Cohere · AI model
Command R7B
Smallest and fastest model in Cohere's R family (December 2024) for RAG, tool use and agents; 128K context, 4K output; $0.0375 input / $0.15 output per 1M tokens.
Last verified Available 5 sources
Key specs
- Provider
- Cohere
- Family
- Command R
- API identifier
- command-r7b-12-2024
- Availability
- Available
- Release date
- 2024-12-13
- License
- Open weights (CC-BY-NC 4.0 License with Acceptable Use Addendum)
- Context window
- 128,000 tokens
- Max output
- 4,000 tokens
- Knowledge cutoff
- June 2024
- API access
- Yes
- Consumer app
- No
Capabilities
Inputs
- Text input Yes
- Image input No Image Inputs marked as not supported in the capabilities panel on the model's docs page; docs model table lists modality as Text
- Audio input No Docs model table lists modality as Text only
- Video input No Docs model table lists modality as Text only
- File input Unknown
Outputs
- Text output Yes
- Image output No Docs model table lists modality as Text only
- Audio output No Docs model table lists modality as Text only
Features
- Reasoning None Reasoning marked as not supported in the capabilities panel on the model's docs page
- Tool calling Yes
- Web search Unknown
"Unknown" means we have not verified this capability yet; it does not mean the model lacks it.
Pricing
Estimate your monthly cost →| Dimension | Tier | Price | Since | Verified | Source |
|---|---|---|---|---|---|
| Input tokens | base | $0.0375 per 1M tokens | 2026-10-12 | 2026-10-25 | Pricing | Secure and Scalable Enterprise AI | Cohere Also listed on the Command R7B docs page |
| Output tokens | base | $0.15 per 1M tokens | 2026-10-12 | 2026-10-25 | Pricing | Secure and Scalable Enterprise AI | Cohere Also listed on the Command R7B docs page |
Prices are shown in the currency the provider publishes; we never convert currencies.
Compare Command R7B
Guides
About Command R7B
Command R7B is the smallest and fastest model in Cohere's R family, released on December 13, 2024. It is documented for retrieval-augmented generation, tool use and agents, has a 128,000-token context window, and its size allows deployment on consumer GPUs and CPUs, including on-device inference. Weights are published under a non-commercial CC-BY-NC 4.0 licence.
Strengths and weaknesses
Strengths
- Listed at $0.0375 input / $0.15 output per 1M tokens, the lowest token price on cohere.com/pricing
- 128,000-token context window
- Documented for RAG, tool use and multi-step agents
- Can run on consumer GPUs and CPUs (per Cohere)
Weaknesses
- Maximum output of 4,000 tokens
- Text-only input
- No reasoning mode (per its docs page)
Sources
Last verified Page updated 2026-10-13