Back

Qwen2.5 Coder 32B Instruct

Qwen
Input: text
Output: text
Released: Nov 11, 2024Updated: Mar 28, 2025

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

  • Significantly improvements in code generation, code reasoning and code fixing.
  • A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.

To read more about its evaluation results, check out Qwen 2.5 Coder's blog.

32,768 Token Context

Process and analyze large documents and conversations.

Advanced Coding

Improved capabilities in front-end development and full-stack updates.

Agentic Workflows

Autonomously navigate multi-step processes with improved reliability.

Available On

ProviderModel IDContextMax OutputInput CostOutput CostThroughputLatency
DeepInfradeepInfra33K16K$0.06/M$0.15/M46.5 t/s333 ms
NebiusnebiusAiStudio131K-$0.06/M$0.18/M51.4 t/s448 ms
Lambdalambda33K33K$0.07/M$0.16/M44.1 t/s390 ms
Parasailparasail131K131K$0.19/M$0.20/M56.7 t/s585 ms
Hyperbolichyperbolic33K8K$0.20/M$0.20/M54.7 t/s1153 ms
Cloudflarecloudflare33K-$0.66/M$1.00/M--
Togethertogether16K2K$0.80/M$0.80/M92.4 t/s403 ms
Featherlessfeatherless16K4K$2.60/M$3.40/M--
Standard Pricing
Input Tokens
$0.00000006

per 1K tokens

Output Tokens
$0.00000015

per 1K tokens

Do Work. With AI.