Mistral Large 4
mistral/mistral-large-4 · family mistral-large · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$1.03
Blended $/1M (3:1)
$0.68
Input $/1M
$2.09
Output $/1M
$2.77
1M in + 1M out
$0.07 −90%
Cache read $/1M
#4259 of 7,967
Cheapest rank
- Provider
- Mistral (
mistral) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Mistral Large 4” is offered by 10 providers — cheapest-effective first. This one (Mistral) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Mistral (this) | $0.68 | $2.09 | $1.03 | 1M |
| NanoGPT | $0.68 | $2.09 | $1.03 | 524k |
| OpenRouter | $0.68 | $2.09 | $1.03 | 1M |
| Vercel AI Gateway | $0.68 | $2.09 | $1.03 | 524k |
| OpenCode Zen | $0.68 | $2.09 | $1.03 | 524k |
| Requesty | $0.68 | $2.09 | $1.03 | 524k |
| LowRouter | $0.7112 | $2.19 | $1.08 | 524k |
| Cortecs | $0.765 | $2.35 | $1.16 | 1M |
| Ollama Cloud | $1.36 | $4.18 | $2.06 | 1M |
| DevPass (LLM Gateway) | $1.36 | $4.18 | $2.06 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Mistral and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"mistral-large-4","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):