SunsetDiff

Replacement for c4ai-aya-vision-8b: what changes when you switch

The official replacement is command-r7b-12-2024. c4ai-aya-vision-8b shut down on 2026-04-04 per Cohere's deprecation page (checked 2026-11-12). The published context window changes from 16,000 tokens on c4ai-aya-vision-8b to 128,000 tokens on command-r7b-12-2024.

c4ai-aya-vision-8b model page · Cohere

Official replacement. Full diff page

c4ai-aya-vision-8b to command-r7b-12-2024

Some values not published Checked 2026-11-12.

Price per 1M tokens

Price comparison. Example monthly cost for 10M input tokens and 2M output tokens. Labeled example, not a bill.
FieldOldNewChange
Input Not published Not published Not published
Output Not published Not published Not published
Cached input Not published Not published Not published
Example monthly cost Not published Not published Example only

Context and max output

Token limits
LimitOldNewChange
Context window 16,000 128,000 +700% (higher)
Max output 4,000 4,000 0% (same)

Capabilities that differ

Only fields with two published values that differ
FieldOldNew
modalities_intext, imagetext

Endpoint changes

  • The chat reference shows POST https://api.cohere.com/v2/chat with model and messages. This sample only changes the model field. Source

Code

python before
import json
import urllib.request
body = json.dumps({"model": "c4ai-aya-vision-8b", "messages": [{"role": "user", "content": "Hello"}]}).encode()
request = urllib.request.Request("https://api.cohere.com/v2/chat", data=body, headers={"Content-Type": "application/json"})
python after
import json
import urllib.request
body = json.dumps({"model": "command-r7b-12-2024", "messages": [{"role": "user", "content": "Hello"}]}).encode()
request = urllib.request.Request("https://api.cohere.com/v2/chat", data=body, headers={"Content-Type": "application/json"})
typescript before
await fetch("https://api.cohere.com/v2/chat", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ model: "c4ai-aya-vision-8b", messages: [{ role: "user", content: "Hello" }] }),
});
typescript after
await fetch("https://api.cohere.com/v2/chat", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ model: "command-r7b-12-2024", messages: [{ role: "user", content: "Hello" }] }),
});
curl before
curl https://api.cohere.com/v2/chat \
  -H "Content-Type: application/json" \
  -d '{"model":"c4ai-aya-vision-8b","messages":[{"role":"user","content":"Hello"}]}'
curl after
curl https://api.cohere.com/v2/chat \
  -H "Content-Type: application/json" \
  -d '{"model":"command-r7b-12-2024","messages":[{"role":"user","content":"Hello"}]}'

Checklist

  1. Read the shutdown date for c4ai-aya-vision-8b on the linked official page.
  2. Point your requests at command-r7b-12-2024.
  3. Re-check price, context, and parameters on the provider pages linked here.
  4. Ship the change before the published shutdown date.

Official replacement. Full diff page

c4ai-aya-vision-8b to command-a-03-2025

Some values not published Checked 2026-11-12.

Price per 1M tokens

Price comparison. Example monthly cost for 10M input tokens and 2M output tokens. Labeled example, not a bill.
FieldOldNewChange
Input Not published Not published Not published
Output Not published Not published Not published
Cached input Not published Not published Not published
Example monthly cost Not published Not published Example only

Context and max output

Token limits
LimitOldNewChange
Context window 16,000 256,000 +1500% (higher)
Max output 4,000 8,000 +100% (higher)

Capabilities that differ

Only fields with two published values that differ
FieldOldNew
modalities_intext, imagetext

Endpoint changes

  • The chat reference shows POST https://api.cohere.com/v2/chat with model and messages. This sample only changes the model field. Source

Code

python before
import json
import urllib.request
body = json.dumps({"model": "c4ai-aya-vision-8b", "messages": [{"role": "user", "content": "Hello"}]}).encode()
request = urllib.request.Request("https://api.cohere.com/v2/chat", data=body, headers={"Content-Type": "application/json"})
python after
import json
import urllib.request
body = json.dumps({"model": "command-a-03-2025", "messages": [{"role": "user", "content": "Hello"}]}).encode()
request = urllib.request.Request("https://api.cohere.com/v2/chat", data=body, headers={"Content-Type": "application/json"})
typescript before
await fetch("https://api.cohere.com/v2/chat", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ model: "c4ai-aya-vision-8b", messages: [{ role: "user", content: "Hello" }] }),
});
typescript after
await fetch("https://api.cohere.com/v2/chat", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ model: "command-a-03-2025", messages: [{ role: "user", content: "Hello" }] }),
});
curl before
curl https://api.cohere.com/v2/chat \
  -H "Content-Type: application/json" \
  -d '{"model":"c4ai-aya-vision-8b","messages":[{"role":"user","content":"Hello"}]}'
curl after
curl https://api.cohere.com/v2/chat \
  -H "Content-Type: application/json" \
  -d '{"model":"command-a-03-2025","messages":[{"role":"user","content":"Hello"}]}'

Checklist

  1. Read the shutdown date for c4ai-aya-vision-8b on the linked official page.
  2. Point your requests at command-a-03-2025.
  3. Re-check price, context, and parameters on the provider pages linked here.
  4. Ship the change before the published shutdown date.

Official replacement. Full diff page

c4ai-aya-vision-8b to command-a-reasoning-08-2025

Some values not published Checked 2026-11-12.

Price per 1M tokens

Price comparison. Example monthly cost for 10M input tokens and 2M output tokens. Labeled example, not a bill.
FieldOldNewChange
Input Not published Not published Not published
Output Not published Not published Not published
Cached input Not published Not published Not published
Example monthly cost Not published Not published Example only

Context and max output

Token limits
LimitOldNewChange
Context window 16,000 256,000 +1500% (higher)
Max output 4,000 32,000 +700% (higher)

Capabilities that differ

Only fields with two published values that differ
FieldOldNew
modalities_intext, imagetext

Endpoint changes

  • The chat reference shows POST https://api.cohere.com/v2/chat with model and messages. This sample only changes the model field. Source

Code

python before
import json
import urllib.request
body = json.dumps({"model": "c4ai-aya-vision-8b", "messages": [{"role": "user", "content": "Hello"}]}).encode()
request = urllib.request.Request("https://api.cohere.com/v2/chat", data=body, headers={"Content-Type": "application/json"})
python after
import json
import urllib.request
body = json.dumps({"model": "command-a-reasoning-08-2025", "messages": [{"role": "user", "content": "Hello"}]}).encode()
request = urllib.request.Request("https://api.cohere.com/v2/chat", data=body, headers={"Content-Type": "application/json"})
typescript before
await fetch("https://api.cohere.com/v2/chat", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ model: "c4ai-aya-vision-8b", messages: [{ role: "user", content: "Hello" }] }),
});
typescript after
await fetch("https://api.cohere.com/v2/chat", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ model: "command-a-reasoning-08-2025", messages: [{ role: "user", content: "Hello" }] }),
});
curl before
curl https://api.cohere.com/v2/chat \
  -H "Content-Type: application/json" \
  -d '{"model":"c4ai-aya-vision-8b","messages":[{"role":"user","content":"Hello"}]}'
curl after
curl https://api.cohere.com/v2/chat \
  -H "Content-Type: application/json" \
  -d '{"model":"command-a-reasoning-08-2025","messages":[{"role":"user","content":"Hello"}]}'

Checklist

  1. Read the shutdown date for c4ai-aya-vision-8b on the linked official page.
  2. Point your requests at command-a-reasoning-08-2025.
  3. Re-check price, context, and parameters on the provider pages linked here.
  4. Ship the change before the published shutdown date.

Related models

Questions

What is the replacement for c4ai-aya-vision-8b?

The official replacement is command-r7b-12-2024. c4ai-aya-vision-8b shut down on 2026-04-04 per Cohere's deprecation page (checked 2026-11-12). The published context window changes from 16,000 tokens on c4ai-aya-vision-8b to 128,000 tokens on command-r7b-12-2024.

Is command-r7b-12-2024 cheaper than c4ai-aya-vision-8b?

A full price comparison is not published. One or both prices are missing from the official pages we checked.

Does command-r7b-12-2024 have a bigger context window than c4ai-aya-vision-8b?

Yes. The context window changes from 16,000 to 128,000 tokens.

Sources

Deprecation alerts

We email you before models shut down. Unsubscribe anytime.

Deprecation alert signup
Providers (optional)