qwen3-coder

completions

On:deepinfraparasail

qwen3-coder

completions

Published by: qwenProviders:

deepinfra parasail

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	Input	Output	Cached
deepinfra	$0.3 / 1M tokens	$1.2 / 1M tokens	$0.15 / 1M tokens
parasail	$0.39 / 1M tokens	$1.6 / 1M tokens	-

Released

Jul 22, 2025

Knowledge

Jan 23, 2025

Context

262144

Input

$0.3 / 1M tokens

Output

$1.2 / 1M tokens

Cached

$0.15 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Cached	Output Price	Input Formats	Output Formats
deepinfra	262144 tokens	$0.3 / 1M tokens	$0.15 / 1M tokens	$1.2 / 1M tokens	text	text
parasail	262144 tokens	$0.39 / 1M tokens	_	$1.6 / 1M tokens	text	text

Released Jul 22, 2025Knowledge Cutoff: Jan 23, 2025

Access qwen3-coder through LangDB AI Gateway

Recommended

Integrate with qwen's qwen3-coder 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-coder

Category Performance Scores:

Academia: Score 52.05 (Top 27% - Rank #94)
Finance: Score 40.80 (Top 43% - Rank #149)
Marketing: Score 51.86 (Top 30% - Rank #104)
Maths: Score 39.30 (Top 43% - Rank #149)
Programming: Score 47.20 (Top 18% - Rank #63)
Science: Score 62.03 (Top 35% - Rank #121)
Writing: Score 50.11 (Top 35% - Rank #121)

Overall Performance: 49.050476190476196 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	47.70	Top 24%	Mathematics
AA Coding Index	47.20	Top 18%	Programming
AAII	42.30	Top 23%	General
AA Math Index	39.30	Top 43%	Mathematics
GPQA	61.80	Top 36%	STEM (Physics, Chemistry, Biology)
HLE	4.40	Top 55%	General Knowledge
LiveCodeBench	58.50	Top 20%	Programming
MATH-500	94.20	Top 18%	Mathematics
MMLU-Pro	78.80	Top 28%	General Knowledge
SciCode	35.90	Top 20%	Scientific

GPQA Score: 61.80 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 262144 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

47.7

Mathematics

AA Coding Index

47.2

Programming

AAII

42.3

General

AA Math Index

39.3

Mathematics

GPQA

61.8

STEM (Physics, Chemistry, Biology)

HLE

4.4

General Knowledge

LiveCodeBench

58.5

Programming

MATH-500

94.2

Mathematics

MMLU-Pro

78.8

General Knowledge

SciCode

35.9

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	47.7	47.2	42.3	39.3	61.8	4.4	58.5	94.2	78.8	35.9

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for qwen3-coder

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-coder",
    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-coder",
    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-coder",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: qwen3-coder

Provider: deepinfra

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

Create API Key

Related Models

Similar models from deepinfra

qwen3-coder

qwen3-coder

Access qwen3-coder 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-Distill-Llama-70B

qwen3-coder by deepinfra - AI Model Details, Pricing, and Performance Metrics

qwen3-coder

qwen3-coder

Access qwen3-coder 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-Distill-Llama-70B