphin aims to be a general purpose reasoning instruct model, similar to the models behind ChatGPT, Claude, Gemini. Part of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3) Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)

Provider
openrouter
Type
completions
Context
32768
Score
59.75
Pricing
In: $0.01 / 1M tokens
Out: $0.03 / 1M tokens
#31
gpt-5-chat

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.

Provider
openai
Type
completions
Context
400K
Score
58.55
Pricing
In: $1.25 / 1M tokens
Out: $10 / 1M tokens
#32
deepseek-r1

DeepSeek-Reasoner is an advanced AI model designed to enhance logical reasoning and problem-solving capabilities, leveraging deep learning techniques to provide accurate and contextually relevant insights across various domains.

Provider
fireworksai
Type
completions
Context
160K
Score
58.48
Pricing
In: $8 / 1M tokens
Out: $8 / 1M tokens
#33
DeepSeek-R1

DeepSeek-Reasoner is an advanced AI model designed to enhance logical reasoning and problem-solving capabilities, leveraging deep learning techniques to provide accurate and contextually relevant insights across various domains.

Provider
deepinfra
Type
completions
Context
16K
Score
58.48
Pricing
In: $0.75 / 1M tokens
Out: $2.4 / 1M tokens
#34
deepseek-r1-05-28

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.

Provider
fireworksai
Type
completions
Context
163840
Score
58.48
Pricing
In: $3 / 1M tokens
Out: $8 / 1M tokens
#35
deepseek-r1-0528-qwen3-8b

DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro. It now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought. The distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.

Provider
parasail
Type
completions
Context
131072
Score
58.48
Pricing
In: $0.05 / 1M tokens
Out: $0.1 / 1M tokens
#36
mistral-small-24b-instruct-2501

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)

Provider
deepinfra
Type
completions
Context
32768
Score
58.43
Pricing
In: $0.05 / 1M tokens
Out: $0.08 / 1M tokens
#37
deepseek-reasoner

DeepSeek-V3.1 (Thinking Mode) is an advanced AI model designed to enhance logical reasoning and problem-solving capabilities, leveraging deep learning techniques to provide accurate and contextually relevant insights across various domains.

Provider
deepseek
Type
completions
Context
128K
Score
57.96
Pricing
In: $0.56 / 1M tokens
Out: $1.68 / 1M tokens
#38
gpt-5-nano

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.

Provider
openai
Type
completions
Context
400K
Score
57.79
Pricing
In: $0.05 / 1M tokens
Out: $0.4 / 1M tokens
#39
glm-4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a "thinking mode" designed for complex reasoning and tool use, and a "non-thinking mode" optimized for instant responses.

Provider
zai
Type
completions
Context
131072
Score
57.13
Pricing
In: $0.6 / 1M tokens
Out: $2.2 / 1M tokens
#40
glm-4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a "thinking mode" designed for complex reasoning and tool use, and a "non-thinking mode" optimized for instant responses.

Provider
parasail
Type
completions
Context
131072
Score
57.13
Pricing
In: $0.59 / 1M tokens
Out: $2.1 / 1M tokens
#41
glm-4.5-x

GLM-4.5-X is a high-performance variant of GLM-4.5 optimized for ultra-fast responses while maintaining the same capabilities and context length as the base model.

Provider
zai
Type
completions
Context
131072
Score
57.13
Pricing
In: $2.2 / 1M tokens
Out: $8.9 / 1M tokens
#42
claude-3-5-sonnet-20240620

Claude most intelligent model. Highest level of intelligence and capability

Provider
anthropic
Type
completions
Context
200K
Score
57
Pricing
In: $3 / 1M tokens
Out: $15 / 1M tokens
#43
sonar-pro

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like double the number of citations per search as Sonar on average. Plus, with a larger context window, it can handle longer and more nuanced searches and follow-up questions.

Provider
openrouter
Type
completions
Context
200K
Score
56.67
Pricing
In: $3 / 1M tokens
Out: $15 / 1M tokens
#44
gpt-4.1

GPT-4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.

Provider
openai
Type
completions
Context
1047576
Score
56.58
Pricing
In: $2 / 1M tokens
Out: $8 / 1M tokens
#45
o1-mini

The o1 series of large language models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. Faster and cheaper reasoning model particularly good at coding, math, and science

Provider
openai
Type
completions
Context
128K
Score
56.12
Pricing
In: $3 / 1M tokens
Out: $12 / 1M tokens
#46
kimi-k2

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

Provider
deepinfra
Type
completions
Context
131K
Score
56.12
Pricing
In: $0.5 / 1M tokens
Out: $2 / 1M tokens
#47
kimi-k2

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

Provider
parasail
Type
completions
Context
131072
Score
56.12
Pricing
In: $0.99 / 1M tokens
Out: $2.99 / 1M tokens
#48
kimi-k2-0905

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.

Provider
openrouter
Type
completions
Context
262144
Score
56.12
Pricing
In: $0.49 / 1M tokens
Out: $1.99 / 1M tokens
#49
qwen3-max

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.

Provider
openrouter
Type
completions
Context
256K
Score
55.26
Pricing
In: $1.2 / 1M tokens
Out: $6 / 1M tokens
#50
claude-sonnet-4

Our high-performance model with exceptional reasoning and efficiency

Provider
anthropic
Type
completions
Context
200K
Score
55.06
Pricing
In: $3 / 1M tokens
Out: $15 / 1M tokens
#51
minimax-m1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it to process long sequences—up to 1 million tokens—while maintaining competitive FLOP efficiency. With 456 billion total parameters and 45.9B active per token, this variant is optimized for complex, multi-step reasoning tasks. Trained via a custom reinforcement learning pipeline (CISPO), M1 excels in long-context understanding, software engineering, agentic tool use, and mathematical reasoning. Benchmarks show strong performance across FullStackBench, SWE-bench, MATH, GPQA, and TAU-Bench, often outperforming other open models like DeepSeek R1 and Qwen3-235B.

Provider
openrouter
Type
completions
Context
1M
Score
54.41
Pricing
In: $0.42 / 1M tokens
Out: $1.93 / 1M tokens
#52
gemini-2.5-flash

Google's best model in terms of price-performance, offering well-rounded capabilities.

Provider
gemini
Type
completions
Context
1M
Score
54.38
Pricing
In: $0.15 / 1M tokens
Out: $0.6 / 1M tokens
#53
grok-code-fast-1

grok-code-fast-1 is exceptionally versatile across the full software development stack and is particularly adept at TypeScript, Python, Java, Rust, C++, and Go. It can complete common programming tasks with minimal oversight, ranging from building zero-to-one projects and providing insightful answers to codebase questions to performing surgical bug fixes.

Provider
xai
Type
completions
Context
256K
Score
53.91
Pricing
In: $0.2 / 1M tokens
Out: $1.5 / 1M tokens
#54
claude-opus-4.1

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.

Provider
anthropic
Type
completions
Context
200K
Score
53.86
Pricing
In: $15 / 1M tokens
Out: $75 / 1M tokens
#55
deepseek-chat

DeepSeek-V3.1 (Non-thinking Mode) is an advanced conversational AI model designed to provide intelligent

Provider
deepseek
Type
completions
Context
128K
Score
53.18
Pricing
In: $0.56 / 1M tokens
Out: $1.68 / 1M tokens
#56
deepseek-chat-v3-0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.

Provider
deepinfra
Type
completions
Context
163840
Score
53.18
Pricing
In: $0.28 / 1M tokens
Out: $0.88 / 1M tokens
#57
deepseek-chat-v3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.

Provider
deepinfra
Type
completions
Context
163840
Score
53.18
Pricing
In: $0.3 / 1M tokens
Out: $1 / 1M tokens
#58
deepseek-chat-v3-0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.

Provider
parasail
Type
completions
Context
163840
Score
53.18
Pricing
In: $0.79 / 1M tokens
Out: $1.15 / 1M tokens
#59
deepseek-chat-v3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the DeepSeek V3-0324

Provider
parasail
Type
completions
Context
163840
Score
53.18
Pricing
In: $0.64 / 1M tokens
Out: $1.65 / 1M tokens
#60
llama-4-maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

Provider
deepinfra
Type
completions
Context
1048576
Score
53.17
Pricing
In: $0.15 / 1M tokens
Out: $0.6 / 1M tokens
#61
llama-4-maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

Provider
parasail
Type
completions
Context
1048576
Score
53.17
Pricing
In: $0.15 / 1M tokens
Out: $0.85 / 1M tokens
#62
QwQ-32B-Preview

QwQ-32B-Preview is an experimental research model developed by the Qwen Team, focused on advancing AI reasoning capabilities.

Provider
togetherai
Type
completions
Context
32768
Score
52.92
Pricing
In: $1.2 / 1M tokens
Out: $1.2 / 1M tokens
#63
qwq-32b-preview

QwQ-32B-Preview is an experimental research model focused on AI reasoning capabilities developed by the Qwen Team. As a preview release, it demonstrates promising analytical abilities while having several important limitations: 1. **Language Mixing and Code-Switching**: The model may mix languages or switch between them unexpectedly, affecting response clarity. 2. **Recursive Reasoning Loops**: The model may enter circular reasoning patterns, leading to lengthy responses without a conclusive answer. 3. **Safety and Ethical Considerations**: The model requires enhanced safety measures to ensure reliable and secure performance, and users should exercise caution when deploying it. 4. **Performance and Benchmark Limitations**: The model excels in math and coding but has room for improvement in other areas, such as common sense reasoning and nuanced language understanding.

Provider
openrouter
Type
completions
Context
32768
Score
52.92
Pricing
In: $0.2 / 1M tokens
Out: $0.2 / 1M tokens
#64
glm-4.5-air

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction.

Provider
zai
Type
completions
Context
131072
Score
52.49
Pricing
In: $0.2 / 1M tokens
Out: $1.1 / 1M tokens
#65
glm-4.5-airx

GLM-4.5-AirX is a lightweight, speed-optimized variant of GLM-4.5-Air delivering ultra-fast responses while preserving the same capabilities and context length as the base Air model.

Provider
zai
Type
completions
Context
131072
Score
52.49
Pricing
In: $1.1 / 1M tokens
Out: $4.5 / 1M tokens
#66
grok-2-1212

Grok 2 1212 introduces significant enhancements to accuracy, instruction adherence, and multilingual support, making it a powerful and flexible choice for developers seeking a highly steerable, intelligent model.

Provider
openrouter
Type
completions
Context
131072
Score
51.51
Pricing
In: $2 / 1M tokens
Out: $10 / 1M tokens
#67
gpt-4.1-nano

GPT-4.1 nano is the fastest, most cost-effective GPT-4.1 model.

Provider
openai
Type
completions
Context
1047576
Score
50.3
Pricing
In: $0.1 / 1M tokens
Out: $0.4 / 1M tokens
#68
qwen3-coder

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Provider
deepinfra
Type
completions
Context
262144
Score
50.11
Pricing
In: $0.3 / 1M tokens
Out: $1.2 / 1M tokens
#69
qwen3-coder-480b-a35b-instruct

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Provider
fireworksai
Type
completions
Context
262144
Score
50.11
Pricing
In: $0.45 / 1M tokens
Out: $1.8 / 1M tokens
#70
qwen3-coder

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Provider
parasail
Type
completions
Context
262144
Score
50.11
Pricing
In: $0.39 / 1M tokens
Out: $1.6 / 1M tokens
#71
claude-3-opus-20240229

Powerful model for highly complex tasks. Top-level intelligence, fluency, and understanding

Provider
anthropic
Type
completions
Context
200K
Score
50.04
Pricing
In: $5 / 1M tokens
Out: $75 / 1M tokens
#72
sonar

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features optimized for speed.

Provider
openrouter
Type
completions
Context
127072
Score
50.04
Pricing
In: $1 / 1M tokens
Out: $1 / 1M tokens
#73
gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Provider
fireworksai
Type
completions
Context
131072
Score
49.78
Pricing
In: $0.07 / 1M tokens
Out: $0.3 / 1M tokens
#74
gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Provider
deepinfra
Type
completions
Context
131072
Score
49.78
Pricing
In: $0.04 / 1M tokens
Out: $0.16 / 1M tokens
#75
qwen-2.5-7b-instruct

Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

Provider
deepinfra
Type
completions
Context
32768
Score
48.84
Pricing
In: $0.04 / 1M tokens
Out: $0.1 / 1M tokens
#76
gemini-2.0-flash

Google's most capable multi-modal model with great performance across all tasks, with a 1 million token context window, and built for the era of Agents.

Provider
gemini
Type
completions
Context
1M
Score
46.27
Pricing
In: $0.1 / 1M tokens
Out: $0.4 / 1M tokens
#77
qwq-32b

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

Provider
deepinfra
Type
completions
Context
131072
Score
45.65
Pricing
In: $0.07 / 1M tokens
Out: $0.15 / 1M tokens
#78
devstral-small-2505

Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%). Devstral supports a 128k context window and uses a custom Tekken tokenizer. It is text-only, with the vision encoder removed, and is suitable for local deployment on high-end consumer hardware (e.g., RTX 4090, 32GB RAM Macs). Devstral is best used in agentic workflows via the OpenHands scaffold and is compatible with inference frameworks like vLLM, Transformers, and Ollama. It is released under the Apache 2.0 license.

Provider
deepinfra
Type
completions
Context
128K
Score
45.42
Pricing
In: $0.06 / 1M tokens
Out: $0.12 / 1M tokens
#79
Qwen2-72B-Instruct

Qwen 2 Instruct (72B) is a large-scale model by Qwen, offering advanced capabilities for complex language tasks.

Provider
togetherai
Type
completions
Context
32768
Score
45.11
Pricing
In: $1.2 / 1M tokens
Out: $1.2 / 1M tokens
#80
qwen-2.5-coder-32b-instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning** and **code fixing**. - A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. To read more about its evaluation results, check out [Qwen 2.5 Coder's blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).

Provider
openrouter
Type
completions
Context
32768
Score
45.02
Pricing
In: $0.06 / 1M tokens
Out: $0.16 / 1M tokens
#81
mistral-medium-3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.

Provider
mistralai
Type
completions
Context
128K
Score
44.93
Pricing
In: $0.4 / 1M tokens
Out: $2 / 1M tokens
#82
mistral-medium-3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.

Provider
openrouter
Type
completions
Context
131072
Score
44.93
Pricing
In: $0.4 / 1M tokens
Out: $2 / 1M tokens
#83
qwen-turbo

Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.

Provider
openrouter
Type
completions
Context
1M
Score
44.79
Pricing
In: $0.05 / 1M tokens
Out: $0.2 / 1M tokens
#84
llama-4-scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

Provider
deepinfra
Type
completions
Context
327680
Score
44.14
Pricing
In: $0.08 / 1M tokens
Out: $0.3 / 1M tokens
#85
mistral-saba

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post [here](https://mistral.ai/en/news/mistral-saba)

Provider
mistralai
Type
completions
Context
32768
Score
44.09
Pricing
In: $0.2 / 1M tokens
Out: $0.6 / 1M tokens
#86
mistral-saba

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post [here](https://mistral.ai/en/news/mistral-saba)

Provider
openrouter
Type
completions
Context
32768
Score
44.09
Pricing
In: $0.2 / 1M tokens
Out: $0.6 / 1M tokens
#87
llama-3.1-nemotron-ultra-253b-v1

Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency. The model supports a context length of up to 128K tokens and can operate efficiently on an 8x NVIDIA H100 node. Note: you must include `detailed thinking on` in the system prompt to enable reasoning. Please see [Usage Recommendations](https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1#quick-start-and-usage-recommendations) for more.

Provider
openrouter
Type
completions
Context
131072
Score
43.97
Pricing
In: $0.6 / 1M tokens
Out: $1.8 / 1M tokens
#88
gemini-2.5-flash-lite

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence.

Provider
openrouter
Type
completions
Context
1048576
Score
43.86
Pricing
In: $0.1 / 1M tokens
Out: $0.4 / 1M tokens
#89
deepseek-v3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek.

Provider
fireworksai
Type
completions
Context
128K
Score
43.81
Pricing
In: $0.9 / 1M tokens
Out: $0.9 / 1M tokens
#90
DeepSeek-V3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek.

Provider
deepinfra
Type
completions
Context
16K
Score
43.81
Pricing
In: $0.49 / 1M tokens
Out: $0.89 / 1M tokens
#91
DeepSeek-V3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek.

Provider
togetherai
Type
completions
Context
131072
Score
43.81
Pricing
In: $1.25 / 1M tokens
Out: $1.25 / 1M tokens
#92
deepseek-v3-03-24

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.

Provider
fireworksai
Type
completions
Context
163840
Score
43.81
Pricing
In: $0.9 / 1M tokens
Out: $0.9 / 1M tokens
#93
deepseek-v3.1-base

This is a base model, trained only for raw next-token prediction. Unlike instruct/chat models, it has not been fine-tuned to follow user instructions. Prompts need to be written more like training text or examples rather than simple requests (e.g., “Translate the following sentence…” instead of just “Translate this”). DeepSeek-V3.1 Base is a 671B parameter open Mixture-of-Experts (MoE) language model with 37B active parameters per forward pass and a context length of 128K tokens. Trained on 14.8T tokens using FP8 mixed precision, it achieves high training efficiency and stability, with strong performance across language, reasoning, math, and coding tasks.

Provider
openrouter
Type
completions
Context
163840
Score
43.81
Pricing
In: $0.2 / 1M tokens
Out: $0.8 / 1M tokens
#94
deephermes-3-mistral-24b-preview

DeepHermes 3 (Mistral 24B Preview) is an instruction-tuned language model by Nous Research based on Mistral-Small-24B, designed for chat, function calling, and advanced multi-turn reasoning. It introduces a dual-mode system that toggles between intuitive chat responses and structured “deep reasoning” mode using special system prompts. Fine-tuned via distillation from R1, it supports structured output (JSON mode) and function call syntax for agent-based applications. DeepHermes 3 supports a **reasoning toggle via system prompt**, allowing users to switch between fast, intuitive responses and deliberate, multi-step reasoning. When activated with the following specific system instruction, the model enters a *"deep thinking"* mode—generating extended chains of thought wrapped in `<think></think>` tags before delivering a final answer. System Prompt: You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

Provider
openrouter
Type
completions
Context
32768
Score
41.24
Pricing
In: $0.09 / 1M tokens
Out: $0.37 / 1M tokens
#95
gpt-4o-mini

GPT-4o mini (o for omni) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.The knowledge cutoff for GPT-4o-mini models is October, 2023.

Provider
openai
Type
completions
Context
128K
Score
40.99
Pricing
In: $0.15 / 1M tokens
Out: $0.6 / 1M tokens
#96
llama-3.3-70b-instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. [Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)

Provider
deepinfra
Type
completions
Context
131072
Score
40.97
Pricing
In: $0.04 / 1M tokens
Out: $0.12 / 1M tokens
#97
llama-3.3-70b-instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. [Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)

Provider
parasail
Type
completions
Context
131072
Score
40.97
Pricing
In: $0.15 / 1M tokens
Out: $0.5 / 1M tokens
#98
gemini-1.5-flash-8b

lightweight model, smaller and faster, lower price + higher rate limits + Lower latency on small prompts (compared to 1.5 Flash)

Provider
gemini
Type
completions
Context
1M
Score
40.95
Pricing
In: $0.04 / 1M tokens
Out: $0.15 / 1M tokens
#99
gemma-3n-e4b-it

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements. This model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/)

Provider
openrouter
Type
completions
Context
32768
Score
40.51
Pricing
In: $0.02 / 1M tokens
Out: $0.04 / 1M tokens
#100
gpt-3.5-turbo

The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.

Provider
openai
Type
completions
Context
16385
Score
40.22
Pricing
In: $0.5 / 1M tokens
Out: $1.5 / 1M tokens
#101
gpt-4o-mini-search-preview

GPT-4o mini Search Preview is a specialized model trained to understand and execute web search queries with the Chat Completions API.

Provider
openai
Type
completions
Context
128K
Score
40.2
Pricing
In: $0.15 / 1M tokens
Out: $0.6 / 1M tokens
#102
gemma-2-27b-it

Gemma 2 offers best-in-class performance, runs at incredible speed across different hardware and easily integrates with other AI tools.

Provider
togetherai
Type
completions
Context
8192
Score
40.2
Pricing
In: $0.3 / 1M tokens
Out: $0.3 / 1M tokens
#103
devstral-medium

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost. It is designed for generalization across prompt styles and tool use in code agents and frameworks. Devstral Medium is available via API only (not open-weight), and supports enterprise deployment on private infrastructure, with optional fine-tuning capabilities.

Provider
openrouter
Type
completions
Context
131072
Score
40.11
Pricing
In: $0.4 / 1M tokens
Out: $2 / 1M tokens
#104
devstral-medium

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost. It is designed for generalization across prompt styles and tool use in code agents and frameworks. Devstral Medium is available via API only (not open-weight), and supports enterprise deployment on private infrastructure, with optional fine-tuning capabilities.

Provider
mistralai
Type
completions
Context
128K
Score
40.11
Pricing
In: $0.4 / 1M tokens
Out: $2 / 1M tokens
#105
qwen-2.5-72b-instruct

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).

Provider
deepinfra
Type
completions
Context
32768
Score
39.97
Pricing
In: $0.12 / 1M tokens
Out: $0.39 / 1M tokens
#106
DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.

Provider
deepinfra
Type
completions
Context
131072
Score
39.92
Pricing
In: $0.23 / 1M tokens
Out: $0.69 / 1M tokens
#107
DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.

Provider
togetherai
Type
completions
Context
131072
Score
39.92
Pricing
In: $2 / 1M tokens
Out: $2 / 1M tokens
#108
deepseek-r1-distill-llama-70b

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: - AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Provider
openrouter
Type
completions
Context
131072
Score
39.92
Pricing
In: $0.11 / 1M tokens
Out: $0.38 / 1M tokens
#109
command-a

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.

Provider
openrouter
Type
completions
Context
32768
Score
39.79
Pricing
In: $2.25 / 1M tokens
Out: $9 / 1M tokens
#110
nemotron-nano-9b-v2

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.

Provider
deepinfra
Type
completions
Context
128K
Score
39.68
Pricing
In: $0.04 / 1M tokens
Out: $0.16 / 1M tokens
#111
nova-pro-v1

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX). Amazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents. **NOTE**: Video input is not supported at this time.

Provider
openrouter
Type
completions
Context
300K
Score
39.15
Pricing
In: $0.8 / 1M tokens
Out: $3.2 / 1M tokens
#112
mistral-small-3.1-24b-instruct

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)

Provider
deepinfra
Type
completions
Context
128K
Score
38.74
Pricing
In: $0.05 / 1M tokens
Out: $0.1 / 1M tokens
#113
mistral-small-3.2-24b-instruct

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks. It supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).

Provider
deepinfra
Type
completions
Context
128K
Score
38.74
Pricing
In: $0.05 / 1M tokens
Out: $0.1 / 1M tokens
#114
mistral-small

With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between (Mistral NeMo 12B)[/mistralai/mistral-nemo] and (Mistral Large 2)[/mistralai/mistral-large], providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.

Provider
openrouter
Type
completions
Context
32768
Score
38.74
Pricing
In: $0.2 / 1M tokens
Out: $0.6 / 1M tokens
#115
mistral-small

With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between (Mistral NeMo 12B)[/mistralai/mistral-nemo] and (Mistral Large 2)[/mistralai/mistral-large], providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.

Provider
mistralai
Type
completions
Context
32768
Score
38.74
Pricing
In: $0.2 / 1M tokens
Out: $0.6 / 1M tokens
#116
mistral-small-3

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)

Provider
mistralai
Type
completions
Context
32768
Score
38.74
Pricing
In: $0.1 / 1M tokens
Out: $0.3 / 1M tokens
#117
mistral-small-3.1

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is [Mistral Small 3.2](mistralai/mistral-small-3.2-24b-instruct)

Provider
mistralai
Type
completions
Context
128K
Score
38.74
Pricing
In: $0.1 / 1M tokens
Out: $0.3 / 1M tokens
#118
mistral-small-3.2

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks. It supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).

Provider
mistralai
Type
completions
Context
128K
Score
38.74
Pricing
In: $0.1 / 1M tokens
Out: $0.3 / 1M tokens
#119
mistral-small-3.2-24b-instruct

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks. It supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).

Provider
parasail
Type
completions
Context
131072
Score
38.74
Pricing
In: $0.09 / 1M tokens
Out: $0.3 / 1M tokens
#120
mistral-tiny

Note: This model is being deprecated. Recommended replacement is the newer [Ministral 8B](/mistral/ministral-8b) This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fine-tuning than [Mistral 7B](/models/mistralai/mistral-7b-instruct-v0.1), inspired by community work. It's best used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial.

Provider
openrouter
Type
completions
Context
32768
Score
38.74
Pricing
In: $0.25 / 1M tokens
Out: $0.25 / 1M tokens
#121
qwen3-235b-a22b

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.

Provider
fireworksai
Type
completions
Context
131072
Score
37.86
Pricing
In: $0.22 / 1M tokens
Out: $0.88 / 1M tokens
#122
qwen3-235b-a22b

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.

Provider
deepinfra
Type
completions
Context
40960
Score
37.86
Pricing
In: $0.13 / 1M tokens
Out: $0.6 / 1M tokens
#123
qwen3-235b-a22b-2507

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks). Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.

Provider
deepinfra
Type
completions
Context
262144
Score
37.86
Pricing
In: $0.13 / 1M tokens
Out: $0.6 / 1M tokens
#124
qwen3-235b-a22b-2507

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks). Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.

Provider
parasail
Type
completions
Context
262144
Score
37.86
Pricing
In: $0.15 / 1M tokens
Out: $0.85 / 1M tokens
#125
mistral-large

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/). It supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.

Provider
openrouter
Type
completions
Context
128K
Score
36.96
Pricing
In: $2.5 / 1M tokens
Out: $7.5 / 1M tokens
#126
mistral-large

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/). It supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.

Provider
mistralai
Type
completions
Context
128K
Score
36.96
Pricing
In: $2 / 1M tokens
Out: $6 / 1M tokens
#127
mistral-large-2.1

Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significant upgrade on the previous [Mistral Large 24.07](/mistralai/mistral-large-2407), with notable improvements in long context understanding, a new system prompt, and more accurate function calling.

Provider
mistralai
Type
completions
Context
128K
Score
36.96
Pricing
In: $2 / 1M tokens
Out: $6 / 1M tokens
#128
mistral-large-2411

Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significant upgrade on the previous [Mistral Large 24.07](/mistralai/mistral-large-2407), with notable improvements in long context understanding, a new system prompt, and more accurate function calling.

Provider
openrouter
Type
completions
Context
131072
Score
36.96
Pricing
In: $2 / 1M tokens
Out: $6 / 1M tokens
#129
qwen3-8b

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math, coding, and logical inference, and "non-thinking" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.

Provider
openrouter
Type
completions
Context
128K
Score
36.21
Pricing
In: $0.04 / 1M tokens
Out: $0.14 / 1M tokens
#130
llama-3.1-405b-instruct

The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs. Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 405B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models including GPT-4o and Claude 3.5 Sonnet in evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Provider
deepinfra
Type
completions
Context
32768
Score
36.15
Pricing
In: $0.8 / 1M tokens
Out: $0.8 / 1M tokens
#131
llama-3.1-405b

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Provider
openrouter
Type
completions
Context
32768
Score
36.15
Pricing
In: $3 / 1M tokens
Out: $3 / 1M tokens
#132
qwen3-30b-a3b

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance. Significantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.

Provider
deepinfra
Type
completions
Context
40960
Score
36.06
Pricing
In: $0.08 / 1M tokens
Out: $0.29 / 1M tokens
#133
qwen3-30b-a3b

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance. Significantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.

Provider
parasail
Type
completions
Context
40960
Score
36.06
Pricing
In: $0.09 / 1M tokens
Out: $0.5 / 1M tokens
#134
qwen3-30b-a3b-instruct-2507

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.

Provider
openrouter
Type
completions
Context
131072
Score
36.06
Pricing
In: $0.2 / 1M tokens
Out: $0.8 / 1M tokens
#135
qwen3-30b-a3b-thinking-2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers. Compared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.

Provider
openrouter
Type
completions
Context
262144
Score
36.06
Pricing
In: $0.12 / 1M tokens
Out: $1 / 1M tokens
#136
gpt-4o

High-intelligence flagship model for complex, multi-step tasks. GPT-4o is cheaper and faster than GPT-4 Turbo. It is multimodal (accepting text or image inputs and outputting text), and it has the same high intelligence as GPT-4 Turbo but is much more efficient—it generates text 2x faster and is 50% cheaper. Additionally, GPT-4o has the best vision and performance across non-English languages of any of our models. GPT-4o is available in the OpenAI API to paying customers.

Provider
openai
Type
completions
Context
128K
Score
35.75
Pricing
In: $2.5 / 1M tokens
Out: $10 / 1M tokens
#137
mistral-medium-3.1

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.

Provider
mistralai
Type
completions
Context
128K
Score
35.7
Pricing
In: $0.4 / 1M tokens
Out: $2 / 1M tokens
#138
mistral-medium-3.1

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.

Provider
openrouter
Type
completions
Context
262144
Score
35.7
Pricing
In: $0.4 / 1M tokens
Out: $2 / 1M tokens
#139
gpt-4o-2024-05-13

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities. For benchmarking against other models, it was briefly called ["im-also-a-good-gpt2-chatbot"](https://twitter.com/LiamFedus/status/1790064963966370209) #multimodal

Provider
openai
Type
completions
Context
128K
Score
35.42
Pricing
In: $5 / 1M tokens
Out: $15 / 1M tokens
#140
devstral-small

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and released under the Apache 2.0 license, it features a 128k token context window and supports both Mistral-style function calling and XML output formats. Designed for agentic coding workflows, Devstral Small 1.1 is optimized for tasks such as codebase exploration, multi-file edits, and integration into autonomous development agents like OpenHands and Cline. It achieves 53.6% on SWE-Bench Verified, surpassing all other open models on this benchmark, while remaining lightweight enough to run on a single 4090 GPU or Apple silicon machine. The model uses a Tekken tokenizer with a 131k vocabulary and is deployable via vLLM, Transformers, Ollama, LM Studio, and other OpenAI-compatible runtimes.

Provider
deepinfra
Type
completions
Context
128K
Score
35.03
Pricing
In: $0.07 / 1M tokens
Out: $0.28 / 1M tokens
#141
glm-4.5v

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a "thinking mode" for deep reasoning and a "non-thinking mode" for fast responses.

Provider
parasail
Type
completions
Context
65536
Score
34.88
Pricing
In: $0.5 / 1M tokens
Out: $1.8 / 1M tokens
#142
glm-4.5v

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a "thinking mode" for deep reasoning and a "non-thinking mode" for fast responses.

Provider
zai
Type
completions
Context
65536
Score
34.88
Pricing
In: $0.6 / 1M tokens
Out: $1.8 / 1M tokens
#143
gemma-2-9b-it

Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class. Designed for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).

Provider
openrouter
Type
completions
Context
8192
Score
34.86
Pricing
In: $0.2 / 1M tokens
Out: $0.2 / 1M tokens
#144
phi-4-multimodal-instruct

Phi-4 Multimodal Instruct is a versatile 5.6B parameter foundation model that combines advanced reasoning and instruction-following capabilities across both text and visual inputs, providing accurate text outputs. The unified architecture enables efficient, low-latency inference, suitable for edge and mobile deployments. Phi-4 Multimodal Instruct supports text inputs in multiple languages including Arabic, Chinese, English, French, German, Japanese, Spanish, and more, with visual input optimized primarily for English. It delivers impressive performance on multimodal tasks involving mathematical, scientific, and document reasoning, providing developers and enterprises a powerful yet compact model for sophisticated interactive applications. For more information, see the [Phi-4 Multimodal blog post](https://azure.microsoft.com/en-us/blog/empowering-innovation-the-next-generation-of-the-phi-family/).

Provider
deepinfra
Type
completions
Context
131072
Score
34.58
Pricing
In: $0.05 / 1M tokens
Out: $0.1 / 1M tokens
#145
nova-lite-v1

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy. With an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.

Provider
openrouter
Type
completions
Context
300K
Score
34.56
Pricing
In: $0.06 / 1M tokens
Out: $0.24 / 1M tokens
#146
qwen3-32b

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Provider
deepinfra
Type
completions
Context
40960
Score
34.51
Pricing
In: $0.1 / 1M tokens
Out: $0.3 / 1M tokens
#147
qwen3-32b

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Provider
parasail
Type
completions
Context
40960
Score
34.51
Pricing
In: $0.1 / 1M tokens
Out: $0.5 / 1M tokens
#148
llama-3.1-nemotron-70b-instruct

NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Reinforcement Learning from Human Feedback (RLHF), it excels in automatic alignment benchmarks. This model is tailored for applications requiring high accuracy in helpfulness and response generation, suitable for diverse user queries across multiple domains. Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Provider
deepinfra
Type
completions
Context
131072
Score
34.11
Pricing
In: $0.12 / 1M tokens
Out: $0.3 / 1M tokens
#149
DeepSeek-R1-Distill-Qwen-32B

DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.

Provider
deepinfra
Type
completions
Context
131072
Score
34.02
Pricing
In: $0.12 / 1M tokens
Out: $0.18 / 1M tokens
#150
deepseek-r1-distill-qwen-32b

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\n\nOther benchmark results include:\n\n- AIME 2024 pass@1: 72.6\n- MATH-500 pass@1: 94.3\n- CodeForces Rating: 1691\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Provider
openrouter
Type
completions
Context
131072
Score
34.02
Pricing
In: $0.29 / 1M tokens
Out: $1.78 / 1M tokens
#151
llama-3.1-70b-instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Provider
deepinfra
Type
completions
Context
131072
Score
33.58
Pricing
In: $0.1 / 1M tokens
Out: $0.28 / 1M tokens
#152
DeepSeek-R1-Distill-Qwen-14B

DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.

Provider
togetherai
Type
completions
Context
131072
Score
33.33
Pricing
In: $1.6 / 1M tokens
Out: $1.6 / 1M tokens
#153
deepseek-r1-distill-qwen-14b

DeepSeek R1 Distill Qwen 14B is a distilled large language model based on [Qwen 2.5 14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: - AIME 2024 pass@1: 69.7 - MATH-500 pass@1: 93.9 - CodeForces Rating: 1481 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Provider
openrouter
Type
completions
Context
64K
Score
33.33
Pricing
In: $0.88 / 1M tokens
Out: $0.88 / 1M tokens
#154
claude-3-haiku-20240307

Fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance

Provider
anthropic
Type
completions
Context
200K
Score
33.3
Pricing
In: $0.25 / 1M tokens
Out: $1.25 / 1M tokens
#155
codestral-2501

[Mistral](/mistralai)'s cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more on their blog post: https://mistral.ai/news/codestral-2501/

Provider
openrouter
Type
completions
Context
262144
Score
32.56
Pricing
In: $0.3 / 1M tokens
Out: $0.9 / 1M tokens
#156
codestral-2501

Mistral's cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more on their blog post: https://mistral.ai/news/codestral-2501/

Provider
mistralai
Type
completions
Context
256K
Score
32.56
Pricing
In: $0.3 / 1M tokens
Out: $0.9 / 1M tokens
#157
codestral-2508

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Provider
mistralai
Type
completions
Context
256K
Score
32.56
Pricing
In: $0.3 / 1M tokens
Out: $0.9 / 1M tokens
#158
codestral-2508

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Provider
openrouter
Type
completions
Context
256K
Score
32.56
Pricing
In: $0.3 / 1M tokens
Out: $0.9 / 1M tokens
#159
phi-4

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more information, please see [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)

Provider
deepinfra
Type
completions
Context
16384
Score
32.53
Pricing
In: $0.07 / 1M tokens
Out: $0.14 / 1M tokens
#160
gemma-3-12b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after [Gemma 3 27B](google/gemma-3-27b-it)

Provider
deepinfra
Type
completions
Context
131072
Score
32.48
Pricing
In: $0.05 / 1M tokens
Out: $0.1 / 1M tokens
#161
command-r-plus

Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG). It offers multilingual support for ten key languages to facilitate global business operations. See benchmarks and the launch post [here](https://txt.cohere.com/command-r-plus-microsoft-azure/). Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).

Provider
openrouter
Type
completions
Context
128K
Score
32.46
Pricing
In: $3 / 1M tokens
Out: $15 / 1M tokens
#162
mistral-large-2407

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/). It supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.

Provider
openrouter
Type
completions
Context
131072
Score
32.38
Pricing
In: $2 / 1M tokens
Out: $6 / 1M tokens
#163
mistral-large-2407

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/). It supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.

Provider
mistralai
Type
completions
Context
128K
Score
32.38
Pricing
In: $2 / 1M tokens
Out: $6 / 1M tokens
#164
command

Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models. Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).

Provider
openrouter
Type
completions
Context
4096
Score
32.19
Pricing
In: $1 / 1M tokens
Out: $2 / 1M tokens
#165
command-r-plus-04-2024

Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG). It offers multilingual support for ten key languages to facilitate global business operations. See benchmarks and the launch post [here](https://txt.cohere.com/command-r-plus-microsoft-azure/). Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).

Provider
openrouter
Type
completions
Context
128K
Score
32.19
Pricing
In: $3 / 1M tokens
Out: $15 / 1M tokens
#166
gemma-3-27b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

Provider
deepinfra
Type
completions
Context
131072
Score
31.61
Pricing
In: $0.09 / 1M tokens
Out: $0.17 / 1M tokens
#167
gemma-3-27b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

Provider
parasail
Type
completions
Context
131072
Score
31.61
Pricing
In: $0.1 / 1M tokens
Out: $0.4 / 1M tokens
#168
qwen3-14b

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, programming, and logical inference, and a "non-thinking" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Provider
deepinfra
Type
completions
Context
40960
Score
30.32
Pricing
In: $0.06 / 1M tokens
Out: $0.24 / 1M tokens
#169
qwen3-14b

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, programming, and logical inference, and a "non-thinking" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Provider
parasail
Type
completions
Context
40960
Score
30.32
Pricing
In: $0.06 / 1M tokens
Out: $0.25 / 1M tokens
#170
mistral-nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.

Provider
deepinfra
Type
completions
Context
131072
Score
30.25
Pricing
In: $0.02 / 1M tokens
Out: $0.04 / 1M tokens
#171
mistral-nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.

Provider
mistralai
Type
completions
Context
128K
Score
30.25
Pricing
In: $0.15 / 1M tokens
Out: $0.15 / 1M tokens
#172
mistral-nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.

Provider
parasail
Type
completions
Context
131072
Score
30.25
Pricing
In: $0.03 / 1M tokens
Out: $0.11 / 1M tokens
#173
nova-micro-v1

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has simple mathematical reasoning and coding abilities.

Provider
openrouter
Type
completions
Context
128K
Score
29.21
Pricing
In: $0.04 / 1M tokens
Out: $0.14 / 1M tokens
#174
mixtral-8x7b-instruct

Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion parameters. Instruct model fine-tuned by Mistral. #moe

Provider
deepinfra
Type
completions
Context
32768
Score
29.01
Pricing
In: $0.08 / 1M tokens
Out: $0.24 / 1M tokens
#175
llama-3.1-8b-instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Provider
deepinfra
Type
completions
Context
131072
Score
27.8
Pricing
In: $0.01 / 1M tokens
Out: $0.02 / 1M tokens
#176
command-r

Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents. Read the launch post [here](https://txt.cohere.com/command-r/). Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).

Provider
openrouter
Type
completions
Context
128K
Score
26.54
Pricing
In: $0.5 / 1M tokens
Out: $1.5 / 1M tokens
#177
command-r-03-2024

Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents. Read the launch post [here](https://txt.cohere.com/command-r/). Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).

Provider
openrouter
Type
completions
Context
128K
Score
26.38
Pricing
In: $0.5 / 1M tokens
Out: $1.5 / 1M tokens
#178
ministral-3b

Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it’s ideal for orchestrating agentic workflows and specialist tasks with efficient inference.

Provider
openrouter
Type
completions
Context
32768
Score
25.85
Pricing
In: $0.04 / 1M tokens
Out: $0.04 / 1M tokens
#179
ministral-3b

Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it’s ideal for orchestrating agentic workflows and specialist tasks with efficient inference.

Provider
mistralai
Type
completions
Context
128K
Score
25.85
Pricing
In: $0.04 / 1M tokens
Out: $0.04 / 1M tokens
#180
deepseek-r1-distill-llama-8b

DeepSeek R1 Distill Llama 8B is a distilled large language model based on [Llama-3.1-8B-Instruct](/meta-llama/llama-3.1-8b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: - AIME 2024 pass@1: 50.4 - MATH-500 pass@1: 89.1 - CodeForces Rating: 1205 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Hugging Face: - [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) - [DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) |

Provider
openrouter
Type
completions
Context
32K
Score
25.75
Pricing
In: $0.04 / 1M tokens
Out: $0.04 / 1M tokens
#181
gemma-3-4b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.

Provider
deepinfra
Type
completions
Context
131072
Score
24.17
Pricing
In: $0.02 / 1M tokens
Out: $0.04 / 1M tokens
#182
llama-3.2-3b-instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages. Trained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings. Click here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md). Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Provider
deepinfra
Type
completions
Context
131072
Score
21.17
Pricing
In: $0.01 / 1M tokens
Out: $0.02 / 1M tokens
#183
mistral-7b-instruct-v0.2

A 7B dense Transformer, fast-deployed and easily customizable. Small, yet powerful for a variety of use cases.

Provider
bedrock
Type
completions
Context
32K
Score
18.42
Pricing
In: $0.15 / 1M tokens
Out: $0.2 / 1M tokens
#184
mistral-7b-instruct

A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to be the latest version.*

Provider
deepinfra
Type
completions
Context
32768
Score
18.42
Pricing
In: $0.03 / 1M tokens
Out: $0.05 / 1M tokens
#185
mistral-7b-instruct-v0.1

A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.

Provider
openrouter
Type
completions
Context
2824
Score
18.42
Pricing
In: $0.15 / 1M tokens
Out: $0.19 / 1M tokens
#186
mistral-7b-instruct-v0.3

A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. An improved version of [Mistral 7B Instruct v0.2](/models/mistralai/mistral-7b-instruct-v0.2), with the following changes: - Extended vocabulary to 32768 - Supports v3 Tokenizer - Supports function calling NOTE: Support for function calling depends on the provider.

Provider
openrouter
Type
completions
Context
32768
Score
18.42
Pricing
In: $0.03 / 1M tokens
Out: $0.06 / 1M tokens
#187
DeepSeek-R1-Distill-Qwen-1.5B

DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.

Provider
togetherai
Type
completions
Context
131072
Score
15.5
Pricing
In: $0.18 / 1M tokens
Out: $0.18 / 1M tokens