Qwen
Qwen3 Coder 480B A35B
qwen/qwen3-coder
Input
$0.30
per 1M tokens
Output
$1.00
per 1M tokens
Cached input
$0.10
per 1M tokens
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...
- Released
- Context window
- 262K tokens
- Max output
- 66K tokens
- Input
- text
- Output
- text
- Reasoning
- No
Price history
No price changes since we started tracking on .
Providers on OpenRouter
3 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| DeepInfraturbo | $0.30 | $1.00 | 262K | 100% | 92.9% |
| Venicefp8 | $0.35 | $1.50 | 256K | 100% | 79.5% |
| Googleus-south1 | $0.22 | $1.80 | 262K | — | 0.0% |