Mistral Large 4 PreviewReady
mistral-large-4
Serverless APILLMReasoningVisionPrompt cachingClosed
An efficient, deployment-friendly large preview model. It ranks #20 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 38.4. Released October 6, 2026.
524K
Context
1.0T
Parameters
#20
Intelligence rank · 38.4
Closed
Weights
View full spec
ReleasedOct 6, 2026
Knowledge cutoff—
Size classlarge
Input modalitiestext, image
Output modalitiestext
Median output speed71 tok/s
Median time to first token1.8s
Usage guide
1. Choose how you'd like to use Mistral Large 4 Preview
☁️ Serverless
Use with pay-per-token pricing. Zero setup, no cold starts, automatic failover between upstream routes.
Usage tiers · Standard • Priority
Try it — sign in
curl https://tokenhub-staging.coality.io/v1/chat/completions \
-H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-large-4",
"messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
}'Pricing
| Bucket | Price | Notes |
|---|---|---|
| Input tokens | $1.70 | per 1M tokens |
| Output tokens | $5.22 | per 1M tokens |
| Cache read | $0.1750 | cached input · 90% off |
| Cache write | $1.70 | per 1M tokens |
Billed per token with micro-dollar precision · effective Oct 26, 2026 · default key limits 600 req/min · 200K tokens/min
Benchmarks
Humanity's Last Exam
35.0
MMMU-Pro
76.4
SciCode
54.2
Terminal-Bench 4.0
26.8
Long Context Reasoning
81.3
Scores from the Artificial Analysis evaluation suite (0–100 scale).
About this model
1.0T-parameter closed model, with a 524K context window, native image input, visible reasoning traces, prompt caching at a 90% discount on cached input, 71 output tokens/s median serving speed and 1.8s to first token.