Qwen3 Coder 480B A35B
Qwen · Open weights · Released Jul 23, 2025 · qwen/qwen3-coder
Best $0.22 in / $1.00 out via Google
262K contextToolsStructured outputPrompt cachingOpen weights
Available from 4 providersUSD / MTOK · PRICES 25 MINUTES AGO · SPEED 6 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 Google | $0.22 | $1.80 | — | 262K | — | 0.69s | 142 tok/s | 100.0% |
 DeepInfra | $0.30 | $1.00 | $0.10 | 262K | fp4 | ✕ | ✕ | 93.1% |
 Venice | $0.35 | $1.50 | $0.04 | 256K | fp8 | 0.72s | 94 tok/s | 64.2% |
 Alibaba | $0.975 | $4.88 | — | 262K | — | 1.7s | 44 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 6 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Oct 9, 2026endpoint removed · novita5 → 4
About
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...
Specifications
Context window262,144
Max output65,536
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJul 23, 2025
Knowledge cutoff2025-06-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-coder)Sources
OpenRouter API25 minutes ago
AGGREGATORHugging Face25 minutes ago
COMMUNITYModelIndex benchmarks20 days ago
MEASUREDVerified 25 minutes ago · list prices, not negotiated rates.