Last refreshed 2026-06-29. Next refresh: weekly.
Why use Qwen3-VL-235B-A22B on Novita AI?
Novita AI offers Qwen3-VL-235B-A22B with pay-as-you-go pricing at $0.98/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Compare Qwen3-VL-235B-A22B across 3 providers to find the best fit for your use caseInput / 1M
$0.98
Output / 1M
$3.95
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: qwen3-vl-235b-a22b-thinkingModel ID
qwen3-vl-235b-a22b-thinkingRequest example
Curated snippets for this provider have not been sourced yet.
Gotchas
- Use provider model ID "qwen3-vl-235b-a22b-thinking", not the LLMReference slug "qwen3-vl-235b-a22b".
Compare Qwen3-VL-235B-A22B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| AWS Bedrock | $0.53 | $2.66 |
| OpenRouter | $0.26 | $2.60 |
| Novita AI | $0.98 | $3.95 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.98 |
| Output tokens | $3.95 |
Capabilities
VisionMultimodalStructured Outputs
About Qwen3-VL-235B-A22B
Qwen3-VL-235B-A22B is Alibaba's Qwen3-VL model. It was released 2025-12-01.
Get Started
Model Specs
Released2025-12-01
Parameters235B (22B active)
Context128k