qwen3-235b-a22b

completions

On:fireworksaideepinfra

qwen3-235b-a22b

completions

Published by: qwenProviders:

fireworksai deepinfra

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	Input	Output
fireworksai	$0.22 / 1M tokens	$0.88 / 1M tokens
deepinfra	$0.13 / 1M tokens	$0.6 / 1M tokens

Released

Apr 29, 2025

Knowledge

Oct 31, 2024

Context

131072

Input

$0.22 / 1M tokens

Output

$0.88 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
fireworksai	131072 tokens	$0.22 / 1M tokens	$0.88 / 1M tokens	text	text	Apache-2.0
deepinfra	40960 tokens	$0.13 / 1M tokens	$0.6 / 1M tokens	text	text	Apache-2.0

Released Apr 29, 2025Knowledge Cutoff: Oct 31, 2024

Access qwen3-235b-a22b through LangDB AI Gateway

Recommended

Integrate with qwen's qwen3-235b-a22b 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

Available from 2 providers

Provider:

Benchmark Results for qwen3-235b-a22b

Category Performance Scores:

Academia: Score 45.60 (Top 48% - Rank #161)
Finance: Score 26.80 (Top 68% - Rank #228)
Marketing: Score 36.09 (Top 73% - Rank #245)
Maths: Score 23.70 (Top 63% - Rank #212)
Programming: Score 23.30 (Top 69% - Rank #232)
Science: Score 60.81 (Top 48% - Rank #161)
Writing: Score 37.86 (Top 73% - Rank #245)

Overall Performance: 36.30793650793651 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	32.70	Top 41%	Mathematics
AA Coding Index	23.30	Top 69%	Programming
AAII	29.90	Top 50%	General
AA Math Index	23.70	Top 63%	Mathematics
GPQA	61.30	Top 47%	STEM (Physics, Chemistry, Biology)
HLE	4.70	Top 49%	General Knowledge
LiveCodeBench	34.30	Top 51%	Programming
MATH-500	90.20	Top 37%	Mathematics
MMLU	87.81	Top 21%	General Knowledge
MMLU-Pro	76.20	Top 43%	General Knowledge
SciCode	29.90	Top 50%	Scientific

MMLU Score: 87.81 - Massive Multitask Language Understanding benchmark

GPQA Score: 61.30 - Graduate-level reasoning benchmark

Model Comparison:

Provider: fireworksai

Model Type: completions

Context Size: 131072 tokens

Comparing against 335 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

32.7

Mathematics

AA Coding Index

23.3

Programming

AAII

29.9

General

AA Math Index

23.7

Mathematics

GPQA

61.3

STEM (Physics, Chemistry, Biology)

HLE

4.7

General Knowledge

LiveCodeBench

34.3

Programming

MATH-500

90.2

Mathematics

MMLU

87.8

General Knowledge

MMLU-Pro

76.2

General Knowledge

SciCode

29.9

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU	MMLU-Pro	SciCode
Score	32.7	23.3	29.9	23.7	61.3	4.7	34.3	90.2	87.8	76.2	29.9

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for qwen3-235b-a22b

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="qwen3-235b-a22b",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "qwen3-235b-a22b",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-235b-a22b",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: qwen3-235b-a22b

Provider: fireworksai

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from fireworksai

qwen3-235b-a22b

qwen3-235b-a22b

Access qwen3-235b-a22b through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

deepseek-r1-05-28

qwen3-235b-a22b by fireworksai - AI Model Details, Pricing, and Performance Metrics

qwen3-235b-a22b

qwen3-235b-a22b

Access qwen3-235b-a22b through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

deepseek-r1-05-28