Supported providers and models

Each agent uses one provider and one model, chosen from a list on the agent's Settings tab (the model isn't free text). The list is kept in line with each provider's current models. A model that has since been retired stays visible on agents that already use it.

Providers

New agents start on OpenAI gpt-5.5.

OpenAI

gpt-5.5, gpt-5.5-pro, gpt-5.5-2026-04-23, gpt-5.4, gpt-5.4-pro, gpt-5.4-mini, gpt-5.4-nano, gpt-5.2, gpt-5.2-pro, gpt-5.1, gpt-5, gpt-5-pro, gpt-5-mini, gpt-5-nano, o3, o3-pro, gpt-4.1, gpt-4.1-mini, gpt-oss-120b, gpt-oss-20b.

Anthropic

claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-opus-4-5, claude-sonnet-4-6, claude-sonnet-4-5, claude-haiku-4-5, claude-fable-5.

Google Gemini

gemini-3.1-pro-preview, gemini-3.5-flash, gemini-3-flash-preview, gemini-3.1-flash-lite, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-flash-latest.

Groq

openai/gpt-oss-120b, groq/compound, llama-3.3-70b-versatile, openai/gpt-oss-20b, qwen/qwen3-32b, meta-llama/llama-4-scout-17b-16e-instruct, groq/compound-mini, llama-3.1-8b-instant.

Good to know

• Every reply costs 1 SentientOne credit whatever the model. Model tokens are billed to you by the provider, at their prices.
• Switching an agent's provider or model doesn't change your integration: the request and the stream stay the same.
• Anthropic prompts use Anthropic's prompt caching for the system prompt; other providers apply their own automatic caching.
• Other providers aren't available for agents.