Qwen3 Coder 480B A35B pricing & benchmarks
Qwen3 Coder 480B A35B is available from Alibaba at $0.300 per million input tokens and $1.00 per million output tokens ($0.475 blended at 3:1). It accepts up to 262,144 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$0.300
Output$1.00
Blended (3:1)$0.475
Specification
qwen/qwen3-coder
Context window262K
Max output66K
ReleasedJul 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Qwen3 Coder 480B A35B yet. We show nothing rather than reprinting an unverified figure.
Where to run Qwen3 Coder 480B A35B
5 hosts · 4.1× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra (turbo) | $0.475 | $0.300 / $1.00 | 262K | fp4 | 98.3% |
| Google (us-south1) | $0.615 | $0.220 / $1.80 | 262K | — | 92.7% |
| Venice | $0.637 | $0.350 / $1.50 | 256K | fp8 | 90.3% |
| Novita | $0.673 | $0.380 / $1.55 | 262K | fp8 | 91.3% |
| Alibaba (opensource) ⚠ re-prices above 32K prompt tokens ($1.75/$8.78) |
$1.95 | $0.975 / $4.88 | 262K | fp8 | 99.6% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B vs DeepSeek V4 Flash 0731
Qwen3 Coder 480B A35B vs Claude Opus 5
Qwen3 Coder 480B A35B vs Gemini 3.6 Flash
Qwen3 Coder 480B A35B vs Kimi K3
Qwen3 Coder 480B A35B vs GPT-5.6 Luna
Qwen3 Coder 480B A35B vs GPT-5.6 Terra
Qwen3 Coder 480B A35B vs GPT-5.6 Sol
Qwen3 Coder 480B A35B vs Grok 4.5
FAQ
How much does Qwen3 Coder 480B A35B cost?
Qwen3 Coder 480B A35B costs $0.300 per million input tokens and $1.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.475 per million tokens.
What is Qwen3 Coder 480B A35B's context window?
Qwen3 Coder 480B A35B accepts up to 262,144 tokens of context, and can generate up to 65,536 output tokens.