tokenstat
tokenstat

Cohere: Command A

cohere/command-a · rates as of · How this catalog is built · Benchmarks

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

Cheapest input
$1.56
$/MTok · LiteLLM
Cheapest output
$1.56
$/MTok
Context
256K
tokens
Sources
3
14 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $5.05 → $1.56
  • ↑ higherInput $0.63 → $1.56
  • ↓ lowerOutput $10 → $5.05
  • ↓ lowerInput $2.50 → $0.63

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
LiteLLMcheapestcohere.command-a-reasoningN/A$1.56$1.56$0.156N/A
LiteLLMcheapestoci/cohere.command-a-reasoningN/A$1.56$1.56$0.156N/A
models.devcohere/command-aKilo Gateway$2.50$10$0256K
OpenRoutercohere/command-aOpenRouter$2.50$10$0256K
models.devcohere/command-aVercel AI Gateway$2.50$10$0256K
models.devcohere-command-aAzure$2.50$10$0131K
models.devcohere-command-aAzure$2.50$10$0131K
models.devcohere--command-a-reasoningSAP AI Core$2.50$10$0256K
LiteLLMcohere/command-aN/A$2.50$10$0.25N/A
LiteLLMcohere-command-aN/A$2.50$10$0.25N/A
LiteLLMazure_ai/cohere-command-aN/A$2.50$10$0.25N/A
LiteLLMcommand-aN/A$2.50$10$0.25N/A
LiteLLMvercel_ai_gateway/cohere/command-aN/A$2.50$10$0.25N/A
models.devcohere/command-aAI/ML API$2.65$10.58$0256K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2024-08-31Released: 2025-08-21Output limit: 8K tokensFamily: command-a

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.