Back to providers page
Try this model
openrouter

qwen3-30b-a3b

completions

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.

Input:$0.1 / 1M tokens
Output:$0.3 / 1M tokens
Context:40960 tokens
text
text

Access qwen3-30b-a3b through LangDB AI Gateway

Recommended

Integrate with qwen's qwen3-30b-a3b 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
Code Example
Configuration
Base URL
API Keys
Headers
Project ID in header
X-Run-Id
X-Thread-Id
Model Parameters
12 available
frequency_penalty
-202
include_reasoning
max_tokens
min_p
001
presence_penalty
-201.999
repetition_penalty
012
response_format
seed
stop
temperature
012
top_k
top_p
011
Additional Configuration
Tools
Guards
User:
Id:
Name:
Tags:
Publicly Shared Threads5
  • openrouter
    Integer solutions to 3x + 5y = 100
    about 2 months ago
    Method to solve 3x + 5y = 100: find one integer solution, then all solutions are (x, y) = (5t, 20 – 3t) for any integer t.
    diophantine equation
    linear diophantine solutions
    integer solutions 3x+5y=100
    general solution diophantine
  • openrouter
    Probability both cards are face cards
    about 2 months ago
    Step-by-step calculation of the probability that two cards drawn from a 52-card deck are both face cards (Jack, Queen, King), resulting in 11/221.
    probability of face cards
    drawing two cards without replacement
    combinatorics with playing cards
    calculating card drawing probabilities
  • openrouter
    pytest parameterized tests for palindrome function
    about 2 months ago
    Pytest parameterized tests for is_palindrome function covering empty, single chars, punctuated phrases, numeric, and non-palindromes.
    pytest palindrome tests
    parameterized pytest examples
    palindrome function unit tests
    string normalization palindrome
  • openrouter
    Vowel Count in "encyclopedia"
    about 2 months ago
    Explanation of vowels in "encyclopedia": It has 5 vowels—E, O, E, I, A—counted by identifying letters A, E, I, O, U only.
    vowels in encyclopedia
    counting vowels
    identifying vowels
    vowel analysis
  • openrouter
    Andrew’s number of sisters
    about 2 months ago
    Andrew has N sisters, since the total number of girls (including Alice) is N, so from his perspective he has N sisters.
    counting siblings
    family members math
    sisters and brothers problem
    logical reasoning siblings
Popular Models10
  • openai
    gpt-4.1-mini
    openai
    GPT-4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.
    Input:$0.4 / 1M tokens
    Output:$1.6 / 1M tokens
    Context:1047576 tokens
    tools
    text
    image
    text
  • anthropic
    claude-sonnet-4
    anthropic
    Our high-performance model with exceptional reasoning and efficiency
    Input:$3 / 1M tokens
    Output:$15 / 1M tokens
    Context:200K tokens
    tools
    text
    image
    text
  • anthropic
    claude-opus-4
    anthropic
    Our most capable and intelligent model yet. Claude Opus 4 sets new standards in complex reasoning and advanced coding
    Input:$15 / 1M tokens
    Output:$75 / 1M tokens
    Context:200K tokens
    tools
    text
    image
    text
  • openai
    gpt-4.1
    openai
    GPT-4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.
    Input:$2 / 1M tokens
    Output:$8 / 1M tokens
    Context:1047576 tokens
    tools
    text
    image
    text
  • gemini
    gemini-2.5-pro-preview
    gemini
    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.
    Input:$1.25 / 1M tokens
    Output:$10 / 1M tokens
    Context:1M tokens
    tools
    text
    image
    audio
    video
    text
  • xai
    grok-4
    xai
    Grok 4 is the latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades.
    Input:$3 / 1M tokens
    Output:$15 / 1M tokens
    Context:256K tokens
    tools
    text
    text
  • gemini
    gemini-2.5-flash-preview
    gemini
    Google's best model in terms of price-performance, offering well-rounded capabilities. Gemini 2.5 Flash rate limits are more restricted since it is an experimental / preview model.
    Input:$0.15 / 1M tokens
    Output:$0.6 / 1M tokens
    Context:1M tokens
    tools
    text
    image
    audio
    video
    text
  • gemini
    gemini-2.0-flash
    gemini
    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.
    Input:$0.1 / 1M tokens
    Output:$0.4 / 1M tokens
    Context:1M tokens
    tools
    text
    image
    audio
    video
    text
  • anthropic
    claude-3.7-sonnet
    anthropic
    Intelligent model, with visible step‑by‑step reasoning
    Input:$3 / 1M tokens
    Output:$15 / 1M tokens
    Context:200K tokens
    tools
    text
    text
    image
  • gemini
    gemini-2.0-flash-lite
    gemini
    Google's smallest and most cost effective model, built for at scale usage.
    Input:$0.07 / 1M tokens
    Output:$0.3 / 1M tokens
    Context:1M tokens
    text
    image
    audio
    video
    text

Related AI Model Resources

Explore more AI models, providers, and integration options:

  • Browse All AI Models
  • AI Providers Directory
  • More from openrouter
  • MCP Servers
  • Integration Documentation
  • Pricing & Plans
  • AI Industry Blog