# Piramyd

- [Piramyd Overview: AI Inference Gateway and Features](https://docs.piramyd.cloud/introduction.md): Learn what Piramyd is: an OpenAI-compatible gateway routing requests to OpenAI, Anthropic, and more with built-in web intelligence and flat-rate pricing.
- [Piramyd Quickstart: First API Call in Five Minutes](https://docs.piramyd.cloud/quickstart.md): Create an account, discover available models with GET /v1/models, and send your first streaming chat completion using Python or JavaScript in minutes.
- [Piramyd API Authentication: Keys, JWTs, and Tracing](https://docs.piramyd.cloud/authentication.md): Piramyd uses API keys for inference endpoints and JWTs for account management. Learn how to obtain, use, and rotate your credentials.
- [Model Discovery and Selection — Piramyd API Reference](https://docs.piramyd.cloud/concepts/models.md): Discover available models at runtime with GET /v1/models. Check capabilities, context windows, tiers, and endpoints before every inference call.
- [Automatic Context Compaction for Long Conversations](https://docs.piramyd.cloud/concepts/context-compaction.md): Piramyd automatically compacts long conversation histories when they approach a model's context window, so multi-turn sessions run without interruption.
- [Tool Call Integrity: Reliable Streaming Tool Arguments](https://docs.piramyd.cloud/concepts/tool-call-integrity.md): Piramyd buffers, validates, and auto-repairs streaming tool call arguments. Your agent always receives complete, valid JSON — no client changes needed.
- [Piramyd Pricing: Flat-Rate Plans with Unlimited Tokens](https://docs.piramyd.cloud/concepts/pricing-and-tiers.md): Piramyd offers three flat-rate subscription plans with unlimited tokens. Throughput is governed by requests per minute (RPM), not token budgets.
- [OpenAI SDK Compatibility Guide for Piramyd Gateway](https://docs.piramyd.cloud/guides/openai-sdk-compatibility.md): Piramyd is fully OpenAI-compatible. Point base_url at https://api.piramyd.cloud/v1 and your existing Python or JS SDK code works immediately.
- [Stream Responses with Server-Sent Events on Piramyd](https://docs.piramyd.cloud/guides/streaming.md): Enable real-time streaming from Piramyd using Server-Sent Events. Set stream: true and handle SSE chunks for chat completions and responses endpoints.
- [Tool and Function Calling Guide for the Piramyd API](https://docs.piramyd.cloud/guides/tool-calling.md): Use tool calling on Piramyd to build AI agents that invoke functions. Covers the 4-step loop, tool_choice values, streaming accumulation, and auto-repair.
- [Vision: Using Image Inputs with Piramyd API Models](https://docs.piramyd.cloud/guides/vision.md): Send image URLs or pre-uploaded images to vision-capable models on Piramyd. Covers inline image_url, the upload endpoint, and Responses input_image format.
- [Web Search, Scraping, and Crawling with the Piramyd API](https://docs.piramyd.cloud/guides/web-intelligence.md): Piramyd bundles SIRS (multi-engine web search) and CROWD (scraping, crawling, extraction) as first-class API endpoints — no separate services needed.
- [System One: Fast Typed Decisions on the Piramyd API](https://docs.piramyd.cloud/guides/system-one.md): System One (Jev) takes a state and typed questions, returning calibrated yes/no, choice, or score answers in 70–500 ms. No chat, no streaming, no tools.
- [Piramyd Error Codes, HTTP Statuses, and Response Format](https://docs.piramyd.cloud/errors/error-reference.md): Complete Piramyd error reference: HTTP status codes, non-streaming and streaming error shapes, common error codes, and finish_reason values.
- [Piramyd API Rate Limits, Tiers, and Request Quotas](https://docs.piramyd.cloud/errors/rate-limits.md): Piramyd enforces per-key RPM limits, not token limits. Compare tier allowances, learn to buy extra RPM, and handle 429 responses correctly.
- [Retry Strategy and Resilience Patterns for Piramyd](https://docs.piramyd.cloud/errors/retry-strategy.md): Learn which Piramyd error codes are retryable and how to implement exponential backoff with jitter, honouring Retry-After for 429 and 503 responses.
- [Piramyd Chat Completions — POST /v1/chat/completions](https://docs.piramyd.cloud/api-reference/chat-completions.md): Primary OpenAI-compatible inference endpoint. Supports streaming, tool calling, vision, thread-based context compaction, and all standard parameters.
- [OpenAI Responses API Reference — POST /v1/responses](https://docs.piramyd.cloud/api-reference/responses.md): OpenAI Responses-compatible endpoint. Accepts string or array input, multimodal input_image blocks, and named SSE streaming events.
- [Messages API — POST /v1/messages | Anthropic Format](https://docs.piramyd.cloud/api-reference/messages.md): Anthropic-compatible endpoint. Accepts x-api-key or Bearer auth, top-level system field, returns Anthropic-shaped responses. Drop-in for the Anthropic SDK.
- [System One Calibrated Decisions — POST /v1/systemone](https://docs.piramyd.cloud/api-reference/system-one.md): Typed decision API for Jev models. Submit a state and structured questions; receive calibrated probabilities, choices, and scores in 70–500 ms.
- [Browse and Filter Models via GET /v1/models Catalog](https://docs.piramyd.cloud/api-reference/models.md): Fetch the live model catalog via GET /v1/models. Each entry includes capability flags, context windows, and endpoint support. Never hardcode model IDs.
- [Piramyd API Compatibility Matrix and Feature Flags](https://docs.piramyd.cloud/api-reference/capabilities.md): GET /v1/capabilities returns an API-level compatibility matrix showing which features Piramyd supports. Use it to check endpoint availability at runtime.
- [Multi-Engine Web Search via POST /v1/search — SIRS](https://docs.piramyd.cloud/api-reference/search.md): POST /v1/search — multi-engine web search via SIRS (SearXNG). Returns ranked results with snippets, sources, score, and optional full page content.
- [POST /v1/scrape — Single URL Content Extraction (CROWD)](https://docs.piramyd.cloud/api-reference/scrape.md): POST /v1/scrape — extract clean content from a URL via CROWD. Returns markdown, HTML, links, or a screenshot optimized for LLM injection.
- [Async Website Crawl and Extraction — POST /v1/crawl](https://docs.piramyd.cloud/api-reference/crawl.md): POST /v1/crawl starts an async website crawl. Returns a job_id immediately. Poll GET /v1/crawl/{job_id} for status and results. Cancel with DELETE.
- [Discover All Website URLs — POST /v1/map via CROWD](https://docs.piramyd.cloud/api-reference/map.md): POST /v1/map — discover all URLs on a site without fetching content. Understand site structure before targeting pages to scrape or crawl.
- [Extract Structured Data with LLMs — POST /v1/extract](https://docs.piramyd.cloud/api-reference/extract.md): POST /v1/extract — use an LLM to pull structured data from up to 20 URLs. Describe what to extract in plain English; enforce shape with JSON Schema.
- [POST /v1/llmstxt — Generate llms.txt for Any Website](https://docs.piramyd.cloud/api-reference/llmstxt.md): POST /v1/llmstxt — generate an llms.txt file for any website: a structured plain-text document of the site's content optimized for LLM context injection.
- [Authentication Endpoints — Login, Profile, and OAuth](https://docs.piramyd.cloud/api-reference/auth.md): POST /v1/auth/token and related endpoints for account authentication. Get a JWT, refresh tokens, manage your profile, and link OAuth providers.
- [No-Auth Status and Observability Endpoints — Piramyd](https://docs.piramyd.cloud/api-reference/status.md): No-auth status and health endpoints for Piramyd: runtime metrics, per-model health, global token stats, and the root service info endpoint.