Mistral AI: Mistral Medium 3.5

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Source-linked mistral-medium Closed weights Released 2026-04-30

API record Report

InputT

OutputT

Input price$1.5/M

Output price$7.5/M

Context262.144K

Max output209.715K

Providers14

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Mistral Medium 3.5
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
SAP AI Core	`mistralai--mistral-medium`	262.144K	262.144K	—	—	—	ReasoningToolsJSON	Docs ↗
Nvidia	`mistralai/mistral-medium-3.5-128b`	262.144K	32.768K	—	—	—	ReasoningToolsJSON	Docs ↗
LLM Gateway	`mistral/mistral-medium-3-5`	262.144K	262.144K	$1.5	$7.5	—	ToolsJSON	Docs ↗
Eden AI	`mistral/mistral-medium-3-5`	262.144K	209.715K	$1.5	$7.5	$0.15	ReasoningToolsJSON	Docs ↗
OpenRouter	`mistralai/mistral-medium-3-5`	262.144K	209.715K	$1.5	$7.5	—	ReasoningToolsJSON	Docs ↗
Pioneer	`mistral-medium-3.5`	256K	131.072K	$1.5	$7.5	$1.5	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`mistralai/mistral-medium-3-5`	262.144K	209.715K	$1.5	$7.5	—	ReasoningToolsJSON	Docs ↗
Mistral	`mistral-medium-2604`	262.144K	262.144K	$1.5	$7.5	$0.15	ReasoningToolsJSON	Docs ↗
DevPass (LLM Gateway)	`mistral-medium-3-5`	262.144K	262.144K	$1.5	$7.5	—	ToolsJSON	Docs ↗
NanoGPT	`mistralai/mistral-medium-3.5`	256K	32.768K	$1.5	$7.5	$0.75	ReasoningToolsJSON	Docs ↗
LowRouter	`auto/mistralai/mistral-medium-3.5`	262.144K	262.144K	$1.569	$7.844	$0.157	ReasoningToolsJSON	Docs ↗
Requesty	`mistral-medium-3-5`	262.144K	209.715K	$1.65	$8.25	$1.65	ReasoningToolsJSON	Docs ↗
evroc	`mistralai/Mistral-Medium-3.5-128B`	262.144K	262.144K	$1.725	$6.9	—	ReasoningToolsJSON	Docs ↗
GreenPT	`mistral-medium-3.5-128b`	262.144K	16.384K	$2.052	$10.26	—	ReasoningToolsJSON	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $1.5/M

Across 12 priced providers

Median input $1.5/M

Midpoint of listed rates

Highest input $2.052/M

1.4× the lowest listed rate

Output range $6.9 – $10.26

Per million output tokens

LLM Gateway $1.5/M

Eden AI $1.5/M

OpenRouter $1.5/M

Pioneer $1.5/M

Kilo Gateway $1.5/M

Mistral $1.5/M

DevPass (LLM Gateway) $1.5/M

NanoGPT $1.5/M

LowRouter $1.569/M

Requesty $1.65/M

evroc $1.725/M

GreenPT $2.052/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

8 providers list the identical $1.5 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 256K to 262.144K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

✓ Structured output Yes

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: Mistral AI
Model family: mistral-medium
Knowledge cutoff: Not documented
License: Not documented
Release date: 2026-04-30
Model ID: mistral/mistral-medium-3-5

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Oct 13, 2026Max Output Tokens262144 → 209715

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Oct 24, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://modelbench.lol/api/v1/models/mistral/mistral-medium-3-5

curl

curl "https://modelbench.lol/api/v1/models/mistral/mistral-medium-3-5"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Mistral Medium 3.5?

Mistral model for multilingual chat, reasoning, and tool-assisted workflows. It is published by Mistral AI and catalogued here from Models.dev.

How much does Mistral Medium 3.5 cost?

Listed input pricing starts at $1.5 per million tokens from LLM Gateway, rising to $2.052 across 12 listed providers.

What is the context length of Mistral Medium 3.5?

Mistral Medium 3.5 accepts up to 262.144K tokens of context and returns up to 209.715K output tokens.

Does Mistral Medium 3.5 support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, reasoning, and image input.

Which providers serve Mistral Medium 3.5?

14 providers list this model: SAP AI Core, Nvidia, LLM Gateway, Eden AI, OpenRouter, Pioneer and 8 more.

Are the weights for Mistral Medium 3.5 open?

No. This model is served through hosted APIs only.

When was Mistral Medium 3.5 released?

The catalog records a release date of 2026-04-30, last verified Oct 24, 2026.

More models from Mistral AI

View all →

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...

262.144K ctx $1.5/M in Mistral: Mistral Small 4

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

262.144K ctx $0.15/M in Mistral: Devstral 2 2512

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

262.144K ctx $0.4/M in Mistral: Ministral 3 14B 2512

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

262.144K ctx $0.2/M in