This page only states stable access rules. Verified fixed aliases are shown directly; fast-moving text model IDs should be read from GET /v1/models before integration.
Available now through the Anthropic Messages endpoint, with an OpenAI-compatible route for existing team tooling.
Enablement returns the available model IDs. Useful for OpenAI SDK, Cursor, Codex CLI, and LangChain migration flows.
Routed through the OpenAI-compatible entrypoint. Exact model IDs are governed by the console and /v1/models.
For cost-sensitive and reasoning workloads. Public copy stays stable; callable aliases come from the live model API.
Video generation runs as async jobs with the same API key, job polling, and usage-log task details.
doubao-seedance-2.0Your current API key can call this capability. When a model ID is not fixed on this page, use GET /v1/models as the source of truth.
This model family is not enabled by default. We configure it by account or project before calls are accepted.
Model versions change quickly. The public site does not pretend to be a real-time list; query the API before connecting production code.