# API Atlas — Final report (OpenAI + Anthropic + xAI + Gemini, runs of 2026-09-18/19 UTC)

Snapshot of the public API surface of **OpenAI**, **Anthropic**, **xAI (Grok)** and **Google Gemini**, built from the
current official documentation (downloaded, hashed, kept under `sources/`), the official machine-readable specs
(OpenAI OpenAPI v2.3.0, xAI OpenAPI 3.1, Google discovery documents v1beta rev. 20260918 and v1), the official SDK
surfaces, and **5,811 real API calls** made with the project's own keys (every one logged, sanitized, in
`reports/live-requests.jsonl`). Machine-readable outputs are in `generated/`; human docs in `docs/`; runnable examples in
`examples/`; smoke tests in `tests/`. Numbers below come from `reports/coverage.json` and `generated/build-report.json`.

## 1. Coverage

| Metric | OpenAI | Anthropic | xAI | Gemini | Total |
|---|---|---|---|---|---|
| Official documentation pages (Markdown twins / split export, HTTP 200) | 551 | 696 | 182 | 291 | 1,720 |
| Machine-readable spec | OpenAPI (352 ops) + SDK `api.md` | SDK `api.md` (201 endpoints) | OpenAPI (38 paths, 44 ops) + gRPC stubs (11 services) | discovery v1beta (86 methods) + v1 (47) + SDK types | — |
| Model records (canonical + snapshots + aliases + retired/id-only) | 230 | 36 | 33 | 97 | 396 |
| Model ids returned live by the models endpoint | 136 | 11 | 12 (+7/3/2 typed) | 58 (v1beta) / 22 (v1) | 217 |
| Model records `LIVE_VERIFIED` | 137 | 21 | 12 | 10 | 180 |
| Endpoint records | 359 | 282 | 104 | 125 | 870 |
| Tool records (exact `type` strings) | 19 | 27 | 12 | 11 | 69 |
| Parameter records (dotted paths) | 4,215 | 2,040 | 891 | 716 | 7,862 |
| Streaming / WebSocket event records | 282 | 68 | 94 | 62 | 506 |
| Error records | 50 | 46 | 12 | 18 | 126 |
| Header records | 33 | 22 | 15 | 16 | 86 |
| Price records | 717 | 158 | 120 | 527 | 1,522 |
| Deprecation records | 165 | 1 (nested: 14 models + 35 items) | 1 (nested) | 1 (nested) | 168 |
| Object/schema records | 189 | 224 | 80 | 213 | 706 |
| SDK records | 9 | 9 | 9 | 8 | 35 |
| Webhook / audit-log event types | 28 / 149 | 44 / — | — | — | 72 / 149 |
| Examples in manifests (`LIVE_VERIFIED` where run) | 95 | 95 | 39 (+17 media) | 82 | 311 |
| Example files (`.sh` / `.py` / `.ts` / `.html`) | — | — | — | — | 425 |
| Test files | — | — | — | — | 63 |
| Test results (`.venv/bin/python -m pytest tests`) | — | — | — | — | **448 passed, 67 skipped (gated), 2 flaky tests fixed and re-run green** (full run 8 min 18 s on 2026-09-19) |
| Live API calls | 2,515 | 1,735 | 588 | 973 | **5,811** |
| Estimated spend (upper bound; several agents logged conservative estimates) | ≈ $0.30 | ≈ $0.33 | ≈ $0.80 (actual ≈ $0.45) | ≈ $0.26 (actual ≈ $0.02, free tier) | **≈ $1.68 logged / ≈ $1.1 actual** |
| Human documentation pages | — | — | — | — | 228 Markdown files |
| Cross-provider feature matrix | — | — | — | — | 125 features: on all 4 = 45, on 3 = 34, on 2 = 16, unique = 26, legacy = 4 |

Endpoint statuses (an endpoint can carry several): OpenAI 123 `LIVE_VERIFIED`, 18 `ACCOUNT_RESTRICTED`, 56 `BETA`, 24 `RETIRED`;
Anthropic 47 `LIVE_VERIFIED`, 59 `ACCOUNT_RESTRICTED`, 111 `BETA`; xAI and Gemini per-status buckets are in
`docs/endpoints/by-status.md`.

## 2. What was actually exercised live (highlights)

**OpenAI** — Responses (create/stream/retrieve/delete/cancel/input_items/input_tokens/compact/background + resume), Chat Completions (incl. store → retrieve → messages → delete), legacy Completions, Conversations, function calling (forced, strict, streaming, round-trip), custom grammar tools, web_search, file_search (vector store round trip), code_interpreter + Containers API, MCP (approval flow), shell, apply_patch, tool_search, Skills API, Agents API (agent → session → streamed turn → items/turns/subagents/artifacts → delete; environment templates; vault list), ChatKit list, Realtime (client_secrets, one WebSocket session with full event sequence), Audio (TTS, transcription variants, translation), Images (one generation + validation errors), provenance checks (C2PA detected), Embeddings, Moderation, Files, Uploads, Vector Stores, Batch (5 batches end to end), Graders, Evals, webhook event types, ~100 deliberate error probes, all Admin GET endpoints (403/401 = `ACCOUNT_RESTRICTED`).

**Anthropic** — Messages (system/multi-turn/prefill/stop sequences/metadata/service_tier/streaming with exact SSE order), count_tokens, custom tools (all `tool_choice` modes, parallel, fine-grained streaming), web_search, web_fetch, code_execution (+ container reuse, skills), tool_search, programmatic tool calling, computer use round trip, text editor / bash / memory shapes, MCP connector, advisor, prompt caching (5 m / 1 h TTL numbers), extended/adaptive/interleaved thinking, effort, fast mode (429 quota 0), 1M context header, context editing + compaction, structured outputs, citations (all location types), vision, PDF, Files API, Message Batches (2 batches end to end), Skills API, Managed Agents (environment → agent → session → streamed events round trip), Admin `GET /v1/organizations/me` (200) and 21 other Admin endpoints (401), Models API pagination, ~50 deliberate error probes.

**xAI** — Models catalogue endpoints (models, language/image/video/embedding models, api-key, me, tokenize-text; redirect aliases grok-3/grok-4-fast/grok-4-0709 → grok-4.3 observed), regional hosts `us.api.x.ai` and undocumented `eu-west-1.api.x.ai`, Chat Completions (reasoning_content, reasoning_effort per model, structured output, function calling, image input, deferred completions, streaming), Responses API (minimal/stream/previous_response_id/store/compact/input_items; server tools web_search, x_search, code_interpreter, mcp, file_search shape; 422 enum list of accepted tool types), Anthropic-compatible `/v1/messages` (text/image/tool_use/thinking blocks, streaming), legacy completions (400 for all live models), Files (upload/list/get/content/public-url/revoke/delete), Collections on api.x.ai (create/add/search/delete), Batches (create/list/get/add/cancel), image generation + edit, one 1-second video job (202 pending → 200), Voice realtime WebSocket text turn (18 events), TTS/STT/voices/client_secrets, grok-build-0.1, Management API (401 = `ACCOUNT_RESTRICTED`), Skills API (404 = `ACCOUNT_RESTRICTED`).

**Gemini** — Models list (v1beta paginated, v1), model get incl. the "no longer available to new users" 404 for 2.5 models, generateContent on 7 models (thoughtSignature, serviceTier), streaming (`?alt=sse` and JSON-array framing), system instructions and every generationConfig knob (with 400s recorded for those "not enabled for this model"), structured output (responseFormat / responseSchema / responseJsonSchema / enum), thinking (budget, levels, disabled), safety settings, countTokens (text/system/image/tools/PDF/YouTube), embeddings (001 and 2, dimensions), Files (resumable/multipart/raw uploads, register, use, delete), function calling (ANY/NONE/VALIDATED, parallel, JSON-schema params, thoughtSignature echo rule with the 400 on omission), urlContext, codeExecution, googleMaps grounding, File Search (store → upload → operation → documents → grounded query → delete), Interactions API (create/stream/chain/get/delete/cancel; Deep Research background create + cancel), Environments CRUD, ephemeral auth tokens (+ constrained Live method), Live API audio WebSocket turn sequence (text modality rejected), TTS (two models, streaming), transcription model (undocumented `audioTranscription` part), Lyria RealTime WebSocket (2 audio chunks), OpenAI-compatibility layer (chat + models), legacy PaLM methods (404/501), tunedModels (501). Paid-tier features refused with 429 quota 0 / 400 FAILED_PRECONDITION: Pro models, image generation, Google Search grounding, context caching, Batch, Lyria 3, Veo (validation-only probes).

## 3. Missing coverage (honest list)

| Area | Why | Status recorded |
|---|---|---|
| OpenAI Admin API (124 endpoints), usage/costs, audit logs, certificates, external storage, WIF | no Admin key (`Missing scopes: api.management.read` …) | `ACCOUNT_RESTRICTED`; shapes from the OpenAPI spec |
| OpenAI computer-use-preview, codex-mini-latest, gpt-5.6-cyber, Daybreak, gpt-oss hosted; Anthropic Mythos ids | 404 `model_not_found` — gated or retired | `ACCOUNT_RESTRICTED` / `RETIRED` per docs |
| OpenAI video create/remix/edit, image edits/streaming, deep research runs, fine-tuning job creation (403), Realtime WebRTC/SIP, Live sessions, voice consents, Responses WebSocket, Agents hosted sandboxes | cost / account / needs peer | `DOCUMENTED` / `UNVERIFIED` / `FAILED_VERIFICATION` |
| Anthropic fast mode, per-message effort, Managed Agents tunnels/dreams/user profiles, Admin API beyond `/me`, cloud platforms | account gating / no cloud credentials | `ACCOUNT_RESTRICTED` / `DOCUMENTED` |
| xAI Management API (billing, audit, keys, ACLs), Skills API, embedding models, `tool_search` (alpha), grok-4.6/4.5 server-tool matrix, video edits/extensions, custom voices, SIP, Collections indexed-search happy path | 401/404/403 gating or cost; indexing did not finish in 75 s | `ACCOUNT_RESTRICTED` / `DOCUMENTED` / `UNVERIFIED` |
| Gemini paid-tier features on this key: Pro models, native image generation, Google Search grounding, explicit context caching, Batch, Lyria 3, Veo generation, computer-use legacy model; Vertex AI; Interactions credentials/agents/triggers/webhooks; `dynamic/*` methods | **the Gemini key is free tier** (429 `limit: 0` / 400 FAILED_PRECONDITION); no Vertex credentials; not exercised | `ACCOUNT_RESTRICTED` / `DOCUMENTED` |
| Anthropic MCP connector and Gemini/xAI MCP against our own local MCP server | needs a public URL | `DOCUMENTED` + local server test |

## 4. Major findings

**Present on all four:** JSON-Schema function calling with a client-side loop; streaming; structured JSON output; reasoning with some control (effort / thinking / reasoning_effort / thinkingConfig); prompt/context caching in some form; files APIs; image input; server-side web search on the three that expose tools inside generation (OpenAI, Anthropic, xAI) plus Gemini grounding (paid); code execution sandboxes; MCP in some form; batch processing (OpenAI, Anthropic, xAI −20 %, Gemini paid); agents platforms (Agents API, Managed Agents, xAI Responses agentic loop, Gemini Interactions API); OpenAI-style wire formats reused by xAI natively and by Gemini through its compatibility layer.

**Unique to OpenAI:** Chat Completions + Conversations as first-class stateful surfaces, background mode with resumable streams, WebSocket Responses, Realtime/Live speech-to-speech over WebRTC/SIP, moderation endpoint, provenance checks, vector stores, fine-tuning/evals/graders (winding down), ChatKit/Workspace Agents, 149 audit-log event types, project/service-account/role model.
**Unique to Anthropic:** `web_fetch`, native citations, server-side context editing/compaction, adaptive/interleaved thinking with signed blocks, `count_tokens` endpoint, memory/advisor/browser tools, programmatic tool calling, Managed Agents memory stores and scheduled deployments, required `anthropic-version` and 50 catalogued beta headers.
**Unique to xAI:** per-request `cost_in_usd_ticks`, X (Twitter) search as a server tool, an Anthropic-compatible Messages endpoint next to the OpenAI-compatible ones, retired-model redirect aliases, regional endpoints with a 1.1× US price uplift, a 500k-context model priced in two tiers around 200k prompt tokens, multi-agent model variant on Responses.
**Unique to Gemini:** a documented free tier, native audio/video/PDF understanding on text models with per-modality token accounting, music generation (Lyria 3 + RealTime), Google Search/Maps grounding, URL context, `thoughtSignature` mandatory echo, Interactions API with Deep Research agents and environments, storage-priced (per token-hour) context caching, `alt=sse` vs JSON-array streaming.

**Legacy and retirements observed live:** OpenAI Assistants gone, DALL·E gone, Sora/Videos shutdown 2026-09-24, `local_shell` unsupported, Evals shutdown 2026-11-30, self-serve fine-tuning ends 2027-01-06; Anthropic `/v1/complete` 400 "deprecated", Claude 3.x ids 404; xAI Live Search 410, `/v1/completions` and `/v1/complete` 400 for every live model, grok-2-image 404, grok-3/4-fast silently redirected; Gemini 2.5 models 404 for new users, Imagen `predict` 404, tunedModels 501, PaLM methods 404/501.

**Undocumented-but-live (`LIVE_DISCOVERED`):** OpenAI `phase`/`billing`/`tool_usage`/`prompt_cache_retention`/`personality`/`shutdown_date`; Anthropic `stop_details`/`container`/`usage.cache_creation.*`/`usage.inference_geo`/`tool_use.caller`/`file_id` on citations; xAI `eu-west-1.api.x.ai`, `x-ratelimit-*` headers, `usage.context_details`, video polling HTTP 202, realtime `ping` and `billable_audio_seconds`, `reasoning_effort: none` on grok-4.3, `store:false` responses still retrievable, x_search emitting `custom_tool_call`; Gemini `Model.thinking`/`maxTemperature`, `X-Gemini-Service-Tier` header, `audioTranscription` part, `generateContent?alt=sse`, `files:register`, `gemini-flash-latest` → 3.8-flash.

**Documentation vs live discrepancies worth knowing:** o3 priced differently on two OpenAI pages; xAI catalogue prices are ticks (1e-10 USD) while docs say cents; xAI `reasoning_effort` documented for models that return 400; Gemini explicit-cache minimum 1,024 live vs 4,096 in docs; Gemini v1 exposes only 22 GA ids although docs say all models are on both versions; Gemini Maps/File Search prices differ between pages; Anthropic `mcp-client-2026-09-15` advertised but rejected. Full lists: `docs/comparisons/models.md` §9 and each domain page.

## 5. Confidence by section

| Section | Confidence | Basis |
|---|---|---|
| OpenAI (all areas) | HIGH, except Admin (MEDIUM: spec-only shapes, all 403) and WebRTC/SIP/Live/video generation (MEDIUM) | 2,515 live calls, OpenAPI spec |
| Anthropic (all areas) | HIGH, except fast mode / Admin beyond `/me` / clouds (MEDIUM) | 1,735 live calls |
| xAI models, pricing, chat, Responses, tools, files, collections, batches, media, voice | HIGH for exercised paths; MEDIUM for gRPC (proto stubs), Management API, Skills, video edits, custom voices | 588 live calls, OpenAPI + WebSocket JSON specs |
| Gemini core generation, streaming, thinking, structured output, files, embeddings, function calling, File Search, Interactions, Live, TTS, transcription | HIGH (free-tier models) | 973 live calls, discovery doc |
| Gemini paid-tier features (Pro models, image/video/music generation, Search grounding, caching, Batch, tuning) | MEDIUM (docs + discovery schemas + validation-error probes only) | key is free tier |
| Cross-provider comparisons, FAQ, endpoint catalogue | HIGH (generated from the merged data) with the listed inconsistencies | derived |
| Security, resilience, multi-provider abstraction (4 adapters), feature detection, capability graph, streaming parsers | HIGH (143 offline tests + 22 live adapter calls) | code + tests |

## 6. Known data-quality issues to fix in a follow-up pass

Detailed in `docs/comparisons/models.md` §9. Main ones: capability flag naming differs between providers; xAI `max_output` and most `knowledge_cutoff` values are null; a few endpoint records marked `success` without a logged call; duplicate Gemini price records with conflicting values (Search $14 vs $35 per 1k, Maps $14 vs $25) kept as-is because both appear on official pages; Lyria RealTime events with null status; composite `http_status` values in some error records. None affect the exact JSON shapes or the tool type strings.

## 7. How to keep it current

`python3 scripts/update_atlas.py` snapshots `generated/`, refreshes the four `llms.txt` indexes, re-crawls all pages (SHA-256 diff; xAI pages are re-split from `llms-full.txt` by `scripts/split_xai_llms_full.py` if the site keeps refusing direct `.md` fetches), re-runs the four model-listing endpoints (`scripts/discover_*_models.py`), rebuilds `generated/` and writes `reports/changes.md` with NEW/REMOVED MODELS, ENDPOINTS, TOOLS, PRICING and CONTEXT WINDOW CHANGES, NEW BETA FEATURES, DEPRECATIONS, live drift and the official pages whose content changed. Curated fragments are never rewritten automatically; every domain generator is preserved under `scripts/generators/` and `generated/fragments/_builders/`.