Qwen3 VL 235B A22B InstructOpen weights
Alibaba · released 2025-09-23
No price from the maker itself is on record for Qwen3 VL 235B A22B Instruct. The lowest of 16 providers is Deep Infra: $0.2 per 1M input tokens and $0.88 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 32.8K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Deep InfraLowestQwen/ | $0.2 | $0.88 | $0.11 | Lowest | Official docs |
EEden AIdeepinfra/ | $0.2 | $0.88 | $0.11 | Official docs | |
 DevPass (LLM Gateway)qwen3-vl-235b-a22b-instruct | $0.2 | $0.88 | $0.11 | Official docs | |
LLLM Gatewaydeepinfra/ | $0.2 | $0.88 | $0.11 | Official docs | |
HHeliconeqwen3-vl-235b-a22b-instruct | $0.3 | $1.5 | — | Official docs | |
 Hugging FaceQwen/ | $0.3 | $1.5 | — | Official docs | |
PPrime Inferenceqwen/ | $0.3 | $1.5 | — | Official docs | |
OOrcaRouterqwen/ | $0.4 | $1.6 | — | Official docs | |
KKilo Gatewayqwen/ | $0.21 | $1.9 | $0.1 | Official docs | |
MMerge Gatewayqwen/ | $0.21 | $1.9 | $0.105 | Official docs | |
 OpenRouterqwen/ | $0.21 | $1.9 | $0.1 | Official docs | |
NNanoGPTqwen/ | $0.3 | $1.9 | $0.15 | Official docs |
5 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTqwen3-vl-235b-a22b-instruct-original | $0.3 | $1.9 | $0.15 | Official docs | |
 Amazon Bedrockqwen. | $0.53 | $2.66 | — | Official docs | |
CCortecsqwen3-vl-235b-a22b | $0.617 | $3.119 | $0.052 | Official docs | |
SSTACKITQwen/ | $1.76 | $2.05 | — | Official docs | |
JJalapeno CloudDeprecatedQwen3-VL-235B-A22B-Instruct | $0.3 | $1.5 | — | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Qwen vision-language instruct model for visual reasoning, documents, and agent tasks
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 32.8K
- Input
- Text, Image
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-03-31
- Open weights
- Yes
- Released
- 2025-09-23
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.