Mistral Large 4
- Family
- Mistral Large
- Released
- 2026-10-06
- Context
- 1M
- Parameters
- 1.05T (49B active)
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Open weights
- License
- Mistral Ecosystem Open-Weight LicenseRestricted
- Weights
- Available
- Code
- Unknown
- Training
- Multi-stage
Cheapest of 3 routes · Mistral AI Studio · cache read $0.070
Cheapest of 3 routes · Mistral AI Studio · cache read $0.070
About
Mistral Large 4 (API id mistral-large-4-0, public preview launched 6 October 2026) is Mistral AI's multimodal mixture-of-experts model: 1.05T total parameters, 49B active per token (52B including embeddings and output layers), and a 1.6B vision encoder, with a 1M-token context window. On 29 October 2026 Mistral released the weights of an improved version on Hugging Face under the Mistral Ecosystem Open-Weight License (a modified MIT license that requires a separate commercial license to run a Model-as-a-Service business).
Providers(3)
Compare all 3Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| Mistral AI Studio | $0.700 | $2.10 | read $0.070 | Serverless |
| OpenRouter | $0.700 | $2.10 | read $0.070 | Serverless |
| Vercel AI Gateway | $0.700 | $2.10 | read $0.070 | Serverless |
Available via routers & gateways(10)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, caching, and guardrails; MIT-licensed open-source core is self-hostable. Now part of Palo Alto Networks as Prisma AIRS AI Gateway.
AIRouter
RouterCommercial LLM router (branded "AI Router" on its site) that picks the best model per request via a Decision API or an OpenAI-compatible Chat Completions endpoint, with a private selection mode that routes on anonymized patterns; sold as BYOK subscription plans priced by routed tokens.
Martian
RouterMartian Gateway: unified OpenAI- and Anthropic-compatible API to 200+ models with per-model token pricing, from Martian, whose site now presents it as an interpretability research lab.
Neutrino AI
RouterCommercial LLM router that dynamically routes each query to the best-suited model with load balancing and fallback handling.
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(7)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 88.1 | diamondObserved 2026-10-17 | Configuration: mistral-large-4 (High) Harness: Epoch AI Inspect harness (GPQA Diamond, 198 Q) Evaluator: Epoch AI Confidence: confirmed Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file gpqa_diamond.csv, row 'mistral-large-4-0_high', run started 2026-10-12). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities Benchmarking Hub'. Retrieved 2026-10-17. | ||
| 26.8 | FrontierMath Tier 4 v2 (private)Observed 2026-10-17 | Configuration: mistral-large-4 (High) Harness: Epoch AI FrontierMath Tier 4 v2 private set Evaluator: Epoch AI Confidence: confirmed Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file frontiermath_tier_4_v2.csv, row 'mistral-large-4-0_high', run started 2026-10-12). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities Benchmarking Hub'. Retrieved 2026-10-17. | ||
| 54.7 | Finance Agent v2 (Vals benchmark_id finance_agent_v2, version 2)Observed 2026-10-17 | Configuration: Vals AI default provider Mistral AI; temperature 1, top-p 0.95, max output 256,000, reasoning effort high Harness: Vals AI Finance Agent harness (Valkyrie) Evaluator: Vals AI Confidence: third-party Cost/task: $1.20 Notes: Vals AI leaderboard (https://www.vals.ai/benchmarks/fabv2), page 'Updated 10/16/2026', retrieved 2026-10-17. Vals model page https://www.vals.ai/models/mistralai_mistral-large-4 shows the hyperparameters. Accuracy. The lab's restatement (https://mistral.ai/news/mistral-large-4/) reads 54.7 (chart read); it matches after rounding and is not the source of this row. | ||
| 15.8 | Harvey's Legal Agent Benchmark v1 (Vals benchmark_id legal_agent_benchmark)Observed 2026-10-17 | Configuration: Vals AI default provider Mistral AI; temperature 1, top-p 0.95, max output 256,000, reasoning effort high Harness: Harvey generation and grading protocol, run by Vals on Valkyrie, internet disabled Evaluator: Vals AI Confidence: third-party Cost/task: $4.18 Notes: Vals AI leaderboard (https://www.vals.ai/benchmarks/hlab), page 'Updated 10/16/2026', retrieved 2026-10-17. Vals model page https://www.vals.ai/models/mistralai_mistral-large-4 shows the hyperparameters. Metric is the task all-pass rate: a task passes only if 100% of its criteria pass, averaged over two LLM judges (GPT 5.5 medium reasoning, Claude Sonnet 4.6). Vals model page: ±2.96. The lab's restatement (https://mistral.ai/news/mistral-large-4/) reads 15.8 (chart read, "Vals.ai Harvey LAB"); it matches after rounding and is not the source of this row. | ||
| 1434.0 | text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26 | Configuration: Mistral Large 4 Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'Mistral Large 4': rank 111, Arena Score 1433.8 (95% CI 1427.4-1440.3), 10331 votes. Retrieved 2026-10-26. | Source Source: LMArena (lmarena.ai), CC BY 4.0 | |
| 1252.0 | vision_style_control overall 2026-10-19 (style control, default view)Observed 2026-10-26 | Configuration: Mistral Large 4 Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena vision style control leaderboard, overall category, published 2026-10-19 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'Mistral Large 4': rank 52, Arena Score 1251.9 (95% CI 1232.6-1271.3), 1008 votes. Retrieved 2026-10-26. | Source Source: LMArena (lmarena.ai), CC BY 4.0 | |
| 1364.0 | text creative_writing 2026-10-22Observed 2026-10-22 | Configuration: Mistral Large 4 Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Large 4' (category creative_writing in text/latest-00000-of-00001.parquet): rank 152 of 416, rating 1363.8 (95% CI 1350.9-1376.6), 2383 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.
API versions
mistral-large-4-0mistral-large-4ML4mistralai/mistral-large-4-0mistral/mistral-large-4