Aya Vision 32B
Aya Vision 32B is Cohere's language model with a 16K context window and up to 4K output tokens. A 32B multimodal vision-language model supporting 23 languages, excelling at image understanding, text, and language benchmarks.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Aya Vision 32B | — | 16K | — | — | Current |
| Aya Tiny Global | — | 8K | — | — | Available |
| Aya 101 | — | — | — | — | Available |
| Aya Expanse 32B | — | 128K | $0.500 | $1.50 | Available |
| Aya Expanse 8B | — | 8K | $0.500 | $1.50 | Available |
| Aya Vision 8B | — | 16K | — | — | Available |
| Tiny Aya Earth | — | 8K | — | — | Available |
| Tiny Aya Fire | — | 8K | — | — | Available |
| Tiny Aya Water | — | 8K | — | — | Available |