Providers, by name

What provider: { name: … } resolves to. Generated from packages/core/src/providers.ts and checked against each provider’s own documentation on 2026-09-02; the table below is what the runtime believes, and tests/providers.test.ts fails if a name exists in the code and not here.

Two formats. anthropic endpoints are spoken to directly. openai endpoints (Chat Completions) are reached through the runtime’s own translator, a loopback server inside the run sandbox that lives for one step. Verified means a tool loop was driven through the endpoint from this runtime; a name without it is documented, not proven — run foldrun probe <model> before a flow depends on it.

Not on the list, and why. Vertex AI puts the model in the URL, so a base URL alone cannot reach it; Bedrock’s legacy InvokeModel streams AWS events, not SSE — both are enterprise arrangements with their own gateways. xAI’s own Anthropic-shaped route is marked deprecated by xAI, so xAI is reached as openai. GitHub Models retired on 2026-07-30. Perplexity’s chat route sunsets on 2026-09-27.

Verified 2026-09-02

The translator itself was driven end to end from foldrun probe against OpenRouter’s Chat-Completions route (format: openai, base_url: https://openrouter.ai/api/v1) — the one OpenAI-shaped endpoint we hold a key for. A tool loop closed, streamed, on:

google/gemini-2.5-flash was refused with a 402 by OpenRouter — the key’s weekly limit could not reserve the 32,000 max_tokens the model loop asks for — and that refusal arrived as a well-formed Anthropic error with the provider’s own words, which is the pass-through working. Gemini’s own endpoint (name: gemini) awaits a Google key.