Deprecations / Migrate

Migrate off Mixtral 8x22B

Retired

Mixtral 8x22B has been retired and shut down on 30 Mar 2025. Mistral's official replacement is Mistral Small 4. The cheapest comparable model we track is Llama 3.1 8B Instruct (Meta) at $0.022 per 1M tokens blended.

Last verified: 13 Aug 2026 · sourced from official provider documentation

What changes

Mixtral 8x22B → Mistral Small 4

Moving to Mistral Small 4 means a larger context window (64K → 256K).

SpecMixtral 8x22BMistral Small 4
StatusRetiredGA
Blended price /1M$0.262
Input / output /1M$0.15 / $0.6
Context window64K256K
Max output
Modalitytexttext, vision
Knowledge cutoff

API string was open-mixtral-8x22b → switch to mistral-small-2603. See Mistral Small 4's full spec sheet →

Cheapest alternatives

Budget-friendly replacements for Mixtral 8x22B

Generally-available models that match Mixtral 8x22B's capabilities (and at least half its 64K context), 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 Mixtral 8x22B

What replaces Mixtral 8x22B?

Mistral's recommended migration for Mixtral 8x22B is Mistral Small 4. The cheapest comparable model in our catalog is Llama 3.1 8B Instruct (Meta) at $0.022/1M blended.

Is Mixtral 8x22B still available?

No — Mixtral 8x22B has been retired (shut down 30 Mar 2025) and is no longer available via Mistral's API.

What is the cheapest alternative to Mixtral 8x22B?

Llama 3.1 8B Instruct (Meta) is the cheapest generally-available alternative we track that matches Mixtral 8x22B'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 Mixtral 8x22B's full spec sheet →