Qwen2.5 Coder 32B Instruct
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**...
Anyone in the Space can @-mention Qwen2.5 Coder 32B Instruct with the team's shared context — pooled credits, one chat, one memory.
Starter is free forever — 1 Space, 100 credits/month, 1 MCP. No card.
Specifications
- Provider
- qwen
- Category
- llm
- Context length
- 32,768 tokens
- Max output
- —
- Modalities
- text
- License
- proprietary
- Released
- 2024-11-11
Pricing
- Input
- $0.66/Mtok
- Output
- $1.00/Mtok
- Model ID
qwen/qwen-2.5-coder-32b-instruct
Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool — one plan, one balance for everyone.
Team cost calculator
5 seats · 80 msgs/day
Switchy meters this against your org's shared credit pool — one plan, one balance for everyone.
Providers
| Provider | Context | Input | Output | P50 latency | Throughput | 30d uptime |
|---|---|---|---|---|---|---|
| qwen | 33k | $0.66/Mtok | $1.00/Mtok | — | — | — |
Performance
Benchmarks
Works well with
Top MCPs
Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.