Skip to main content

Providers & Models

OpenAI

API base: https://api.openai.com/v1
Dashboard: platform.openai.com

ModelNotes
gpt-4oBest quality, recommended for support
gpt-4o-miniFaster and cheaper, good for simple tickets
gpt-4-turboPrevious generation flagship
gpt-3.5-turboCheapest option, lower quality

Anthropic (Claude)

API base: https://api.anthropic.com/v1
Dashboard: console.anthropic.com

ModelNotes
claude-opus-4-7Most capable, highest cost
claude-sonnet-4-6Balanced — recommended for support
claude-haiku-4-5-20251001Fastest and cheapest
claude-3-5-sonnet-20241022Previous generation, widely used
claude-3-5-haiku-20241022Previous generation fast model

Mistral AI

API base: https://api.mistral.ai/v1
Dashboard: console.mistral.ai

ModelNotes
mistral-large-latestMost capable Mistral model
mistral-small-latestGood quality at lower cost
open-mistral-nemoOpen-weight model
codestral-latestOptimised for technical/code questions

Custom (OpenAI-compatible)

Any API that speaks the OpenAI chat completions format can be used. Set the Custom API Base URL to your endpoint's base path.

Examples:

  • OpenCode: https://api.opencode.ai/v1
  • Local model via Ollama: http://localhost:11434/v1
  • Together AI: https://api.together.xyz/v1

The model name must match exactly what your endpoint expects.

note

When using a local or self-hosted model, make sure the Paymenter server can reach the endpoint. A model that is too slow (over 45 seconds to respond) will time out and trigger the escalation flow.