# Claude API (slim)

> Anthropic's Messages API for Claude, with server-side tools, an MCP connector and computer use.

- Full: https://www.anchorterminal.com/tools/anthropic-api.md (~5,750 tokens) · this version ~1,380 tokens · JSON https://www.anchorterminal.com/tools/anthropic-api.json · canonical https://www.anchorterminal.com/tools/anthropic-api
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 77.6/100 · rank #18 of 452 · #2 in Model APIs & inference · agent-ready · confidence medium**


Assessment: Structured outputs and strict tool use are GA, with grammar-constrained sampling on every current model. Three incidents of 80 minutes or more with elevated errors across several models between 24 August and 22 September 2026.

Disclosure: Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.

## Facts

- Kind: Model API · vendor: Anthropic · category: Model APIs & inference · legal entity: Anthropic, PBC · provenance 100/100
- Endpoint: `https://api.anthropic.com/v1/messages` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: MIT (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Free tier: Small free credit for new users. Card requirement not stated
- Trains on API data: No, not without express permission
- Data retention: Docs say not retained by default, privacy centre says deleted within 30 days. Flagged content up to 2 years
- Zero data retention: By agreement with sales, Messages and token counting only, not Fable 5.1 or Mythos 5.1
- Rate limits: Start tier 1,000 requests a minute per model and a $500 monthly cap. New organisations may begin on a lower Evaluation tier
- MCP: Remote MCP connector in beta (`mcp-client-2025-11-20`)
- Batch: 50% off
- Models ($/1M in/out): `claude-fable-5-1` $10/$50; `claude-opus-5-5` $4/$20; `claude-sonnet-5-5` $2/$10; `claude-haiku-4-5-20251001` $1/$5
- Prices: Web search tool $10 per 1,000 requests
- 2026-06-15 Shutdown: `claude-opus-4` and `claude-sonnet-4` (20250514) retired
- 2026-08-05 Shutdown: `claude-opus-4-1-20250805` retired
- 2026-09-24 Price change: Pre-output refusals in the bio, frontier_llm and reasoning_extraction categories are billed again
- 2026-11-30 Shutdown: `claude-sonnet-4-5-20250929` retires, replacement `claude-sonnet-5-5`

- Scores: Reliability 60, Performance pending, Schema & documentation 90, Agent ergonomics 95, Security & auth 92, Payments & pricing 30, Task success pending, Maintenance & community 91, Transparency & trust 88 · total over the 7 assessed categories
- Why: Reliability, Status page at status.claude.com with component history (20). · Schema & documentation, No OpenAPI document in the docs. · Agent ergonomics, Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). · Security & auth, Model reading. · Payments & pricing, No machine payment protocol (0). · Maintenance & community, Model reading. · Transparency & trust, Closed service with clear commercial terms, SDKs MIT (15).
- Sources: 20, open questions: 4, both in the full twin
- Capabilities: inference.llm
- JSON: https://www.anchorterminal.com/api/v1/tools/anthropic-api.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/anthropic-api.svg` or a link to https://www.anchorterminal.com/tools/anthropic-api from a page on anthropic.com or platform.claude.com or one of their subdomains, or the README of github.com/anthropics/anthropic-sdk-python, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Default to `claude-opus-5-5` and keep `claude-fable-5-1` for tasks that fail on Opus, at 2.5 times the price
2. Don't send `tool_choice` any or tool to the 5.x models. Use auto with `strict: true` on the tool
3. Put `cache_control` on the system prompt and tool list. Reads cost 0.05x input on Opus 5.5
4. Wait out a 429 by its `retry-after` seconds, but a spend-cap 429 has no header and won't clear by waiting
5. Move off `claude-sonnet-4-5-20250929` before 2026-11-30. Retired ids fail, they don't redirect

## Connect

```bash
pip install anthropic   # or: npm i @anthropic-ai/sdk
```

```bash
curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-opus-5-5","max_tokens":512,"messages":[{"role":"user","content":"hello"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI API | A | 82.8 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| GroqCloud | BB | 75.7 | inference.llm | https://www.anchorterminal.com/tools/groq.min.md |
| BlockRun.AI | BB | 72.5 | inference.llm | https://www.anchorterminal.com/tools/blockrun-ai.min.md |
| Mistral AI API | BB | 71.3 | inference.llm | https://www.anchorterminal.com/tools/mistral-api.min.md |
| OpenRouter | B | 68.8 | inference.llm | https://www.anchorterminal.com/tools/openrouter.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)