Deprecations / Migrate

Migrate off Mistral Large 2.0

Retired

Mistral Large 2.0 has been retired and shut down on 30 Mar 2025. Mistral's official replacement is Mistral Large 3. 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

Mistral Large 2.0 → Mistral Large 3

Moving to Mistral Large 3 means a larger context window (128K → 256K).

SpecMistral Large 2.0Mistral Large 3
StatusRetiredGA
Blended price /1M$0.75
Input / output /1M$0.5 / $1.50
Context window128K256K
Max output
Modalitytexttext, vision
Knowledge cutoff

API string was mistral-large-2407 → switch to mistral-large-2512. See Mistral Large 3's full spec sheet →

Cheapest alternatives

Budget-friendly replacements for Mistral Large 2.0

Generally-available models that match Mistral Large 2.0's capabilities (and at least half its 128K 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 Mistral Large 2.0

What replaces Mistral Large 2.0?

Mistral's recommended migration for Mistral Large 2.0 is Mistral Large 3. The cheapest comparable model in our catalog is Llama 3.1 8B Instruct (Meta) at $0.022/1M blended.

Is Mistral Large 2.0 still available?

No — Mistral Large 2.0 has been retired (shut down 30 Mar 2025) and is no longer available via Mistral's API.

What is the cheapest alternative to Mistral Large 2.0?

Llama 3.1 8B Instruct (Meta) is the cheapest generally-available alternative we track that matches Mistral Large 2.0'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 Mistral Large 2.0's full spec sheet →