Mistral: Mistral Medium 3.5

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-st…

mistralai/mistral-medium-3.5-20260430

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
262144
Published model ID
mistral-medium-3-5
Capabilities
batch, fileInput, multimodal, reasoning, streaming, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

1–3 / 3

Published prices

1–8 / 8

mistral-medium-3-5 ↗

$1.50

Inference provider
mistral
Platform
Mistral
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
input / 1M tokens

mistral-medium-3-5 ↗

$0.75

Inference provider
mistral
Platform
Mistral
Unit
input_tokens_per_million
Currency
USD
Billing conditions
inference_type
Batch API
Billing label
input / 1M tokens

mistral-medium-3-5 ↗

$7.50

Inference provider
mistral
Platform
Mistral
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
output / 1M tokens

mistral-medium-3-5 ↗

$3.75

Inference provider
mistral
Platform
Mistral
Unit
output_tokens_per_million
Currency
USD
Billing conditions
inference_type
Batch API
Billing label
output / 1M tokens

Provider specifications & access

1–1 / 1

Mistral Medium 3.5 ↗

source model id
mistral-medium-3-5
hosting
mistral-hosted
platforms
  • Mistral
context length
256000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • batch
  • reasoning
  • streaming
  • structuredOutputs
  • toolCalling
retirement date
2027-04-30

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

18 / 100

source id
stanfordFMTI
canonical model id
mistralai/mistral-medium-3.5-20260430
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Mistral
assessment type
organization-level disclosure
metric
disclosure_score
result label
18 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Source specification observations

1–5 / 5

mistral ↗

field
context_length
value
256000
normalized value
256000
scope
source-model
source id
mistral
confidence
1

openRouter ↗

field
context_length
value
262144
normalized value
262144
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
context_length
value
262144
normalized value
262144
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
209715
normalized value
209715
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
209715
normalized value
209715
scope
source-model
source id
openRouter
confidence
1

Original sources

1–12 / 12

Mistral AI · blog ↗

Hugging Face · Model reference ↗

Hugging Face · Weights ↗

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Mistral AI · Model documentation ↗

Mistral AI · legal ↗

Epoch AI · Catalog ↗

GitHub · Catalog ↗

Hugging Face · Catalog ↗

Mistral AI · Catalog ↗

OpenRouter · Catalog ↗

Source links

1–7 / 7

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace