Mistral Large 4 API Pricing & Monthly Cost Simulator
Verified 2026 unit economics for Mistral Mistral Large 4 (mistralai/mistral-large-4-0): $0.7/1M uncached input, $0.07/1M cached prefix read, and $2.1/1M output across a 1,048,576-token context window (released 2026-10-06).
Uncached Input (/1M)
$0.7
Cached Prompt Read (/1M)
$0.07 (-90%)
Output Completion (/1M)
$2.1
50% Batch API (In / Out)
$0.35 / $1.05
Interactive 30-Day Monthly Spend Simulator
Live Unit-Cost & Prompt Cache Slider (Mistral Large 4)
mistralai/mistral-large-4-0
Estimated 30-day spend
$96.60/mo
Cost per 1,000 calls
$3.2200
Monthly savings vs 0% cache
$37.80/mo
Technical Limits & API Capabilities
Context window
1,048,576
Max output tokens
262,144
Workload tier
Coding & Agent
Input modalities
text, image
Tool Calling: Yes
JSON Schema Strict: Yes
Reasoning Tokens: Supported
50% Batch API: Available
Same-Category 2026 Model Alternatives (Coding & Agent)
| Model | Provider | Input / Cached ($/1M) | Output ($/1M) | Context / Max Out |
|---|---|---|---|---|
| Mistral Large 4 | Mistral | $0.7 / $0.07 | $2.1 | 1,048,576 / 262,144 |
| Gemini 4 Hydrogen | $1.5 / $0.075 | $7.5 | 1,048,576 / 943,718 | |
| Gemini 4 Carbon | $2 / $0.1 | $10 | 1,048,576 / 943,718 | |
| Muse Ember | Meta | $0.1 / $0.004 | $0.5 | 1,048,576 / 943,718 |
| GPT-6.1 Terra | OpenAI | $1 / $0.05 | $5 | 1,050,000 / 128,000 |
| MiniMax M3.1 Flash | MiniMax | $0.15 / $0.015 | $0.6 | 1,048,576 / 524,288 |
| Muse Spark Open | Meta | $1.25 / $0.15 | $4.25 | 1,048,576 / 943,718 |
Head-to-Head Matchups Featuring Mistral Large 4
- Mistral Large 4 vs Muse Spark Open — $0.7 vs $1.25 / 1M
Frequently Asked Questions
How much does Mistral Large 4 cost per 1 million tokens in 2026?
Mistral Large 4 by Mistral is billed at $0.7 per 1M uncached input tokens, $0.07 per 1M cached input read tokens (90% cache discount), and $2.1 per 1M output tokens.
What are the context window and max output token limits for Mistral Large 4?
Mistral Large 4 supports a 1,048,576-token input context window and up to 262,144 completion output tokens per request, accepting text, image inputs.
Does Mistral Large 4 support strict JSON Schema outputs, tool calling, and Batch API?
Mistral Large 4 capability profile: tool calling = Supported, strict JSON Schema structured outputs = Supported, reasoning mode = Supported, and 50% asynchronous Batch API = Supported.