API Reference Overview
Base URL, authentication, surfaces, and the full endpoint map for the Ablatic API
This page is the map of the Ablatic API: the base URL, how to authenticate, the two compatible surfaces, and every public endpoint.
Base URL
https://api.ablatic.ai/v1The host api.ablatic.ai proxies only /v1/* and /health. Any other path returns 404.
Authentication
Every request except the unauthenticated probes below needs an API key. Keys look like sk-ablatic-... and are created in the console. A key is shown once at creation and stored only as a SHA-256 hash, so it cannot be recovered.
Two headers carry the key, one per surface. Both run the same validation.
Authorization: Bearer sk-ablatic-...x-api-key: sk-ablatic-...Use Authorization: Bearer on the OpenAI-style endpoints. Use x-api-key on the Anthropic-style endpoints.
The surfaces
The API exposes the same model over three request and response shapes. Pick the one your client speaks; the model and pipeline behind them are identical.
- OpenAI Chat. Drop-in for the
openaiSDK. Base URLhttps://api.ablatic.ai/v1, endpoint/v1/chat/completions, modeltalos,Authorization: Bearer. - OpenAI Responses. For clients that default to the Responses API (Vercel AI SDK, Codex-style agents). Endpoint
/v1/responses, stateless only. See Responses. - Anthropic Messages. Drop-in for the
anthropicSDK and Claude Code. Base URLhttps://api.ablatic.ai, endpoint/v1/messages, key viax-api-key.
The default model is talos. You select the reasoning mode with reasoning_effort. See Models.
Endpoints
OpenAI-style
| Method | Path | Purpose |
|---|---|---|
| POST | /v1/chat/completions | Chat completion, streaming SSE |
| POST | /v1/responses | Responses API completion (stateless) |
| GET | /v1/models | List the model (no auth) |
| GET | /v1/audit | List Glassbox audit records |
| GET | /v1/audit/stats | Audit summary stats |
| GET | /v1/audit/{request_id} | Fetch one audit record |
| DELETE | /v1/audit/{request_id} | GDPR erasure of one record |
| POST | /v1/files | Upload a file for context injection |
| GET | /v1/files | List uploaded files |
| GET | /v1/files/{file_id} | Fetch one file |
| DELETE | /v1/files/{file_id} | Delete one file |
| POST | /v1/agent/run | Server-side autonomous agent loop |
| POST | /v1/agent/run/{run_id}/cancel | Cancel a running agent |
| POST | /v1/simulation/analyze | Analyze HDF5, NumPy, or video data |
Anthropic-style
| Method | Path | Purpose |
|---|---|---|
| POST | /v1/messages | Anthropic Messages completion |
| POST | /v1/messages/count_tokens | Estimate input tokens (heuristic) |
| GET | /v1/messages/_health | Health probe (no auth) |
| POST | /v1/messages/batches | Create a message batch |
| GET | /v1/messages/batches | List batches |
| GET | /v1/messages/batches/{id} | Fetch one batch |
| POST | /v1/messages/batches/{id}/cancel | Cancel a batch |
| DELETE | /v1/messages/batches/{id} | Delete a batch |
| GET | /v1/messages/batches/{id}/results | Stream batch results (NDJSON) |
Message Batches run on the Anthropic-compatible surface. The OpenAI-style /v1/batches endpoint is not offered. See Batch.
No authentication
Three endpoints need no key: GET /v1/models, GET /v1/messages/_health, and GET /health.
Common headers
These headers ride on most requests and responses across both surfaces.
| Direction | Header | Meaning |
|---|---|---|
| Request | X-Timezone | Timezone for usage and billing windows. Default UTC |
| Request | Idempotency-Key | Safe-retry key on batch creation |
| Response | X-Request-Id | Unique id for the request, quote it in support tickets |
| Response | X-RateLimit-Limit | Concurrent-request limit (see note below) |
| Response | X-RateLimit-Remaining | Remaining capacity |
| Response | X-RateLimit-Reset | When the window resets |
| Response | Retry-After | Seconds to wait, sent on 429 and 503 |
X-RateLimit-Limit currently reflects the concurrent-request limit, not requests per minute. Do not read it as RPM. See Rate limits.