Cohere models & pricing

Cohere hosts 22 models (22 with public pricing) covering 4 modalities. Command R+ chat, Embed v3 multilingual embeddings, Rerank, and enterprise RAG models. Cheapest input starts at $0.1000/M tokens; the most premium goes up to $100/M. Use Future AGI's Agent Command Center to route any Cohere model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗
22

embedding 8

Model Input / 1M Output / 1M Context Caps
Embed English Light v2.0 $0.1000/M 1,024
Embed English Light v3.0 $0.1000/M 1,024
Embed English v2.0 $0.1000/M 4,096
Embed English v3.0 $0.1000/M 1,024
Embed Multilingual v2.0 $0.1000/M 768
Embed Multilingual v3.0 $0.1000/M 1,024
Embed v4.0 $0.120/M 128,000
Embed Multilingual Light v3.0 $100/M 1,024

chat 7

Model Input / 1M Output / 1M Context Caps
Command R $0.150/M $0.600/M 128,000 tools
Command R 08.2024 $0.150/M $0.600/M 128,000 tools
Command R7b 12.2024 $0.150/M $0.0375/M 128,000 tools
Command Light $0.300/M $0.600/M 4,096
Command A 03.2025 $2.50/M $10.00/M 256,000 tools
Command R+ $2.50/M $10.00/M 128,000 tools
Command R Plus 08.2024 $2.50/M $10.00/M 128,000 tools

rerank 5

Model Input / 1M Output / 1M Context Caps
Rerank English v2.0 4,096
Rerank English v3.0 4,096
Rerank Multilingual v2.0 4,096
Rerank Multilingual v3.0 4,096
Rerank v3.5 4,096

completion 2

Model Input / 1M Output / 1M Context Caps
Command $1.00/M $2.00/M 4,096
Command Nightly $1.00/M $2.00/M 4,096

FAQ

How many Cohere models are there?

22 Cohere models are listed across 4 modalities on this page. 22 have public per-token pricing.

How is Cohere pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which Cohere model is cheapest?

Input pricing on Cohere starts at $0.1000 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.

Can I route to Cohere via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Cohere target, and call Cohere models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any Cohere model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.