AI Models · Open-Source vs Open-Source

Mistral Large 4 Open vs Mistral Medium 3.5 Open

Mistral Large 4 vs Mistral Medium 3.5 compared — price per token, context window, multimodality, openness and which to choose. Full 2026 breakdown.

Prices & specs refreshed from live data · olud.ai

Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.

Mistral Large 4OpenMistral AI
$1.36 /M input
$4.18 /M outputNo per-token fees if you self-host
TypeOpen-weight
Context window1M tokens
MultimodalYes
Self-hostYes
Mistral Medium 3.5OpenMistral AI
$1.5 /M input
$7.5 /M outputNo per-token fees if you self-host
TypeOpen-weight
Context window262K tokens
MultimodalYes
Self-hostYes
Choose Mistral Large 4 for the lower output price ($4.18/M vs $7.5/M). It also gives you the larger 1M context window.

Mistral Large 4 vs Mistral Medium 3.5 specs

SpecMistral Large 4Mistral Medium 3.5Winner
MakerMistral AIMistral AI–
TypeOpen-weightOpen-weight–
Context window1M tokens262K tokensMistral Large 4
Input price$1.36/M · free self-host$1.5/M · free self-hostMistral Large 4
Output price$4.18/M · free self-host$7.5/M · free self-hostMistral Large 4
Vision / multimodalYesYes= Tie
Tool / function callingYesYes= Tie
Self-hostableYesYes= Tie
LicenseApache 2.0Apache 2.0–

Price gap & when to choose each

1.8×cheaper per output token

Mistral Large 4 is ~1.8× cheaper than Mistral Medium 3.5 on output tokens ($4.18 vs $7.5 per M tokens).

Choose Mistral Large 4 if…
  • You want to self-host or run on your cloud
  • You need the longer 1M context window
  • You prioritize data privacy & control
  • You want the lowest operating costs
  • You are building open or reproducible AI
Choose Mistral Medium 3.5 if…
  • You want to self-host or run on your cloud
  • You prioritize data privacy & control
  • You are building open or reproducible AI

Feature comparison

CapabilityMistral Large 4Mistral Medium 3.5
Open weights (downloadable)✓✓
Self-hostable✓✓
Runs fully offline✓✓
Vision / multimodal✓✓
Tool / function calling✓✓
1M+ context window✓✗

Benchmarks: Mistral Large 4 vs Mistral Medium 3.5

Independent benchmark scores measured by Artificial Analysis. Higher is better (except latency).

Mistral Large 4 delivers 4× more intelligence per dollar.
Mistral Large 4
Mistral Medium 3.5
Intelligence index
38.4
14.2
Humanity's Last Exam
35%
13.8%
Long Context Reasoning
81.3%
69.3%
SciCode
54.2%
40.2%
Coding index
–
46.9
GPQA
–
74.8%
IFBench
–
68.8%
τ²-Bench
–
94.2%
τ-Bench Banking
–
15.1%
Terminal-Bench
–
50.6%
Terminal-Bench Hard
–
33.3%
Speed
79.4 tok/s
154.2 tok/s
Latency
1.03s
0.79s
Intelligence per $
18.6
4.7

Benchmark data by Artificial Analysis.

How Mistral Large 4 and Mistral Medium 3.5 score

🤝 Neck and neck on these criteria (4.8 vs 4.6 / 5).
CriterionMistral Large 4Mistral Medium 3.5
Cost-efficiency4.04.0
Context window5.04.0
Openness5.05.0
Self-hosting5.05.0
Multimodality5.05.0

Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.

What each model is

Mistral Large 4 Open

Mistral AI · Open-weight

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

Mistral Medium 3.5 Open

Mistral AI · Open-weight

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...

Other models in these families

These variants are tracked but not compared here — one page per family keeps the comparison readable.

Other variants tracked
Mistral Medium 3.5Mistral Medium 3.5 (batch)Mistral Small 4Mistral Small 4 (batch)Mistral Large 3 2512Mistral Large 3 2512 (batch)Mistral Medium 3.1Mistral Medium 3.1 (batch)Mistral Medium 3Devstral 2 2512Mistral Small 3.1 24BMistral Small 3.2 24BMistral LargeMistral Large 2407Mistral Small 3SabaMinistral 3 14B 2512Mixtral 8x22B InstructMinistral 3 8B 2512Ministral 3 8B 2512 (batch)Ministral 3 3B 2512UncensoredCodestral 2508Codestral 2508 (batch)Voxtral Small 24B 2507Mistral Nemo
Other variants tracked
Mistral Large 4Mistral Medium 3.5 (batch)Mistral Small 4Mistral Small 4 (batch)Mistral Large 3 2512Mistral Large 3 2512 (batch)Mistral Medium 3.1Mistral Medium 3.1 (batch)Mistral Medium 3Devstral 2 2512Mistral Small 3.1 24BMistral Small 3.2 24BMistral LargeMistral Large 2407Mistral Small 3SabaMinistral 3 14B 2512Mixtral 8x22B InstructMinistral 3 8B 2512Ministral 3 8B 2512 (batch)Ministral 3 3B 2512UncensoredCodestral 2508Codestral 2508 (batch)Voxtral Small 24B 2507Mistral Nemo

Frequently asked questions

Mistral Large 4 vs Mistral Medium 3.5 — which is cheaper?

Mistral Large 4 is cheaper on output ($4.18/M vs $7.5/M).

Which has the larger context window?

Mistral Large 4 offers the larger context window (1M tokens).

Mistral Large 4 vs Mistral Medium 3.5 — which should I pick in 2026?

Choose Mistral Large 4 for the lower output price ($4.18/M vs $7.5/M). It also gives you the larger 1M context window.

People also compare

DeepSeek V4.1 Flash 1017 vs Mistral Medium 3.5GLM 5.3 (batch) vs Mistral Medium 3.5Hy3 vs Mistral Medium 3.5MiMo-V2.6-Pro vs Mistral Medium 3.5Nemotron 3.5 Super VL vs Mistral Medium 3.5Kimi K3 (batch) vs Mistral Medium 3.5

Explore more open-source AI

Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.

Open the leaderboard →