Mistral: Mistral Large 3 2512

Mistral AI

mistral/mistral-large-2512

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Context

262K

Input /1M

$0.50

Output /1M

$1.50

Latency (TTFT)

368ms

Pricing

Per 1M tokens, in USD

Input$0.50

Output$1.50

Cache read$0.05

Specs

text inimage infile intext out

TokenizerMistral

Max output tokens209,715

Supported parameters

frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Where it ranks on price

Against 157 routable models

Input$0.50

Cheaper than 49% of routable models

Output$1.50

Cheaper than 64% of routable models

Benchmarks

Intelligence9.7

Coding20.1

Agentic2.4

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-2512",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

Mistral: Mistral Large 3 2512

Mistral AI

mistral/mistral-large-2512

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Context

262K

Input /1M

$0.50

Output /1M

$1.50

Latency (TTFT)

368ms

Pricing

Per 1M tokens, in USD

Input$0.50

Output$1.50

Cache read$0.05

Specs

text inimage infile intext out

TokenizerMistral

Max output tokens209,715

Supported parameters

frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Where it ranks on price

Against 157 routable models

Input$0.50

Cheaper than 49% of routable models

Output$1.50

Cheaper than 64% of routable models

Benchmarks

Intelligence9.7

Coding20.1

Agentic2.4

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-2512",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'