Qwen2.5-Coder 32B Instruct: API Pricing, Context Window & Benchmarks
Qwen2.5-Coder 32B Instruct is a language model from Qwen, released in September 2024.
Qwen2.5-Coder is a specialized coding model trained on 5.5 trillion tokens of code data, supporting 92 programming languages with a 128K context window. It excels in code generation, completion, repair, and multi-programming tasks while
Qwen2.5-Coder 32B Instruct benchmarks
Rankings
Quality Tracker
Qwen2.5-Coder 32B Instruct Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Wed Jul 22 2026Qwen2.5-Coder 32B Instruct pricing
Providers
Qwen2.5-Coder 32B Instruct starts at $0.0900 per million input tokens and $0.0900 per million output tokens via Lambda. See all 4 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Lambda | $0.0900 | $0.0900 | 128.0K/128.0K | —/0.50 | 42/— | — | / |
 DeepInfra | $0.180 | $0.180 | 128.0K/128.0K | —/0.50 | 44/— | — | / |
 Hyperbolic | $0.200 | $0.200 | 128.0K/128.0K | —/0.50 | 100/— | — | / |
 Fireworks | $0.890 | $0.890 | 128.0K/128.0K | —/0.26 | 110/— | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
Qwen2.5-Coder 32B Instruct model size
Qwen2.5-Coder 32B Instruct has 32 billion parameters and was trained on 5.5 trillion tokens. See how it compares to other models in the same parameter range.
Qwen2.5-Coder 32B Instruct context window
Input and output token limits for Qwen2.5-Coder 32B Instruct, plus how it ranks on long-context understanding.
Qwen2.5-Coder 32B Instruct API
Available from the model provider
Qwen2.5-Coder 32B Instruct has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationQwen2.5-Coder 32B Instruct latency
Qwen2.5-Coder 32B Instruct time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Qwen2.5-Coder 32B Instruct examples
Recent arena outputs from Qwen2.5-Coder 32B Instruct, picked from the highest-ranked matchups.
Qwen2.5-Coder 32B Instruct license
Qwen2.5-Coder 32B Instruct is released under the Apache 2.0 license, which permits commercial use, has 32.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 32.0B
Apache License 2.0 - allows commercial use
Qwen2.5-Coder 32B Instruct resources
Official sources for Qwen2.5-Coder 32B Instruct: api documentation, paper or system card, official launch post, source repository, model weights.
Qwen2.5-Coder 32B Instruct vs other models
The most-compared alternatives to Qwen2.5-Coder 32B Instruct are Claude 3 Haiku, Gemma 2 27B, Llama 3.2 11B Instruct. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Qwen2.5-Coder 32B Instruct
Models ranked just above and below Qwen2.5-Coder 32B Instruct by LLM Stats score.
FAQ
Common questions about Qwen2.5-Coder 32B Instruct.