AI Index

GPT-5.6 TerravsMistral Medium 3.5

Both language models, compared at each maker’s own API list prices. Every figure links to its source.

Compare at your usage

Every model priced for the same request
Prompt per request
Cache hits
Batch
Service tier

8,000 tokens in, 2,000 out

GPT-5.6 Terra on OpenAI APIMistral Medium 3.5
Rate appliedBase rateNot offered: no current API price
Inputper 1M tokens$2.00 —
Cache readper 1M tokens$0.20 —
Outputper 1M tokens$12.00 —
Cost per request$0.040—
Per 1,000 requests$40.00—

Every model is priced for the same request at its maker’s own list prices (each with its source and date), so bold marks the cheapest. A model that can’t serve the request is named, not ranked; a condition its seller doesn’t price says which rate was used.

Where each stands among all scored models

Each line runs from the lowest to the highest score on the board; the tick is the median.

Epoch Capabilities Index#14 vs #93 of 118Mistral Medium 3.5: 141.6GPT-5.6 Terra: 160.9LMArena Text#34 vs #77 of 163Mistral Medium 3.5: 1,426GPT-5.6 Terra: 1,467LMArena Text · Coding#35 vs #74 of 163Mistral Medium 3.5: 1,477GPT-5.6 Terra: 1,517LMArena Vision#31 vs #56 of 89Mistral Medium 3.5: 1,223GPT-5.6 Terra: 1,271
  • GPT-5.6 Terra
  • Mistral Medium 3.5

Key differences

GPT-5.6 TerraMistral Medium 3.5
Context
1,050,000 GPT-5.6 Terra model · as of Nov 4, 2026
256,000 Mistral docs: mistral-medium-3-5-26-04 · as of Nov 3, 2026

These differences use verified vendor specifications or each maker’s official API on the same region, currency, meter and billing conditions. Different conditions remain side by side in the full table; they do not establish which model is cheaper. Declared features describe support, not measured quality or a recommendation. Missing evidence does not mean a feature is unsupported.

Full comparison

GPT-5.6 Terra OpenAI Mistral Medium 3.5 Mistral AI
Overview
ReleasedJul 9, 2026 Apr 28, 2026
Open weights— Yes
Knowledge cutoffFeb 2026 Not stated
Specs
Context1.05M 256K
Max input922K Not stated
Max output128K 262.14K
Input modalitiesText, Image Text, Image
Output modalitiesText Text
ReasoningYes Yes
Reasoning effortsnone, low, medium, high, xhigh, max none, high
Reasoning can be offYes Yes
Tool useYes Yes
Structured outputYes Yes
Pricing · per 1M tokens
Input price$2.00Also priced under other conditions: Batch, Flex tier, Fast tier, Prompts over 272K tokens —
Output price$12.00Also priced under other conditions: Batch, Flex tier, Fast tier, Prompts over 272K tokens —
Cache read price$0.20Also priced under other conditions: Batch, Flex tier, Fast tier, Prompts over 272K tokens —
Cache write pricefrom $2.50Also priced under other conditions: 12-hour cache, Prompts over 272K tokens, Batch, Flex tier, Fast tier30-minute cache —
Blended price (3 input : 1 output)$4.50 —
Pricing under conditions · per 1M tokens
Input price, long prompts$4.00Prompts over 272K tokens —
Output price, long prompts$18.00Prompts over 272K tokens —
Batch input price$1.00Batch —
Batch output price$6.00Batch —
Flex tier input price$1.00Flex tier —
Flex tier output price$6.00Flex tier —
Cited scores
Epoch Capabilities Index160.9 141.6
LMArena Text1,467 xhigh effort1,426
LMArena Text · Coding1,517 xhigh effort1,477
LMArena Vision1,271 xhigh effort1,223
LMArena Text · Chinese1,516 xhigh effort1,448
Epoch AI · GPQA Diamond93.3% max effort—
Epoch AI · FrontierMath Tiers 1–386% max effort—

Headline prices may come from different channels, regions or tiers. Check each source before choosing a model; missing facts stay blank.

Model details and sources

Cited scores