Model comparison

GPT-6 Luna vs Mistral Small 4

OpenAI against Mistral, compared on context, price, and verified benchmark results.

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

OpenAI

GPT-6 Luna

Budget

Mistral

Mistral Small 4

Budget · Open weights

AI model capability comparison
Specification	GPT-6 Luna	Mistral Small 4
Provider
Provider	OpenAI	Mistral
Tier
Tier	Budget	Budget
Context window
Context window	Winner: 1.05M	262K
Max output
Max output	128K	Not verifiedUnverified
Input / 1M tokens
Input / 1M tokens	Winner: $0.10	$0.15
Output / 1M tokens
Output / 1M tokens	Winner: $0.50	$0.60
Weights
Weights	Closed	Open
Parameters
Parameters	GPT-6 low-cost tier	119B total / 6.5B active (MoE)
Reasoning levels
Reasoning levels	none, low, medium, high, xhigh, max	Not verifiedUnverified
Modalities
Modalities	text, image	text, image
License
License	Not disclosedUnverified	Apache 2.0
API model id
API model id	gpt-6-luna	mistral-small-2603
Released
Released	September 22, 2026	March 16, 2026
Artificial Analysis Intelligence Index [max] (2026-09-26)
Artificial Analysis Intelligence Index [max] (2026-09-26)	37.3	Not verifiedUnverified
Artificial Analysis Intelligence Index (2026-09-26)
Artificial Analysis Intelligence Index (2026-09-26)	Not verifiedUnverified	11.3
DeepSWE 1.1 [max] (2026-09-22)
DeepSWE 1.1 [max] (2026-09-22)	66.6	Not verifiedUnverified

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.
2026-09-22
OpenAI — Introducing GPT-6 Sol and Luna (vendor; not yet on Datacurve's board)
Agentic software engineering: pass@1 on real repo tasks with reported cost per completed task.
Directly comparable

Pricing tiers

GPT-6 Luna: Direct successor to GPT-5.6 Luna at half the price. Cached input $0.01/MTok; cache writes $0.125. Above 272K input the whole request bills $0.20/$0.75 ($0.02 cached). Batch/Flex $0.05/$0.25; Fast mode $0.20/$1.00. Knowledge cutoff May 18 2026.

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

BudgetRecord checked September 26, 2026

GPT-6 Luna

GPT-6 Luna is OpenAI's cheapest current model at $0.10/$0.50 — the direct successor to GPT-5.6 Luna at half the price, with the full 1.05M-token context.

Best for

High-volume chat and extraction
Classification
Cost-capped agent loops

Watch out

Small tier: it matches GPT-5.6 Luna on the Artificial Analysis index but sits well below GPT-6 Sol on hard reasoning; the DeepSWE figure is vendor-reported at max effort.

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

GPT-6 Luna is cheaper on output at $0.50 per million tokens against $0.60 for Mistral Small 4 — about 1.2×. 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.

GPT-6 Luna: OpenAI — Introducing GPT-6 Sol and Luna (accessed 2026-09-26)
GPT-6 Luna: OpenAI model docs — gpt-6-luna (1.05M context, 128K output) (accessed 2026-09-26)
GPT-6 Luna: OpenAI API pricing (gpt-6-luna $0.10/$0.50, cached $0.01) (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? GPT-6 Luna · Mistral Small 4

Common questions

GPT-6 Luna vs Mistral Small 4

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

Is GPT-6 Luna or Mistral Small 4 cheaper for input?

GPT-6 Luna is cheaper at $0.10 per million input tokens, against $0.15 for Mistral Small 4 — roughly 1.5× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-6 Luna has tiered pricing: Direct successor to GPT-5.6 Luna at half the price. Cached input $0.01/MTok; cache writes $0.125. Above 272K input the whole request bills $0.20/$0.75 ($0.02 cached). Batch/Flex $0.05/$0.25; Fast mode $0.20/$1.00. Knowledge cutoff May 18 2026. 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 GPT-6 Luna or Mistral Small 4 cheaper for output?

GPT-6 Luna is cheaper at $0.50 per million output tokens, against $0.60 for Mistral Small 4 — roughly 1.2× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-6 Luna has tiered pricing: Direct successor to GPT-5.6 Luna at half the price. Cached input $0.01/MTok; cache writes $0.125. Above 272K input the whole request bills $0.20/$0.75 ($0.02 cached). Batch/Flex $0.05/$0.25; Fast mode $0.20/$1.00. Knowledge cutoff May 18 2026. 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, GPT-6 Luna or Mistral Small 4?

GPT-6 Luna accepts 1.05M tokens against 262K for Mistral Small 4. This only matters if you routinely send very long documents or large codebases.

Should I use GPT-6 Luna or Mistral Small 4?

Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. GPT-6 Luna suits high-volume chat and extraction; Mistral Small 4 suits cheap eu-hosted inference.

Can I self-host GPT-6 Luna or Mistral Small 4?

Mistral Small 4 publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. GPT-6 Luna is a closed model whose supported access paths are controlled by its provider.

Next step

Choosing between them

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

Input price: GPT-6 Luna costs $0.10 per 1M tokens versus $0.15 for Mistral Small 4 — a 1.5x difference at the headline tier.
Context: GPT-6 Luna takes 1.05M against 262K for Mistral Small 4 — only decisive if your prompts approach the smaller window.
Deployment: Mistral Small 4 publishes weights you can self-host; the other is API-only.

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.