qwen3-30b-a3b-thinking-2507

completions

byopenrouter

qwen3-30b-a3b-thinking-2507

completions

Published by: qwenProvider:

openrouter

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.

Released

Apr 29, 2025

Knowledge

Oct 31, 2024

License

Apache-2.0

Context

262144

Input

$0.12 / 1M tokens

Output

$1 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Released Apr 29, 2025Knowledge Cutoff: Oct 31, 2024License: Apache-2.0

Context: 262144 Input: $0.12 / 1M tokensOutput: $1 / 1M tokensCapabilities: toolsAccepts: textReturns: text

Access qwen3-30b-a3b-thinking-2507 through LangDB AI Gateway

Recommended

Integrate with qwen's qwen3-30b-a3b-thinking-2507 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

Benchmark Results for qwen3-30b-a3b-thinking-2507

Category Performance Scores:

Academia: Score 46.15 (Top 39% - Rank #135)
Finance: Score 24.10 (Top 66% - Rank #228)
Marketing: Score 33.26 (Top 75% - Rank #259)
Maths: Score 21.70 (Top 64% - Rank #221)
Programming: Score 29.30 (Top 46% - Rank #159)
Science: Score 61.02 (Top 37% - Rank #128)
Writing: Score 36.05 (Top 71% - Rank #245)

Overall Performance: 35.94103174603175 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	26.00	Top 42%	Mathematics
AA Coding Index	29.30	Top 46%	Programming
AAII	26.50	Top 53%	General
AA Math Index	21.70	Top 64%	Mathematics
GPQA	65.80	Top 28%	STEM (Physics, Chemistry, Biology)
HLE	4.60	Top 44%	General Knowledge
LiveCodeBench	32.20	Top 46%	Programming
MATH-500	86.30	Top 42%	Mathematics
MMLU-Pro	71.00	Top 53%	General Knowledge
SciCode	26.40	Top 52%	Scientific

GPQA Score: 65.80 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 262144 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

26.0

Mathematics

AA Coding Index

29.3

Programming

AAII

26.5

General

AA Math Index

21.7

Mathematics

GPQA

65.8

STEM (Physics, Chemistry, Biology)

HLE

4.6

General Knowledge

LiveCodeBench

32.2

Programming

MATH-500

86.3

Mathematics

MMLU-Pro

71.0

General Knowledge

SciCode

26.4

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	26.0	29.3	26.5	21.7	65.8	4.6	32.2	86.3	71.0	26.4

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for qwen3-30b-a3b-thinking-2507

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="qwen3-30b-a3b-thinking-2507",
    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: "qwen3-30b-a3b-thinking-2507",
    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": "qwen3-30b-a3b-thinking-2507",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: qwen3-30b-a3b-thinking-2507

Provider: openrouter

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

Create API Key

Related Models

Similar models from openrouter

qwen3-30b-a3b-thinking-2507

qwen3-30b-a3b-thinking-2507

Access qwen3-30b-a3b-thinking-2507 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2501

codestral-2508

qwen3-30b-a3b-thinking-2507 by openrouter - AI Model Details, Pricing, and Performance Metrics

qwen3-30b-a3b-thinking-2507

qwen3-30b-a3b-thinking-2507

Access qwen3-30b-a3b-thinking-2507 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2501

codestral-2508