Qwen3 VL 235B A22B Instruct
Qwen · Open weights · Released Sep 23, 2025 · qwen/qwen3-vl-235b-a22b-instruct
Best $0.20 in / $0.88 out via DeepInfra · fp8
262K contextVisionToolsStructured outputPrompt cachingOpen weights
Available from 5 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 3 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.20 | $0.88 | $0.11 | 262K | fp8 | ✕ | ✕ | 98.9% | |
| $0.21 | $1.90 | $0.10 | 131K | fp8 | 1.3s | 74 tok/s | 100.0% | |
| $0.21 | $1.90 | $0.10 | 128K | fp8 | 1.4s | 102 tok/s | 97.8% | |
| $0.26 | $1.04 | — | 131K | — | 1.9s | 53 tok/s | 99.9% | |
| $0.30 | $1.50 | — | 131K | bf16 | ✕ | ✕ | 94.9% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 3 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.20 / $0.88
per MTok in / out
CACHE READ $0.11
Recent changesRSS ↗
Oct 5, 2026endpoint removed · primeintellect6 → 5
Oct 4, 2026endpoint added · primeintellect5 → 6
About
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Specifications
Context window262,144
Max output32,768
Modalities intext, image
Modalities outtext
LicenseOpen weights
ReleasedSep 23, 2025
Knowledge cutoff2025-03-31
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-vl-235b-a22b-instruct)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks20 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.