Command A
Cohere · 2 thinking configurations
Intelligence7.0
Input / 1M$2.50
Output / 1M$10.00
Context256K
Tariff: Cohere · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 1 without both values
Selected: thinking default · Click a point to switch configuration
Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
7.0 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
52.7 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
4.0 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
15.2 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
36.5 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
16.4 %Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputYes
Speed59.8 tok/s
First token1.71 s
Maximum output64K
Catalog listing date2026-09-22