Command A
Pricing & Specs

Cohere · $2.5 input / $10 output per 1M tokens · 256K context window

$2.5
per 1M input tokens
$10
per 1M output tokens
256K
context window (tokens)

The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on Command A costs about $0.0075 — roughly $7.50 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.

Command A API Pricing

TokensPrice
Input$2.5 / 1M tokens
Output$10 / 1M tokens

No cache pricing is published. Batch pricing is not documented.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0075
1K 1,000 runs of that task: $7.50
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

Command A Specs

SpecValue
Context window256K tokens
Input modalitiestext
Output modalitiestext
Latency (measured by OpenMark)~238ms median response
Reasoning modelNo
Tool / function callingYes
JSON modeYes
StreamingYes
Prompt cachingNo

Capabilities

tool use agents RAG multilingual streaming structured outputs

Notes

Blocked by GCP geo-IP false positive (DO IP classified as RU). Ticket open with DO.

FAQ

How much does Command A cost?

Command A costs $2.5 per 1M input tokens and $10 per 1M output tokens.

What is Command A's context window?

Command A has a 256K-token context window.

Can I test Command A on my own task?

Yes. OpenMark lets you benchmark Command A against 100+ models on your own task with real API calls — no API keys needed, free tier available.

Is Command A the right model for YOUR task?

Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.

Benchmark Command A — Free →