Skip to main content
stagewise supports multiple LLM providers out of the box. You can route requests through the stagewise proxy (default), connect directly to official APIs, or use fully custom endpoints. Open the configuration page at Settings → Agent → Models & Providers.

Supported providers

ProviderModelsDescription
AnthropicClaude Opus 4.6, Sonnet 4.6, Haiku 4.5Claude models with extended thinking support
OpenAIGPT-5.4, GPT-5.3 Codex, GPT-5.3 InstantGPT and Codex models
GoogleGemini 3.1 Pro, Gemini 3 Flash, Gemini 3.1 Flash LiteGemini models with large context windows
Moonshot AIKimi K2.5Multimodal dialogue and agent tasks
AlibabaQwen 3-32B, Qwen 3-Coder 30B-A3BCost-effective coding models

Endpoint modes

Each provider can be configured with one of three endpoint modes:

stagewise (default)

Requests are routed through the stagewise proxy. This is the simplest setup — no API key required. Usage is billed through your stagewise account.

Official API

Connect directly to the provider’s official API endpoint. You need to supply your own API key. This is the standard BYOK (Bring Your Own Key) setup. See the BYOK setup guide for step-by-step instructions.

Custom endpoint

Route requests to a custom endpoint that implements one of the supported API specifications. Useful for:
  • Self-hosted models (e.g. vLLM, Ollama)
  • Enterprise proxy servers
  • Alternative API providers (Azure, AWS Bedrock, Google Vertex)
See the Custom providers guide for details.

Model capabilities

Each model declares its supported input and output modalities:
  • Text — All models support text input and output
  • Image — Most models accept image attachments (JPEG, PNG, GIF, WebP)
  • File — PDF file uploads (supported by most models)
  • Video — Video input (Google and Moonshot models only)
  • Tool calling — All built-in models support function/tool calling
Input size limits vary by provider. For example, Anthropic limits images to 5 MB while Google allows up to 100 MB.

Switching models

You can switch the active model at any time from the model selector in the chat sidebar. The model choice applies per chat — each conversation can use a different model.