Qwen: Qwen3 Coder 480B A35B
qwen/qwen3-coder
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...
Modalities
In / Out Price
$0.30 / $1 per 1M
Context
262K
Released
Jul 23, 2025
Knowledge Cutoff
Jun 2025
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Google | 262K | $0.22 | $1.80 | — | — | — | 100.00% |
 DeepInfrafp4 | 262K | $0.30 | $1 | $0.10 | — | — | 87.50% |
 Venicefp8 | 256K | $0.35 | $1.50 | $0.04 | — | — | 46.15% |
 Alibaba | 262K | $0.975 | $4.88 | — | — | — | 100.00% |