Mistral

Mistral Large 4

Mistral flagship multimodal reasoning model with European multilingual excellence, Apache-compatible toolcalling syntax, and precision coding.

#17released Sep 25, 2026·Proprietary·Not disclosed
textimage256K ctxreasoning
Intelligence
89.8 #17
AAQI 90.0
Output Speed
92 t/s
ITL 10.9 ms/tok
Blended price (3:1)
$3.5 /1M
In $2/M · Out $6/M
Context
256K
≈ 640 A4 pages · max out 32,768

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Mistral Large 4
Claude Mythos Preview (#1)
Average (68)
Coding (84.5)Mathematics (87)Hard Science (GPQA) (89.5)Agentic & Tool Use (81)Knowledge (MMLU) (91)Vision / Multimodal (90)

Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.

Strengths & Trade-offs

Where it wins

  • Top European frontier model — multilingual depth
  • Strong coding and reasoning tier
  • $2/$6 pricing below US frontier peers

Trade-offs to watch

  • 256K context is small vs. 1M-token competitors
  • Proprietary hosted API

Killer Use Cases

EU-compliant deployments
European data-residency enterprise workloads.
Multilingual products
Cross-European-language assistants.
Coding copilots
Agentic development in regulated industries.

Developer Quickstart & API

Set MISTRAL_API_KEY first — get an API key
curl https://api.mistral.ai/v1/chat/completions \
  -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "mistral-large-4",
    "messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
  }'

Official Resources & Links

API deployment

Compare hosts & latency

Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
View providers matrix →

Scores by Source

Head-to-head Live Matchups

Live Specs & Architecture

Under the hood
Mistral Large 4 — undisclosed flagship
  • European multilingual excellence across 40+ languages
  • Reasoning, coding and multimodal categories
  • 256K context with 32K output window
Release date
Sep 25, 2026
Architecture
Mistral Large 4 — undisclosed flagship
Parameters
Not disclosed
License
Proprietary
Context Window
256,000 tokens
Max Output
32,768 tokens
Modalities
text + image
Cache Pricing
read $0.2 · write $2 /1M
Reasoning
Effort levels
Input Price
$2/M
Output Price
$6/M
Output Speed
92 t/s
Time to First Token
—
Data Updated
Sep 28, 2026

Estimated monthly bill

Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...

Cite & embed

GitHub Markdown badge
Loading badge markdown...
BibTeX
@misc{llmpodium2026mistrallarge4,
  title = {Benchmark Analysis and Intelligence Evaluation of Mistral Large 4},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/mistral-large-4}
}

Embed Score Badge

Add a live Podium Score badge to your GitHub or Hugging Face README — it links back to the live ranking.

Preview
Mistral Large 4 LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

More from Mistral

Alternative Models

Closest alternatives to Mistral Large 4 based on capabilities, pricing, and benchmark scores.

0 / 4