ModelRefs / Mistral Large 2 - AI model implementation reference

Mistral Large 2 - AI model implementation reference

Mistral Large 2 is a retired Mistral AI text model generation from 2024, with hosted and weight-based implementation history. Mistral's deprecated and retired models table gives mistral-large-2407 a retirement date of 30 March 2025 with Mistral Large 3 as the replacement, and mistral-large-2411 a retirement date of 31 May 2026 with Mistral Medium 3.5 as the replacement. The profile remains useful for existing deployments, migration review, and release-specific license and serving decisions rather than new selection.

Overview

Mistral Large 2 is attributed to Mistral AI in ModelRefs' canonical registry. Tracked modalities: Text. Primary use cases considered on ModelRefs: Legacy general language, coding, and tool-use deployments; Migration analysis for self-managed or hosted Mistral Large 2 workloads.

This ModelRefs profile is decision-support material, not a final or universal ranking. Confirm current behavior, access, pricing, limits, licensing, and lifecycle in Mistral AI's own documentation, and evaluate Mistral Large 2 on representative workloads before implementation.

Lifecycle

Retired. No longer served. Requests to it fail rather than falling back.

Deprecated
27 February 2026
Stopped serving
31 May 2026
Provider's replacement
Mistral Medium 3.5

Provider-documented snapshots

  • mistral-large-2411
  • mistral-large-2407

Dates are for mistral-large-2411, which matches this entry's release date. The earlier mistral-large-2407 was deprecated on 30 November 2024 and retired on 30 March 2025, replaced by Mistral Large 3.

Source: docs.mistral.ai, checked 2026-10-16.

Benchmark & Evaluation

ModelRefs currently has partial, narrow benchmark coverage for Mistral Large 2. Treat the available benchmark evidence as one input to the decision, not a guarantee that Mistral Large 2 is the strongest option for your workload, and evaluate it on representative workloads before selecting it.

  • Provider-reported benchmark results should be interpreted with methodology, dataset, prompting, tool, sampling, and recency limitations in mind.
  • The release card contains provider-reported evaluations; lifecycle status limits the value of stale cross-model comparisons.

Implementation considerations

  • Resolve the canonical route to the exact release artifact and license.
  • Plan prompt, tokenizer, tool, quality, and latency regression tests before moving to a replacement.
  • Release-specific weights and historical hosted access are documented.
  • Both releases are retired on Mistral's own API: mistral-large-2407 since 30 March 2025 and mistral-large-2411 since 31 May 2026. Deployments through third-party hosts follow those hosts' own lifecycle schedules and must be checked separately.

Risks and limitations

  • Mistral AI documents this generation as legacy; do not infer current hosted availability.
  • Model artifacts do not provide a managed production service; operators own serving, security, monitoring, evaluation, and incident response.
  • Quantization, prompt templates, runtime versions, hardware, and fine-tuning can materially change observed behavior.

Source coverage

ModelRefs reviewed Mistral AI's published material on 2026-06-28. Model behavior, access, pricing, limits, and lifecycle can change, so verify the linked provider documentation before implementation. What remains open is recorded on this page: Retirement dates on third-party hosts are not mirrored here and need separate verification. Fit and comparison signals remain provisional until tested on your own workload.

Connected ModelRefs evidence

Sources

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Mistral Large 2 - AI model implementation reference.