jishie

Pixtral Large (latest)

mistral/pixtral-large-latest · family pixtral · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.

$3.00
Blended $/1M (3:1)
$2
Input $/1M
$6
Output $/1M
$8.00
1M in + 1M out
—
Cache read $/1M
#5774 of 7,708
Cheapest rank
Provider
Mistral (mistral)
Kind
text (outputs text)
Context
128,000 tokens
Max output
128,000 tokens
Capabilities
tools text image

Same model, other providers

“Pixtral Large (latest)” is offered by 2 providers — cheapest-effective first. This one (Mistral) is the cheapest.

ProviderInputOutputBlendedContext
Mistral (this)$2$6$3.00128k
Merge Gateway$2$6$3.00128k

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":"pixtral-large-latest","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Mistral models · model index · JSON