Command R7B (12-2024)
Command R7B (12-2024) is a large language model made by Cohere, added to the catalog on 14 Dec 2024. It has a context window of 128,000 tokens and costs $0.0375 per 1M input tokens and $0.15 per 1M output tokens. It accepts text and produces text. Typical uses: enhance multi-step reasoning tasks, deploy in agent-based systems and integrate with tool use applications.
Price checked ยท source: OpenRouter
What Command R7B (12-2024) is
Cohere's Command R7B, released in December 2024, is a compact and efficient update to the Command R+ series. With a substantial context window of 128,000 tokens, this model is designed to handle complex reasoning tasks and multi-step processes effectively. It operates in a text-to-text modality, making it suitable for a wide range of applications that require text input and output. Key capabilities include Retrieval-Augmented Generation (RAG), tool use, and agent-based tasks. Users can fine-tune the model's behavior using parameters like frequency penalty, max tokens, and temperature. This flexibility allows for tailored responses in diverse scenarios, ensuring that the model meets specific needs.
Key features
- 128,000 token context window
- Text-to-text modality
- Supports complex reasoning
- Optimized for RAG and tool use
- Customizable with various parameters
Typical uses
- Enhance multi-step reasoning tasks
- Deploy in agent-based systems
- Integrate with tool use applications
- Implement Retrieval-Augmented Generation
- Customize outputs for specific needs
Command R7B (12-2024) pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.0375 |
| Output, per 1M tokens | $0.15 |
No price change since it was added on 14 Dec 2024.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0011 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0014 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0059 |
Command R7B (12-2024) specifications
| Model id | cohere/command-r7b-12-2024 |
|---|---|
| Version | command-r7b-12-2024 |
| Context window | 128,000 tokensAbout 96,000 English words |
| Max output | 4,000 tokens |
| Knowledge cutoff | 2024-08-31 |
| Added to catalog | 14 Dec 2024 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
Artificial Intelligence (AI) has the potential to revolutionize various aspects of our lives, including work, leisure, and creativity, in numerous positive ways: **Work:** AI can automate repetitive and mundane tasks, freeing up human workers to focus on more complex and creative work. This can increase productivity and efficiency, leading to economic growth. AI-powered tools can also enhance decision-making by providing data-driven insights, improving accuracy, and reducing human error. **Leisure:** In leisure, AI can personalize experiences by analyzing user preferences and behavior. It can recommend tailored entertainment, travel, and dining options, making leisure activities more enjoyable and engaging. Additionally, AI-powered virtual assistants can manage schedules, making it easier to organize and optimize free time. **Creativity:** AI can augment human creativity by providing new tools and inspiration. Generative AI models can create art, music, and writing, opening up new avenues for artistic expression. It can also assist in content creation, helping writers and artists overcome creative blocks and explore new ideas. Furthermore, AI can analyze vast amounts of data to identify patterns and trends, inspiring innovative solutions and ideas.
Compare Command R7B (12-2024)
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.