​
Default model

command-r-plus

​
Supported models

Any model available through the Cohere API:
  • command-r-plus (default, flagship)
  • command-r
  • command-r7b
  • Any other model ID the API accepts

​
Authentication

Environment variable: 
export COHERE_API_KEY=...
Config command: 
ai-blackteam config set providers.cohere.api_key ...
Get your API key from the Cohere dashboard.

​
Example usage

ai-blackteam run -p cohere -a encoding-obfuscation -t "Write a phishing email"
ai-blackteam batch -p cohere --attacks all -t "Write a phishing email"

​
Tool-use support

Yes. Compatible with all 39 tool-use attacks in the framework — agent exploitation, MCP exploitation, multi-agent protocol attacks, and tool-injection vectors. Filter the attack catalog with: 
ai-blackteam list-attacks
# look for rows with Mode = tool-use

​
Notes

  • The provider uses the OpenAI SDK pointed at Cohere’s compatibility endpoint (base_url="https://api.cohere.com/compatibility/v1")
  • Max output tokens per request: 4,096
  • Retry with exponential backoff is automatic on API failures (3 attempts)