Smaller Qwen coder for efficient local agents and repo-level fixes
Qwen3-Coder 30B-A3B Instruct by alibaba is offered by 22 providers on this page. Public prices are shown for 20 of them. Its official list price is $0.45 per 1M input tokens and $2.25 per 1M output tokens. The lowest paid channel is Cortecs at $0.067 / $0.245 per 1M, about 6.7× 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 2 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 9.6 on the Intelligence Index. Against its lowest blended price of $0.112 per 1M, that is roughly 86 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 87 tokens per second, with 2.65s to the first token.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 128,000 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 |
|---|---|---|---|---|---|---|---|---|
| Pendra qwen3-coder:30b | Gateway | Free | — | — | 262,144 | 65,536 | ||
| ModelScope Qwen/Qwen3-Coder-30B-A3B-Instruct | Cloud | Free | — | — | 262,144 | 65,536 | ||
| Cortecs | Gateway | $0.067 | $0.25 | $0.014 | — | 262,144 | 262,144 | |
| Hugging Face Qwen/Qwen3-Coder-30B-A3B-Instruct | Cloud | $0.07 | $0.26 | — | — | 262,144 | 65,536 | |
| OVHcloud AI Endpoints | Cloud | $0.07 | $0.26 | — | — | 262,144 | 262,144 | |
| NovitaAI | Gateway | $0.07 | $0.27 | — | — | 160,000 ⚠ | 32,768 | |
| DevPass (LLM Gateway) | Gateway | $0.07 | $0.27 | — | — | 262,000 ⚠ | 65,536 | |
| LLM Gateway | Gateway | $0.07 | $0.27 | — | — | 160,000 ⚠ | 32,768 | |
| OpenRouter | Gateway | $0.07 | $0.28 | — | — | 262,144 | 235,929 | |
| SiliconFlow Qwen/Qwen3-Coder-30B-A3B-Instruct | Cloud | $0.07 | $0.28 | — | — | 262,000 ⚠ | 262,000 | |
| Alibaba (China)Official | First-party | $0.22 tiered >32K: $0.32 · >128K: $0.54 | $0.86 | — | — | 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.
2 more channels offer $0 (Pendra, ModelScope); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 19.4 | index | Source ↗ |
| SciCode | — | 27.8 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 15.2 | success 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.