Qwen3 VL 30B A3B Instruct
Qwen · Open weights · Released Oct 6, 2025 · qwen/qwen3-vl-30b-a3b-instruct
Best $0.13 in / $0.52 out via Alibaba · 131K ctx at this price (headline 262K)
262K contextVisionToolsStructured outputOpen weights
Available from 4 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 8 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 Alibaba | $0.13 | $0.52 | — | 131K | — | 1.3s | 109 tok/s | 100.0% |
 DeepInfra | $0.15 | $0.60 | — | 262K | fp8 | 0.51s | 36 tok/s | 99.4% |
 Novita | $0.20 | $0.70 | — | 131K | bf16 | 1.4s | 111 tok/s | 99.0% |
 SiliconFlow | $0.29 | $1.00 | — | 262K | fp8 | 2s | 18 tok/s | 84.9% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 8 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Oct 5, 2026endpoint removed · primeintellect5 → 4
Oct 4, 2026endpoint added · primeintellect4 → 5
Sep 1, 2026endpoint removed · darkbloom5 → 4
Aug 31, 2026endpoint added · darkbloom4 → 5
About
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
Specifications
Context window262,144
Max output16,384
Modalities intext, image
Modalities outtext
LicenseOpen weights
ReleasedOct 6, 2025
Knowledge cutoff2025-03-31
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-vl-30b-a3b-instruct)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks18 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.