Provider

Cohere

Every Cohere model UltraGPT can reach, kept in sync with the live catalog — pricing, context window and capabilities for each one.

5 models from Cohere Up to 256K tokens of context 1 free to run
Open the appBrowse every provider

5

Models tracked

1

Providers

1

Reasoning models

0

See images (vision)

256K

Largest context window

1

Free to run

Directory

All Cohere models.

Search and filter this provider's lineup — pricing per million tokens, context window, modalities, reasoning effort and independent benchmark scores where available.

5 of 5 models

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

StreamingJSON mode
Context window256K tok
Max output8.2K tok
ReleasedMar 13, 2025
Knowledge cutoffAug 31, 2024
TextText
Input$2.5 / 1M tok
Output$10 / 1M tok
Intelligence13.9
Coding27.8
Agentic3.6

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

Tool callingStreamingJSON mode
Context window128K tok
Max output4K tok
ReleasedAug 30, 2024
Knowledge cutoffMar 31, 2024
TextText
Input$0.15 / 1M tok
Output$0.6 / 1M tok

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

Tool callingStreamingJSON mode
Context window128K tok
Max output4K tok
ReleasedAug 30, 2024
Knowledge cutoffMar 31, 2024
TextText
Input$2.5 / 1M tok
Output$10 / 1M tok

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

Tool callingStreamingJSON mode
Context window128K tok
Max output4K tok
ReleasedDec 2, 2024
Knowledge cutoffAug 31, 2024
TextText
Input$0.037 / 1M tok
Output$0.15 / 1M tok

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

ReasoningTool callingStreaming
Context window256K tok
Max output64K tok
ReleasedJun 17, 2026
Knowledge cutoff
TextText
InputFree
OutputFree
Coding36.5
Agentic1.1

Every Cohere model above, one subscription away.

UltraGPT puts this whole directory behind a single login and one flat monthly price — no separate bill per provider.