AI Model Watch
Models / Cohere

Command (legacy)

Deprecated

Original Command generative model. Deprecated 2025-09-15 per docs.cohere.com/docs/deprecations.md. Replacement: command-r-08-2024. Legacy price $1.00 in / $2.00 out per 1M confirmed first-party 2026-07-26 from the cohere.com/pricing FAQ ("Command pricing is $1.00/1M tokens for input and $2.00/1M tokens for output"). Context window not specified on current docs; 4096 is the historical value (low confidence) - treat as approximate. Correction 2026-09-02 (our error, not a provider change, so no changelog event): this row carried retires_on 2025-09-15 and a note calling that date a shutdown. It is the DEPRECATION date. Cohere publishes the two as distinct states — "Deprecated: no longer available to new customers but remain available to existing users until retirement... A shutdown date will be assigned at that time" vs "Shutdown: no longer available for users" — and docs.cohere.com/docs/models.md, re-read 2026-09-02, labels this model "Deprecated Sept 15, 2025" while labelling c4ai-aya-expanse-8b "Retired Apr 4, 2026". Cohere has assigned this model no shutdown date, so retires_on is now null; deprecated_on carries the 2025-09-15 date it always meant.

Command (legacy) by Cohere costs $1 per 1M input tokens and $2 per 1M output tokens ($1.25/1M blended), with a 4K (4096-token) context window. It is deprecated; the recommended replacement is Command R (08-2024).

Last verified: 26 Sep 2026 · sourced from official provider documentation

Deprecated since 15 Sep 2025 · no retirement date published

Lifecycle warning

This model is deprecated. Recommended migration: Command R (08-2024).

Read the Command (legacy) migration guide → replacement & cheapest alternatives

Provider
Cohere
Status
Deprecated
Input price
$1 / 1M tokens
Output price
$2 / 1M tokens
Cached input
—
Blended price
$1.25 / 1M tokens
Context window
4096 tokens (4K)
Max output
4000 tokens
Modality
text
Open weights
No — API only
Knowledge cutoff
—
Released
—
API string
command

Source: Cohere official documentation ↗

See also

Explore more

All Cohere models→

Prices, context windows and lifecycle status for every Cohere model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Command (legacy) — questions & answers

How much does Command (legacy) cost?

Command (legacy) is priced at $1 per 1M input tokens and $2 per 1M output tokens ($1.25/1M blended at a 3:1 input-to-output ratio).

What is the context window of Command (legacy)?

Command (legacy) has a 4096-token context window (4K), with up to 4000 output tokens per request.

Is Command (legacy) being deprecated or retired?

Command (legacy) is deprecated. It was deprecated on 15 Sep 2025; no retirement date has been published yet. The recommended migration is Command R (08-2024).

Does Command (legacy) support image or vision input?

Our catalog lists Command (legacy)'s modalities as text; image/vision input is not among them.

Can I self-host Command (legacy)?

No — Command (legacy) is proprietary. Its weights are not publicly released, so it is available only through Cohere's API (or hosted partners), not for self-hosting.

What is the API model string for Command (legacy)?

The API model identifier for Command (legacy) is "command" when calling Cohere's API.