← Model list

Command A

cohere·cohere/command-a-03-2025·GA·Open weights·command-a series

Cohere command model for multilingual enterprise agents, tools, and chat

At a glance
Official price$2.50 / $10.00 per 1M
Cache read · Cohere
Lowest paid$2.50 / $10.00
OpenRouter Gateway · 1× spread
Context256,000
⚠ Providers report 131,072–288,000; the table below is authoritative
Output limit8,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2024-06-01
Released / updated2025-03-13 / 2025-03-13

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence22.8
Value5
Coding27.8
Agentic9.2
Output speed207 tok/s
TTFT0.38 s
Cost per task$0
Value formulaIQ 22.8 ÷ min blended $4.375 = 5
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
defaultIQ 7.5 · 60 tok/s
defaultIQ 22.8 · 207 tok/s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 6 providers6 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
OpenRouter
cohere/command-a
Gateway$2.50$10.00256,0008,192
CohereOfficialFirst-party$2.50$10.00256,0008,000
Azure Cognitive Services
cohere-command-a
First-party$2.50$10.00131,0728,192
Azure
cohere-command-a
First-party$2.50$10.00131,0728,192
Vercel AI Gateway
cohere/command-a
Cloud$2.50$10.00256,0008,000
Eden AIGateway$2.50$10.00288,0008,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1OpenRouter$1,000.00
2Cohere · Official$1,000.00
3Azure Cognitive Services$1,000.00
4Azure$1,000.00
5Vercel AI Gateway$1,000.00
6Eden AI$1,000.00
Switch to OpenRouter to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark1 items

NameConditionsScoreMetricSource
Aider Polyglot12percent correctSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$10.00$02026-08-052026-08-132026-08-05 · Input list $2.502026-08-06 · Input list $2.502026-08-07 · Input list $2.502026-08-08 · Input list $2.502026-08-09 · Input list $2.502026-08-10 · Input list $2.502026-08-11 · Input list $2.502026-08-12 · Input list $2.502026-08-13 · Input list $2.502026-08-05 · Output list $10.002026-08-06 · Output list $10.002026-08-07 · Output list $10.002026-08-08 · Output list $10.002026-08-09 · Output list $10.002026-08-10 · Output list $10.002026-08-11 · Output list $10.002026-08-12 · Output list $10.002026-08-13 · Output list $10.002026-08-05 · Min blended $4.382026-08-06 · Min blended $4.382026-08-07 · Min blended $4.382026-08-08 · Min blended $4.382026-08-09 · Min blended $4.382026-08-10 · Min blended $4.382026-08-11 · Min blended $4.382026-08-12 · Min blended $4.382026-08-13 · Min blended $4.38