← Model list
Mistral Large 3 675B
mistral·mistral/mistral-large-3-675b-instruct-2512-2·GA·Open weights·mistral-large series
Flagship Mistral model for advanced reasoning, coding, and multilingual work
At a glance
Reference price$1.00 / $3.00 per 1M
Cache read $0.50 · NanoGPT
Lowest paid$1.00 / $3.00
NanoGPT Gateway
Context262,144
Output limit256,000
Capabilities
ReasoningTool useStructured output? Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Knowledge cutoff—
Released / updated2025-12-25 / 2026-01-19
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 2 providers1 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT mistralai/mistral-large-3-675b-instruct-2512 | Gateway | $1.00 | $3.00 | $0.50 | — | 262,144 | 256,000 | |
| Ollama Cloud mistral-large-3:675b | Cloud | — | — | — | — | 262,144 | 262,144 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1NanoGPT$290.00
The cheapest paid channel is the only channel.
Related models
Mistral Large 3 675B Instruct 2512same series$0 / $0Mistral Large 3same series$0.50 / $1.50Mistral Large (latest)same series$0.50 / $1.50Qwen3-Next 80B-A3B Instructcheaper alternative$0.144 / $0.574Qwen3-Coder 30B-A3B Instructcheaper alternative$0.216 / $0.861Qwen3 Coder Nextcheaper alternative$0.50 / $1.20Llama-3.1-8B-Instructcheaper alternative$0.15 / $0.45
Price historyone sample accumulated per data sync
Input listOutput listMin blended