Cohere · language model
Command R7B (12-2024): pricing, context and benchmarks
Command R7B (12-2024) is a language model from Cohere released on December 14, 2024. It costs $0.04 per million input tokens and $0.15 per million output tokens, with a 128K-token context window. No independent score has been published for it so far.
| Price | 29/30 | |
|---|---|---|
| Context | 3/15 | |
| Features | 3/15 |
What you need to know about Command R7B (12-2024)
Command R7B (12-2024) was released by Cohere (Canada) on December 14, 2024. It accepts text as input and produces text. Its context window reaches 128,000 tokens, larger than 19 % of the models in the registry, and it can write up to 4,000 tokens in one go.
Released more than 1 year ago, it belongs to a generation most vendors have since superseded.
Command R7B (12-2024) pricing
On OpenRouter, Command R7B (12-2024) costs $0.04 per million input tokens and $0.15 per million output tokens. Counting three tokens read for every token written, its average price is $0.066 per million, more expensive than 4 % of paid models (11.6 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0002. At 1,000 tasks a day, budget $5 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for Command R7B (12-2024). We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It does not support tool calling: it is not suited to driving an AI agent that has to act.
- It can answer in an enforced JSON format (structured outputs).
- Its knowledge stops at August 2024.
Its weights are not published: it can only be used through the Cohere API or a broker such as OpenRouter, which means sending your data off your machines.
Other Cohere models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Command A+ | Sep 22, 2026 | $0.6 | — |
| North Mini Code | Jun 17, 2026 | Free | — |
| Command A | Mar 13, 2025 | $4.38 | — |
| Command R (08-2024) | Aug 30, 2024 | $0.26 | — |
| Command R+ (08-2024) | Aug 30, 2024 | $4.38 | — |
Verdict
Command R7B (12-2024) scores 58/100 on our grid, which only uses published figures.
Strengths
- Low price: cheaper than 96 % of paid models.
Limitations
- No tool calling: unusable as an agent's brain.
- No independent score published: performance cannot be verified.
- Older generation, often replaced by a newer model from the same vendor.
- Text only: reads neither images nor files.
Avoid if…
- your data must not leave your servers;
- you are building an agent that must call tools.
Alternatives
- Schematron V2 Turbo$0.06
- Nova Micro 1.0$0.06
- Granite 4.0 Micro$0.04
- Schematron V2 Small$0.1
- Gemma 3 12B$0.08
- Llama 3.2 1B Instruct$0.07
Comparisons and tools
Learn more
Frequently asked questions
How much does Command R7B (12-2024) cost?
$0.04 per million input tokens and $0.15 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0002.
How big is Command R7B (12-2024)'s context window?
128,000 tokens, roughly 96,000 words, with a maximum of 4,000 output tokens.
Can Command R7B (12-2024) run locally?
No, Cohere does not publish its weights: it is API-only.
Is Command R7B (12-2024) suitable for an AI agent?
No: without tool calling it cannot act, only answer.
What are the alternatives to Command R7B (12-2024)?
The closest models on price and performance are Schematron V2 Turbo, Nova Micro 1.0, and Granite 4.0 Micro.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score