Guides
The gateway serves the Anthropic Messages API at /v1/messages, so the Anthropic SDKs and Claude Code work against it unchanged. It is a translation onto the same chat surface, so every catalog model is reachable, not just Claude.
POST https://api-pr-1793.preview.experientiallabs.ai/v1/messages speaks the Anthropic Messages wire protocol. Authenticate with the Anthropic-style x-api-key header or with Authorization: Bearer, either carries the same xpl_ key. Name any slug from GET https://api-pr-1793.preview.experientiallabs.ai/v1/models as the model.
curl "https://api-pr-1793.preview.experientiallabs.ai/v1/messages" \-H "x-api-key: $EXPLABS_API_KEY" \-H "anthropic-version: 2023-06-01" \-H "Content-Type: application/json" \-d '{"model": "qwen3.8-27b", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}]}'
Set stream: trueto receive Anthropic's server-sent event stream (message_start, content_block_delta, message_stop, and the rest), exactly as the Anthropic SDKs expect.
curl -N "https://api-pr-1793.preview.experientiallabs.ai/v1/messages" \-H "x-api-key: $EXPLABS_API_KEY" \-H "anthropic-version: 2023-06-01" \-H "Content-Type: application/json" \-d '{"model": "qwen3.8-27b", "max_tokens": 1024, "stream": true, "messages": [{"role": "user", "content": "Hello"}]}'
The lane maps onto the gateway's shared chat surface, so a few Anthropic features are route-scoped. Where a route cannot express something, the gateway translates or drops it with a disclosure instead of failing the request; only signed provider state is rejected:
thinkingconfig passes through verbatim and thinking/redacted-thinking history blocks round-trip with signatures intact. On a non-Anthropic reasoning route the config translates to the route's nearest reasoning effort (disclosed as thinking->reasoning_effort:<tier>; a bare thinking: {type: enabled} is accepted and reads as the default depth; an explicit output_config.effort wins with thinking->dropped(superseded_by_effort)), and on a route with no reasoning it is dropped with a disclosure. Block-level cache_control markers on a non-Anthropic route are disclosed as not_forwarded(provider_decides_caching): there is no field to forward, the provider caches on its own, and cache reads still bill at the cached rate. OpenRouter's reasoning object (effort or max_tokens, plus enabled) is accepted beside thinkingand wins when both are present. On a reasoning-exposed non-Anthropic rung the model's own reasoning streams as an unsigned thinking block (tool turns carry it sealed in a trailing redacted_thinking block) and replays on the next turn; Anthropic-signed thinking blocks replayed onto a non-Anthropic route are dropped with the messages.thinking->dropped(unsupported_by_provider) disclosure instead of a 400.400 names messages and suggests a capable alias.tool_result.is_error=true is native on Anthropic rungs and folds into the result text on every other wire (disclosed), so a failed tool call never ends a session.Idempotency-Key is not honored on this lane (Anthropic defines none)./v1/messages/count_tokensanswers with the gateway's own token estimate for the route (the response discloses that it is an estimate, not the provider's count); per-turn usage on the stream is the authoritative figure./v1/messages use Anthropic's envelope, {"type":"error","error":{"type":"invalid_request_error","message":"..."}}, at the same HTTP statuses as the OpenAI routes. Branch on the status and the Anthropic error type; the underlying meanings match the Errors table.Claude Code connects through this same lane by pointing ANTHROPIC_BASE_URL at the gateway and passing an xpl_ key as ANTHROPIC_API_KEY. The per-agent configuration is in Coding agents.
Prefer the OpenAI protocol? The Quickstart covers Chat Completions and the Responses API. The full surface is in the API reference.