Qwen3 Coder 30B A3B Instruct
Qwen · Open weights · Released Jul 31, 2025 · qwen/qwen3-coder-30b-a3b-instruct
Best $0.07 in / $0.28 out via SiliconFlow · fp8
262K contextToolsStructured outputOpen weights
Available from 2 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 13 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.07 | $0.28 | — | 262K | fp8 | 2.1s | 26 tok/s | 99.5% | |
| $0.15 | $0.60 | — | 262K | — | 0.96s | 491 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 13 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Nov 18, 2026endpoint added · siliconflow1 → 2
Nov 16, 2026endpoint removed · siliconflow2 → 1
Nov 5, 2026endpoint removed · cheaperinference3 → 2
Oct 23, 2026endpoint added · cheaperinference2 → 3
Oct 17, 2026endpoint added · amazon-bedrock1 → 2
Oct 15, 2026endpoint removed · amazon-bedrock2 → 1
Oct 10, 2026endpoint removed · alibaba3 → 2
Oct 9, 2026endpoint removed · novita4 → 3
About
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...
Specifications
Context window262,144
Max output235,929
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJul 31, 2025
Knowledge cutoff2025-06-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-coder-30b-a3b-instruct)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks16 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.