Model comparison

Mistral Medium 3.5 vs Mistral Small 4

Two Mistral tiers compared on the figures that decide which one a workload actually needs.

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Mistral

Mistral Medium 3.5

Frontier · Open weights

Mistral

Mistral Small 4

Budget · Open weights

AI model capability comparison
Specification	Mistral Medium 3.5	Mistral Small 4
Provider
Provider	Mistral	Mistral
Tier
Tier	Frontier	Budget
Context window
Context window	262K	262K
Max output
Max output	Not verifiedUnverified	Not verifiedUnverified
Input / 1M tokens
Input / 1M tokens	$1.50	Winner: $0.15
Output / 1M tokens
Output / 1M tokens	$7.50	Winner: $0.60
Weights
Weights	Open	Open
Parameters
Parameters	128B dense	119B total / 6.5B active (MoE)
Reasoning levels
Reasoning levels	Not verifiedUnverified	Not verifiedUnverified
Modalities
Modalities	text, image	text, image
License
License	Modified MIT	Apache 2.0
API model id
API model id	mistral-medium-3-5	mistral-small-2603
Released
Released	April 28, 2026	March 16, 2026
Artificial Analysis Intelligence Index (2026-09-26)
Artificial Analysis Intelligence Index (2026-09-26)	Winner: 14.2	11.3

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

2026-09-26
Artificial Analysis (Reasoning)
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check measuredAt.

Pricing tiers

Mistral Medium 3.5: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense.

Mistral Small 4: Mistral first-party API $0.15/$0.60 per MTok. Open weights (Apache 2.0). 119B total / 6.5B active MoE.

FrontierOpen weightsRecord checked September 26, 2026

Mistral Medium 3.5

Mistral Medium 3.5 is the model Mistral calls its new flagship — a 128B dense open-weight model with a 256K context, powering its Vibe remote agents.

Best for

EU-hosted frontier work
Open-weight self-hosting
Mistral Vibe agents

Watch out

Far behind US and Chinese frontier models on the Artificial Analysis index; max output is not published. Check the Modified MIT terms before redistribution.

BudgetOpen weightsRecord checked September 26, 2026

Mistral Small 4

Mistral Small 4 is Mistral's low-cost Apache-2.0 MoE — 6.5B active parameters with a 256K context and image input.

Best for

Cheap EU-hosted inference
Open-weight self-hosting
High-volume extraction

Watch out

Small active size: not for hard reasoning or agentic coding; max output is not published.

When the cheaper one wins

Mistral Small 4 is cheaper on output at $0.60 per million tokens against $7.50 for Mistral Medium 3.5 — about 13×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

Pricing verified on both sides — Input and output rates are verified for both models.
3/5 core specs verified on both sides — Not published for at least one side: max output, reasoning levels.
1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
Verified within the last 90 days — Newest catalog check was 2 days ago.
Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Mistral Medium 3.5: Mistral docs — Mistral Medium 3.5 (26.04) (accessed 2026-09-26)
Mistral Medium 3.5: Mistral — Vibe remote agents and Mistral Medium 3.5 (accessed 2026-09-26)
Mistral Medium 3.5: Mistral changelog (2026-04-28) (accessed 2026-09-26)
Mistral Small 4: Mistral docs — Mistral Small 4 (26.03) (accessed 2026-09-26)
Mistral Small 4: Mistral changelog (accessed 2026-09-26)

Related comparisons

Diving deeper on one model? Mistral Medium 3.5 · Mistral Small 4

Common questions

Mistral Medium 3.5 vs Mistral Small 4

Answered from the verified figures on this page rather than general guidance.

Is Mistral Medium 3.5 or Mistral Small 4 cheaper for input?

Mistral Small 4 is cheaper at $0.15 per million input tokens, against $1.50 for Mistral Medium 3.5 — roughly 10× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Mistral Medium 3.5 has tiered pricing: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense. Mistral Small 4 has tiered pricing: Mistral first-party API $0.15/$0.60 per MTok. Open weights (Apache 2.0). 119B total / 6.5B active MoE.

Is Mistral Medium 3.5 or Mistral Small 4 cheaper for output?

Mistral Small 4 is cheaper at $0.60 per million output tokens, against $7.50 for Mistral Medium 3.5 — roughly 13× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Mistral Medium 3.5 has tiered pricing: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense. Mistral Small 4 has tiered pricing: Mistral first-party API $0.15/$0.60 per MTok. Open weights (Apache 2.0). 119B total / 6.5B active MoE.

Which has the larger context window, Mistral Medium 3.5 or Mistral Small 4?

Both accept about 262K tokens of context, so document length will not decide between them.

Should I use Mistral Medium 3.5 or Mistral Small 4?

Mistral Medium 3.5 is the frontier tier and Mistral Small 4 the budget tier. The useful question is whether your hardest task actually fails on the cheaper one — most production volume such as classification, extraction and summarisation does not.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

Input price: Mistral Small 4 costs $0.15 per 1M tokens versus $1.50 for Mistral Medium 3.5 — a 10x difference at the headline tier.
Positioning: Mistral Medium 3.5 sits in the frontier tier, Mistral Small 4 in the budget tier — most production volume (classification, extraction, summarisation) does not need the pricier tier.

Run the model picker Estimate stack cost All model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.