Qwen 2.5 Coder 32B

Alibaba CloudcodingOpen Source

Specialized coding model from Alibaba. Top open-source code model on HumanEval and SWE-Bench.

Context Window

131K

tokens

Max Output

8K

tokens

Input Price

$0.15

per 1M tokens

Output Price

$0.45

per 1M tokens

Speed

125

tokens/sec

Released

Nov 2024

2024-11-11

Blended Cost

$0.30

per 1M tokens

Value Score

246.7

quality per $

Capabilities

ChatCode Generation

Benchmarks

Quality Index
74
MMLU Pro
74.8
HumanEval (Coding)
92.7
MATH
64.2

Open Source — Licensed under Apache 2.0

About Qwen 2.5 Coder 32B

Qwen 2.5 Coder 32B is a coding AI model by Alibaba Cloud, released on November 11, 2024. It supports a context window of 131K tokens and can generate up to 8K output tokens.

At $0.15 per million input tokens and $0.45 per million output tokens, its blended cost of $0.30/1M tokens makes it one of the most affordable models available. Its value score of 246.7 reflects the balance of quality and cost.

Qwen 2.5 Coder 32B is available as an open-source model under the Apache 2.0 license, meaning you can self-host it for predictable costs or use it through API providers like Swfte Connect.

Using Qwen 2.5 Coder 32B with Swfte

Access Qwen 2.5 Coder 32B through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Qwen 2.5 Coder 32B in our AI Playground before integrating.