LLM Reference

Mistral Medium 3.5

Released
2026-04-29
Last refreshed
2026-06-29
Status
Researched 77d ago
Open weightsCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Mistral Medium 3.5 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 262k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2026-04-29
Context
262k
Parameters
128B
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
Mistral Modified MIT LicenseCommercial use: conditional
Weights
Available
Code
Unknown
Training
Pretrained
Created by

Enterprise AI solutions for trust and transparency.

Paris, France
Founded 2023
Website
Pricing
Output / 1M
$7.50
Input / 1M
$1.50

Cheapest of 3 routes · Mistral AI Studio

About

Mistral's 128B flagship merged model, released April 29, 2026. Open weights available on HuggingFace since ~May 22, 2026 under a Modified MIT License (free for companies with <$20M/month revenue). Dense 128B architecture with 256k context window, configurable reasoning effort, vision encoder for variable image sizes, and native function calling. Achieves 91.4% on τ³-Telecom and 77.6% on SWE-Bench Verified. Strong multilingual support across 24+ languages. Replaces Mistral Medium 3.1, Magistral, and Devstral 2 as Mistral's primary merged model. Available via Mistral API at $1.50/$7.50 per million tokens (input/output) and via NVIDIA NIM/endpoints.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ C

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Mistral AI Studio$1.50$7.50
Serverless
OpenRouter$1.50$7.50
Serverless
Vercel AI Gateway$1.50$7.50
Serverless

Available via routers & gateways(10)

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
SWE-bench Verified77.6SWE-bench VerifiedObserved 2026-04-30Source
Google-Proof Q&A71.3Observed 2026-04-29Source
MMLU PRO79.8Observed 2026-04-29Source
τ-bench91.4τ³-Telecom (agentic tool use) (accuracy)Observed 2026-06-07Source

Migration checks

No linked migration route is available for this model yet.

Compare Mistral Medium 3.5 with other models

Show all 2 popular comparisonssorted by 7-day search impressions