Open Qwen coding heavyweight for repository reasoning and agentic engineering
Qwen3-Coder 480B-A35B Instruct by alibaba is offered by 20 providers on this page. Public prices are shown for 18 of them. Its official list price is $1.50 per 1M input tokens and $7.50 per 1M output tokens. The lowest paid channel is submodel at $0.20 / $0.80 per 1M, about 10× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 11.9 on the Intelligence Index. Against its lowest blended price of $0.35 per 1M, that is roughly 34 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 50 tokens per second, with 2.97s to the first token.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 131,072 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-04.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | Cloud | Free | — | — | 262,144 | 66,536 | deprecated | |
| submodel Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | Gateway | $0.20 | $0.80 | — | — | 262,144 | 262,144 | |
| SiliconFlow Qwen/Qwen3-Coder-480B-A35B-Instruct | Cloud | $0.25 | $1.00 | — | — | 262,000 ⚠ | 262,000 | |
| SiliconFlow (China) Qwen/Qwen3-Coder-480B-A35B-Instruct | Cloud | $0.25 | $1.00 | — | — | 262,000 ⚠ | 262,000 | |
| Abacus Qwen/Qwen3-Coder-480B-A35B-Instruct | Gateway | $0.29 | $1.20 | — | — | 262,144 | 16,384 | |
| Jiekou.AI | Gateway | $0.29 | $1.20 | — | — | 262,144 | 65,536 | |
| Merge Gateway | Gateway | $0.22 | $1.80 | — | — | 131,072 ⚠ | 32,768 | |
| LLM Gateway | Gateway | $0.22 | $1.80 | $0.022 | — | 262,144 | 65,536 | |
| NovitaAI | Gateway | $0.38 | $1.55 | — | — | 262,144 | 65,536 | |
| DevPass (LLM Gateway) | Gateway | $0.38 | $1.55 | — | — | 262,144 | 65,536 | |
| Alibaba (China)Official | First-party | $0.86 tiered >32K: $1.29 · >128K: $2.15 | $3.44 | — | — | 262,144 | 65,536 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | dataset: public | 38.7 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.