Command A+
Command A+ is a large language model made by Cohere, added to the catalog on 22 Sep 2026. It has a context window of 192,000 tokens and costs $0.30 per 1M input tokens and $1.50 per 1M output tokens. It accepts text and images and produces text. Typical uses: tool-assisted enterprise workflows, reasoning over long prompts and working with image and text inputs.
Price checked · source: OpenRouter
What Command A+ is
Cohere Command A+ is a text-generating model from Cohere. It accepts text and image inputs and produces text. The catalog describes it as a model for enterprise agentic workflows. Its context window holds up to 192,000 tokens, and its maximum output is 64,000 tokens. The context figure describes the amount of input context available to a request, while the output limit sets the stated maximum length of a generated response. Requests can include either listed input type, with text as the model’s listed output. The model also supports reasoning.
Command A+ supports native tool calling with strict tool schemas, as well as structured outputs and response-format controls. These features are relevant to workflows that invoke tools or need responses arranged in a defined format. Its 192K-token context can accommodate substantial input, and image input can be included when visual material is part of a task. The stated context and output limits are useful to consider for tasks involving lengthy inputs or longer text responses. Potential tasks include tool-assisted enterprise workflows, reasoning over provided text, handling requests that include images, and generating structured text. The catalog does not specify particular tools, image-processing functions, or supported schema formats, so the description is limited to the listed capabilities. It also does not identify a specialized output type beyond text.
Key features
- Accepts text and image inputs and produces text.
- Has a 192,000-token context window and a 64,000-token maximum output.
- Supports native tool calling with strict tool schemas.
- Supports structured outputs, response formats, and reasoning.
Typical uses
- Tool-assisted enterprise workflows
- Reasoning over long prompts
- Working with image and text inputs
- Producing structured text responses
Command A+ pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.30 |
| Output, per 1M tokens | $1.50 |
| Cached input read, per 1M tokens | $0.15 |
No price change since it was added on 22 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0006 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0087 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.012 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.047 |
Command A+ specifications
| Model id | cohere/command-a-plus |
|---|---|
| Version | command-a-plus-05-2026 |
| Context window | 192,000 tokensAbout 144,000 English words |
| Max output | 64,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 22 Sep 2026 |
| Input types | text, image |
|---|---|
| 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.
No output has been recorded for Command A+ yet.
Compare Command A+
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.