Settings

Available AI models

Choose from hundreds of AI models from multiple providers for your Flows, Agents, and Products. Platform keys give you access to a curated selection without provider setup. Connect your own provider keys to use additional supported models and pay providers directly.

New accounts include a curated set of models. To view models available to your workspace, open Settings > Models. For an overview of the settings area, see What’s in Settings?.

Platform keys vs. bring your own key (BYOK)

Platform keys are included with every Runtype plan. They give you access to popular models from OpenAI, Anthropic, Google, xAI, Vercel AI Gateway, Mixlayer, and Cloudflare Workers AI without adding provider API keys. Runtype tracks usage for platform-key calls, and you can review it in Usage data.

BYOK lets you connect provider API keys to use supported models from those providers. Use BYOK when you need provider-specific limits, direct provider billing, or models that platform keys do not include. BYOK is available on Team plans and higher. For details, see Billing and plans.

To connect provider keys, open Settings > Models, select Providers, and follow Connecting AI model providers.

Supported providers

Runtype groups supported models by their access method:

  • Platform keys: OpenAI, Anthropic, Google, xAI, Vercel AI Gateway, Mixlayer, and Cloudflare Workers AI.
  • BYOK: DeepSeek, Mistral AI, AWS Bedrock, Google Vertex AI, OpenRouter, and other supported providers.

To browse the catalog, open Settings > Models. Search by model name or provider, and filter by capability, context length, output token limit, price, or response format.

Choosing the right model

Use these starting points when you choose a model:

  • General-purpose tasks: Claude Sonnet 4.6, GPT-5.4, and Gemini 3.1 Pro Preview provide a balance of quality and speed.
  • Fast, cost-sensitive tasks: GPT-5.4 mini, GPT-5.4 nano, Claude Haiku 4.5, and Gemini 3.1 Flash Lite fit high-volume or latency-sensitive Flows.
  • Complex reasoning: Claude Opus 4.6 and other models that support reasoning fit multi-step reasoning tasks.
  • Vision and images: GPT-5.4, Claude Opus 4.6, and Gemini models with vision support accept images with text.

If you are new to Runtype, start with a Flow and test the same prompt with different models. Compare response quality, speed, and cost before you choose one.

Smart model routing

Use a routed model name such as claude-sonnet-4-6 or gpt-5.4 when you want Runtype to choose a provider through its routing configuration. You do not need a provider-specific model identifier for common cases.

To choose a provider yourself, use a provider-pinned model name.

Next steps

Continue with these guides: