Aya Vision 32B
Summary
Aya Vision 32B is an open-weight language model from Cohere, released on 4 Mar 2025. It accepts text and images and generates text, with a 16K-token context window and up to 4K output tokens per response.
Open multilingual vision model for OCR, visual reasoning, and image question answering
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Cohere |
|---|---|
| Release date | 4 Mar 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [models.dev] |
| Context window | 16K (16,000 tokens) [models.dev] |
| Max output | 4K tokens [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
Aya Vision 32B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Cohere API c4ai-aya-vision-32b | – | – | – | 16K | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of Aya Vision 32B?
Aya Vision 32B has a context window of 16,000 tokens (16K) and can generate up to 4,000 tokens in a single response, according to models.dev.
Is Aya Vision 32B open source?
Aya Vision 32B is an open-weight model. Check the license terms before commercial use.
When was Aya Vision 32B released?
Cohere released Aya Vision 32B on 4 Mar 2025, according to models.dev.
Change history
No changes detected since we started tracking this model. We re-check every source daily.