Skip to content
modeldeprecations.dev
Cohere c4ai-aya-vision-8b

Aya Vision 8B (Cohere)

Retired

Yes — Aya Vision 8B is retired. Cohere deprecated it on April 4, 2026 and shut it down on April 4, 2026; API requests to it now fail. The recommended replacement is Aya Vision 32B.

The compact multilingual vision model from Cohere Labs, answering questions about images in 23 languages at a size you could actually deploy. Retired 4 April 2026 with no notice, and the replacements Cohere names for it are text models - the only vision-capable Aya left is the 32B.

The facts

Provider Cohere
Model id c4ai-aya-vision-8b
Released
Deprecated April 4, 2026
Shutdown April 4, 2026 · 121 days ago
Status Retired
Last verified August 3, 2026

What to use instead

Cohere Aya Vision 32B c4ai-aya-vision-32b Active

Cohere's notice points at command-a-03-2025 and command-a-reasoning-08-2025, neither of which takes images. If you need vision, the 32B Aya or command-a-vision-07-2025 are the real options.

What parameters c4ai-aya-vision-32b accepts on modelparams.dev

Change the id

In most cases the migration is one string. Check the parameter differences before you ship — newer models drop older sampling knobs more often than they add them.

- "model": "c4ai-aya-vision-8b"
+ "model": "c4ai-aya-vision-32b"

Frequently asked questions

When did Cohere Aya Vision 8B shut down?
Cohere Aya Vision 8B shut down on April 4, 2026. API requests to it fail from that date onward.
What replaces Cohere Aya Vision 8B?
Cohere recommends Aya Vision 32B (`c4ai-aya-vision-32b`) as the replacement for Cohere Aya Vision 8B. Cohere's notice points at command-a-03-2025 and command-a-reasoning-08-2025, neither of which takes images. If you need vision, the 32B Aya or command-a-vision-07-2025 are the real options.
Is Cohere Aya Vision 8B still available?
No. Cohere Aya Vision 8B is retired and no longer served — it was shut down on April 4, 2026. Calls to it return an error.
How do I migrate from Cohere Aya Vision 8B to c4ai-aya-vision-32b?
Swap the model id in your API call: replace "c4ai-aya-vision-8b" with "c4ai-aya-vision-32b". Cohere's notice points at command-a-03-2025 and command-a-reasoning-08-2025, neither of which takes images. If you need vision, the 32B Aya or command-a-vision-07-2025 are the real options.

Sources

Found something wrong? The data is one YAML file — edit it on GitHub.

This page, for machines

Drop the badge in a README so it turns red the day this model is retired:

[![c4ai-aya-vision-8b](https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/cohere/c4ai-aya-vision-8b.json)](https://modeldeprecations.dev/cohere/c4ai-aya-vision-8b)

Other Cohere models

All Cohere deprecations →

How to use this site

The full guide, in Markdown. Copy it and hand it to a coding agent verbatim.

# How to use modeldeprecations.dev

[modeldeprecations.dev](https://modeldeprecations.dev) answers one question per model: is it deprecated,
when does it shut down, and what replaces it. Every date on the site is cited to the
provider's own documentation, with the date we last checked it.

Three lifecycle states are used, matching the providers' own vocabulary:

- **active** — still supported, no deprecation announced.
- **deprecated** — the provider has announced it is going away. It still answers requests.
- **retired** — API access is gone. Requests fail.

A model can be active *and* carry a shutdown date: Anthropic publishes a
"not sooner than" date and Google publishes an earliest shutdown date for models
that are current and fully supported. Those are reported as scheduled shutdowns,
not deprecations, because that is what the provider actually committed to.

## Check one model

```bash
curl https://modeldeprecations.dev/api/v1/models/openai/gpt-4-32k.json
```

Or fetch the page as Markdown, which includes the answer, the dates and the sources:

```bash
curl https://modeldeprecations.dev/openai/gpt-4-32k.md
```

## Full catalog

```bash
curl https://modeldeprecations.dev/api/v1/models.json
```

Ids are `provider/model`. Dated snapshots (`gpt-4-32k-0613`) are listed as aliases of
their canonical entry rather than as separate records.

Each entry carries `computed_status`, the lifecycle state recomputed against the build
date — so a model whose shutdown has passed reads `retired` without anyone editing data.

## Badges

A shields.io endpoint per model, for READMEs that should go red when a model dies:

```
https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/openai/gpt-4-32k.json
```

## Calendar and changelog

- Subscribe to every shutdown date: https://modeldeprecations.dev/calendar.ics
- Changelog RSS: https://modeldeprecations.dev/changelog.xml

## JSON Schema

```bash
curl https://modeldeprecations.dev/api/v1/schema.json
```

## Contribute

Data lives in YAML under `models/{provider}/{model}.yaml` in the
[GitHub repo](https://github.com/mnfst/modeldeprecations.dev). Every lifecycle date needs a source URL; CI rejects a
date without one. Open a PR.

## For agents

- Machine-readable overview: https://modeldeprecations.dev/llms.txt
- This guide plus every model inline: https://modeldeprecations.dev/llms-full.txt
- Any page also exists as Markdown: append `.md` to a model URL.
- In a browser, this site registers a **WebMCP** tool on `navigator.modelContext`:
  `check_model_deprecation`, `list_shutdowns`, `find_replacement`, and `get_usage_guide`.
- Parameters each model accepts are catalogued on the sibling site, https://modelparams.dev.