QQwen · Released Jul 31, 2025
Qwen3 Coder 30B A3B Instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
- Released
- Jul 31 2025
- Context window
- 262K 236K out
- Input / 1M tokens
- $0.07 from Free
- Output / 1M tokens
- $0.28 from Free
Where to run it
18 providers compared
Free to try on Pendra, ModelScope — free endpoints are often limited-time and rate-limited. Cheapest: Hugging Face at $0.07 / $0.26 per 1M input / output tokens — 87% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Pendrafree · may be limited-time | Free | Free | — | 262K | 66K | — | Free |
| ModelScopefree · may be limited-time | Free | Free | — | 262K | 66K | — | Free |
| Hugging Face | $0.07 | $0.26 | — | 262K | 66K | — | Cheapest |
| LLM Gateway | $0.07 | $0.27 | — | 160K | 33K | — | +2% |
| DevPass (LLM Gateway) | $0.07 | $0.27 | — | 262K | 66K | — | +2% |
| SiliconFlowFP8 | $0.07 | $0.28 | — | 262K | 236K | 99.4%24h | +4% |
| Kilo Gateway | $0.07 | $0.28 | — | 262K | 236K | — | +4% |
| Helicone | $0.10 | $0.30 | — | 262K | 262K | — | +28% |
| NanoGPT | $0.10 | $0.40 | $0.05 | 128K | 66K | — | +49% |
| SiliconFlow (China) | $0.10 | $0.42 | — | 262K | 262K | — | +56% |
| Amazon Bedrockus-west-2 | $0.15 | $0.60 | — | 262K | 236K | 100%24h | +123% |
| Vercel AI Gateway | $0.15 | $0.60 | — | 262K | 8K | — | +123% |
| Clarifai | $0.12 | $0.75 | — | 262K | 66K | — | +133% |
| Cortecs | $0.18 | $0.70 | $0.014 | 262K | 262K | — | +163% |
| Alibaba (China) | $0.22 | $0.86 | — | 262K | 66K | — | +221% |
| Eden AI | $0.23 | $0.90 | — | 128K | 66K | — | +235% |
| GreenPT | $0.28 | $1.08 | — | 128K | 33K | — | +312% |
| Alibaba | $0.45 | $2.25 | — | 262K | 66K | — | +666% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Qwen3 Coder 30B A3B Instruct. Scores appear here automatically once it does.
Specs
Details
- Model ID
qwen/qwen3-coder-30b-a3b-instruct- Developer
- Qwen
- Release date
- Jul 31, 2025 ·
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- API price
- $0.07 / $0.28 per 1M input / output tokens
- Providers
- 18
- Input types
- text
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.