Cohere Chat API (Command models) vs Jais 3

Cohere Chat API (Command models)

A public OpenAPI file, Markdown twins of every docs page and SDKs in four languages make the Chat API easy for an agent to read. Production keys do not cover the four newest Command models, whose limits are set by sales, and the SaaS agreement lets Cohere share API data with third parties.

Jais 3

Jais 3 runs on the owner's hardware through OpenAI-compatible servers in vLLM and SGLang, with tool calls, three reasoning levels and a 512K context, from a 2.2 GB 0.9B model to a 758 GB 375B one. The weights download without sign-up under Apache-2.0, but every launch command trusts remote code, and no technical report or security contact is published.

Cohere Chat API (Command models)

1. Call POST https://api.cohere.com/v2/chat with Authorization: bearer <key>. model and messages are the only required fields
2. Use command-a-03-2025, command-r-08-2024, command-r-plus-08-2024 or command-r7b-12-2024 for production traffic. Newer variants stay at trial limits on a production key
3. Keep a trial key under 20 chat requests a minute and 1,000 calls a month, and do not use it for commercial work
4. Set response_format with a json_schema for structured output, and tell the model to produce JSON when using json_object without a schema
5. Ask the account Owner to turn off training under Data Controls in the dashboard before sending confidential prompts

Jais 3

1. Start vLLM or SGLang with --reasoning-parser k2_horizon, and add --tool-call-parser k2_horizon (vLLM also --enable-auto-tool-choice) for tools, or tool calls come back as raw text
2. Pass reasoning_effort (high, medium or low) and tool_call_format inside chat_template_kwargs. Other values return a template error
3. Send each earlier assistant turn back with reasoning_content as a string, even an empty one. A missing or null thinking field makes the template raise an error
4. Send your own system message, or set default_system_prompt to an empty string. Without one the template inserts an identity prompt naming IFM, Inception42 and Cerebras
5. Budget at least 32,768 output tokens at high effort, which the cards recommend for every request