OpenAI — Chat Completions
POST /v1/chat/completions
| Capability | Supported |
|---|---|
| Streaming | ✓ |
| Function calling | ✓ |
| Web search | ✓ |
OpenAI — Responses API
POST /v1/responses
| Capability | Supported |
|---|---|
| Streaming | ✓ |
| Function calling | ✓ |
| Web search | ✓ |
Anthropic — Messages API
POST /v1/messages
| Capability | Supported |
|---|---|
| Streaming | ✓ |
| Function calling | ✓ |
| Web search | ✓ |
| Web fetch | ✓ |
Anthropic — Count Tokens
POST /v1/messages/count_tokens
Count input tokens before sending a request. See count tokens.
Policy-governed endpoints
abliteration.ai exposes a parallel/policy/* surface that adds project quotas, policy evaluation, and streaming policy metadata. See policy endpoints.
| Compat endpoint | Governed variant |
|---|---|
/v1/chat/completions | /policy/chat/completions |
/v1/messages | /policy/messages |
/v1/responses | /policy/responses |