AI Model Watch
Deprecations / Migrate

Migrate off Summarize (legacy endpoint)

Retired

Summarize (legacy endpoint) has been retired and shut down on 15 Sep 2025. Cohere has not named an official replacement. The cheapest comparable model we track is Llama 3.1 8B Instruct (Meta) at $0.022 per 1M tokens blended.

Last verified: 24 Oct 2026 · sourced from official provider documentation

StatusRetiredCohere
Shut down15 Sep 2025deprecated 15 Sep 2025
Cheapest alternativeLlama 3.1 8B Instruct$0.022 /M blended
Cheapest alternatives

Budget-friendly replacements for Summarize (legacy endpoint)

Generally-available models that match Summarize (legacy endpoint)'s capabilities, ranked by blended price. Every number is computed from official catalog prices.

ModelBlended /1MInput / outputContext
Llama 3.1 8B Instruct
Meta
$0.022$0.02 / $0.03128K
Amazon Nova Micro
Amazon
$0.061$0.035 / $0.14128K
Command R7B
Cohere
$0.066$0.037 / $0.15128K
FAQ

Migrating off Summarize (legacy endpoint)

What replaces Summarize (legacy endpoint)?

Cohere has not published an official replacement for Summarize (legacy endpoint). The cheapest comparable model in our catalog is Llama 3.1 8B Instruct (Meta) at $0.022/1M blended.

Is Summarize (legacy endpoint) still available?

No — Summarize (legacy endpoint) has been retired (shut down 15 Sep 2025) and is no longer available via Cohere's API.

What is the cheapest alternative to Summarize (legacy endpoint)?

Llama 3.1 8B Instruct (Meta) is the cheapest generally-available alternative we track that matches Summarize (legacy endpoint)'s capabilities, at $0.02 per 1M input and $0.03 per 1M output tokens ($0.022/1M blended).

Browse the full deprecation watch → or see Summarize (legacy endpoint)'s full spec sheet →