Mistral Medium 3

mistral/mistral-medium-2505

Maker: Mistral AI, France
Released: 2025-05-07
Knowledge cutoff: 2025-05
Family: mistral-medium
Weights: closed
Tasks: text.chat, vision.understand, vision.extract
Cheapest offering: Azure OpenAI, about $0.001 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Azure OpenAI	`mistral-medium-2505`	ga	Input: $0.4 Output: $2 Since 2026-11-04 · models.dev, MIT	none	Context: 128,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed
Mistral AI	`mistral-medium-2505`	deprecated	Input: $0.4 Output: $2 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 131,072 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed
Google Vertex AI	`mistral-medium-3`	ga	Input: $0.4 Output: $2 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 131,072 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:gpqa_diamond`	0.618	0.5953	2025-05-07	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:hle`	0.082	0.0452	2025-05-07	Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

mistral-medium-2505
mistral-medium-3

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/mistral/mistral-medium-2505' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=azure-openai,mistral,vertex' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).