Models · Cohere
Command
Cohere Command is an enterprise-focused model optimized for agentic workflows, RAG applications, and multilingual tasks. It excels at tool use, structured output, and working with business data across languages.
Input $1.00 per 1M tokens
Output $2.00 per 1M tokens
Context 128K tokens · $3.00 combined per 1M
Benchmark performance
Source: Artificial Analysis. Updated 2026-09-20.
Key strengths
- — Excellent for RAG and enterprise search
- — Strong multilingual capabilities
- — Great structured JSON output
- — Purpose-built for business applications
Best use cases
- Enterprise RAG and knowledge retrieval
- Structured data extraction
- Multilingual business automation
- Document understanding and Q&A
Pricing details
| Input (per 1M tokens) | $1.00 |
| Output (per 1M tokens) | $2.00 |
| Context window | 128K tokens |
| Architecture | Enterprise-optimized transformer, 128K context, tuned for tool use and structured outputs |
| Provider | Cohere |
Agentic, multilingual
Recent coverage
TypeSafe’s Jev AI cuts costs 444x by outputting typed decisions, not text
OpenClaw 2026.9.5 Fixes Update Crashes With Atomic Rollbacks
GPT-6 Astra stabs doll in 17 of 20 RoboHarm safety tests
U.S. Troops Nearly Boarded Chinese Ship Over AI Hallucination
Grok Voice 2.0 cuts word errors by 67% for short phrases at $0.10/hr
The sharpest AI news, curated daily.
One email each morning. Summarized, sourced, and skimmable in under three minutes.
Pricing data is sourced from official API documentation and updated weekly. Actual costs may vary based on prompt caching, batch processing, service tiers, and regional pricing. Inblix is not affiliated with Cohere.