Aya Vision 32B

by CohereChat

Open multilingual vision model for OCR, visual reasoning, and image question answering

Context
16K tokens
Max output
4,000 tokens
Released
2025-03-04
Weights
Open

cohere/c4ai-aya-vision-32b

Specifications

Full facts as recorded, incl. what is unknown.

Released
2025-03-04
Weights
Open
Input
Text, Image
Output
Text
Context window
16,000 max across endpoints
Max output
4,000
Providers
1
Epoch Capabilities Index
not evaluated
Direct price range
no comparable direct price
More details
Last updated
2025-05-14
Knowledge cutoff

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

More from Cohere

Newest Cohere models in the catalogue. All Cohere models

ModelReleasedContextListed price
Embed 5 Pro2026-09-30128Kfrom $0.12
Embed 5 Fast2026-09-30128Kfrom $0.08
North Small Translate2026-09-0932.8Kunpriced
North Mini Code2026-06-17256Kunpriced
North Mini Code2026-06-09256Kunpriced
Command A Plus2026-05-20128Kfrom $2.50
Tiny Aya Fire2026-02-178Kunpriced
Tiny Aya Earth2026-02-178Kunpriced
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model