Qwen3 30B A3B
Qwen · Open weights · Released Apr 28, 2025 · qwen/qwen3-30b-a3b
Best $0.12 in / $0.50 out via DeepInfra · fp8
41K contextToolsReasoningStructured outputOpen weights
Available from 3 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 12 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.096 | $0.40 | — | 41K | fp8 | — | — | — | |
| $0.12 | $0.50 | — | 41K | fp8 | 0.53s | 118 tok/s | 100.0% | |
| $0.18 | $0.75 | — | 41K | fp8 | — | — | 99.3% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 12 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Nov 5, 2026endpoint removed · cheaperinference2 → 1
Oct 23, 2026endpoint added · cheaperinference1 → 2
Oct 10, 2026endpoint removed · alibaba2 → 1
Oct 10, 2026context changed131072 → 40960
About
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
Specifications
Context window40,960
Max output16,384
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedApr 28, 2025
Knowledge cutoff2025-03-31
TokenizerQwen3
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-30b-a3b)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks12 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.