# Kyma API

- [What is Kyma API?](https://docs.kymaapi.com/introduction.md): Kyma API is an LLM API gateway that routes one key to 119 models and publishes measured uptime per model.
- [Quickstart](https://docs.kymaapi.com/quickstart.md): Get from zero to working API call in 30 seconds.
- [Pricing](https://docs.kymaapi.com/pricing.md): Pay-per-token pricing, credits, and rate limits. Start with $0.50 free on the free tier.
- [FAQ](https://docs.kymaapi.com/faq.md): Frequently asked questions about Kyma API.
- [Changelog](https://docs.kymaapi.com/changelog.md): Latest updates to Kyma API.
- [Any OpenAI Client](https://docs.kymaapi.com/guides/any-openai-client.md): Use Kyma with any tool that supports OpenAI-compatible APIs.
- [Python](https://docs.kymaapi.com/guides/python.md): Full Python integration guide with OpenAI SDK.
- [JavaScript / Node.js](https://docs.kymaapi.com/guides/javascript.md): Integrate Kyma API with JavaScript using the OpenAI SDK.
- [Anthropic SDK](https://docs.kymaapi.com/guides/anthropic.md): Use Kyma with the Anthropic Python/JS SDK — drop-in compatible.
- [cURL](https://docs.kymaapi.com/guides/curl.md): Use Kyma API directly from the terminal.
- [LangChain](https://docs.kymaapi.com/guides/langchain.md): Use Kyma API with LangChain for building AI applications, chains, and agents.
- [Streaming](https://docs.kymaapi.com/guides/streaming.md): Stream responses token-by-token for real-time UX.
- [Latency & connection model](https://docs.kymaapi.com/guides/latency.md): How Kyma connects your request to the model, and what that costs in latency.
- [Prompt Caching](https://docs.kymaapi.com/guides/prompt-caching.md): Repeated prompt prefixes bill at each model's own cached-input rate.
- [Tool Calling](https://docs.kymaapi.com/guides/tool-calling.md): Use function calling with Kyma API. Same format as OpenAI.
- [Structured Outputs](https://docs.kymaapi.com/guides/structured-outputs.md): Get JSON responses from models. Supports json_object and json_schema modes.
- [Routing and pricing](https://docs.kymaapi.com/guides/routing.md): Which infrastructure serves your request, in what order, and exactly what you are charged for it.
- [Model Aliases](https://docs.kymaapi.com/guides/model-aliases.md): Kyma publishes no model aliases. Call an exact model id.
- [Rate Limits](https://docs.kymaapi.com/guides/rate-limits.md): Tier-based limits for text, image, video and audio endpoints, the 429 responses they return, and where to read your tier's exact numbers.
- [Authentication](https://docs.kymaapi.com/guides/authentication.md): How to get and use your Kyma API key.
- [Choosing a Model](https://docs.kymaapi.com/guides/models.md): How to pick the right Kyma model without memorizing the whole catalog.
- [Model comparisons](https://docs.kymaapi.com/guides/model-comparisons.md): How /compare pages are built, what they will and will not tell you, and which of them Kyma asks a search engine to index.
- [Error Handling](https://docs.kymaapi.com/guides/error-handling.md): Handle errors and rate limits gracefully.
- [Build a Chatbot](https://docs.kymaapi.com/guides/use-cases/chatbot.md): Streaming multi-turn chatbot with conversation history.
- [Build a Coding Agent](https://docs.kymaapi.com/guides/use-cases/coding-agent.md): Agent that writes and executes code using tool calling.
- [Content Generation Pipeline](https://docs.kymaapi.com/guides/use-cases/content-generation.md): Batch content generation with structured JSON output.
- [RAG & Search Applications](https://docs.kymaapi.com/guides/use-cases/rag-search.md): Retrieval-augmented generation — inject context, get grounded answers.
- [Data Extraction & Structured Output](https://docs.kymaapi.com/guides/use-cases/data-extraction.md): Extract structured data from unstructured text using JSON schemas.
- [Speech & Audio Applications](https://docs.kymaapi.com/guides/use-cases/speech-and-audio.md): Build transcription, translation, and voice pipelines on one Kyma key.
- [Agent Backend](https://docs.kymaapi.com/guides/use-cases/agent-backend.md): Build an AI agent backend with tool calling, multi-step reasoning, and conversation loops.
- [Automation Workflows](https://docs.kymaapi.com/guides/use-cases/automation-workflows.md): Automate repetitive tasks with AI — email drafts, data processing, notifications, and more.
- [Internal Copilot](https://docs.kymaapi.com/guides/use-cases/internal-copilot.md): Build an internal AI assistant that answers questions using your company's knowledge base.
- [Agent Auto-Setup](https://docs.kymaapi.com/guides/agent-setup.md): Universal setup guide for any AI agent or OpenAI-compatible client. Just provide your API key.
- [Vercel AI SDK](https://docs.kymaapi.com/guides/vercel-ai-sdk.md): Use Kyma API with the Vercel AI SDK for streaming, chat UIs, and structured output.
- [MCP Server](https://docs.kymaapi.com/guides/mcp-server.md): Paste one URL into Claude, Cursor, Codex, ChatGPT, Grok, or Perplexity. OAuth login, live catalog, test chat, credits.
- [Cloudflare Workers](https://docs.kymaapi.com/guides/cloudflare-workers.md): Deploy a Kyma-powered AI API on Cloudflare Workers.
- [GitHub Actions](https://docs.kymaapi.com/guides/github-actions.md): Use Kyma API in GitHub Actions for AI-powered code review and automation.
- [n8n](https://docs.kymaapi.com/guides/n8n.md): Use Kyma API as an AI provider in n8n automation workflows.
- [Claude Code](https://docs.kymaapi.com/guides/claude-code.md): Point Claude Code at Kyma with two environment variables.
- [Cline](https://docs.kymaapi.com/guides/cline.md): Use Kyma as your AI backend in Cline (VS Code agent).
- [Roo Code](https://docs.kymaapi.com/guides/roo-code.md): Use Kyma with Roo Code VS Code extension.
- [Cursor IDE](https://docs.kymaapi.com/guides/cursor.md): Use Kyma API as your AI backend in Cursor.
- [OpenClaw Setup](https://docs.kymaapi.com/guides/openclaw.md): Use OpenClaw with Kyma API — active open models, auto-failover, 2-minute setup.
- [OpenCode](https://docs.kymaapi.com/guides/opencode.md): Use Kyma with OpenCode — open source coding assistant.
- [Kilo Code](https://docs.kymaapi.com/guides/kilo-code.md): Use Kyma with Kilo Code VS Code extension.
- [Continue.dev](https://docs.kymaapi.com/guides/continue.md): Use Kyma with Continue.dev IDE extension.
- [Windsurf](https://docs.kymaapi.com/guides/windsurf.md): Use Kyma with Windsurf (Codeium) IDE.
- [GitHub Copilot](https://docs.kymaapi.com/guides/copilot.md): Use Kyma models with GitHub Copilot in VS Code.
- [Aider](https://docs.kymaapi.com/guides/aider.md): Use Kyma with Aider — AI pair programming in your terminal.
- [OpenAffiliate](https://docs.kymaapi.com/guides/openaffiliate.md): Use Kyma API with OpenAffiliate to generate affiliate content from real program data.
- [watch-cli: give your agent eyes and ears](https://docs.kymaapi.com/guides/watch-cli.md): Turn any video URL into frames plus a full transcript your agent can reason over. Transcription runs on Kyma; a one-hour video costs about $0.05.
- [Errors](https://docs.kymaapi.com/api-reference/errors.md): Every error Kyma returns, what it means, and what to do next.
- [Chat Completions](https://docs.kymaapi.com/api-reference/chat-completions.md): Generate a chat response from a model.
- [Messages (Anthropic format)](https://docs.kymaapi.com/api-reference/messages.md): Send a conversation in the Anthropic Messages format and get an Anthropic-shaped reply from any Kyma chat model.
- [Create embeddings](https://docs.kymaapi.com/api-reference/embeddings.md): Turn text into vectors for retrieval. OpenAI-compatible.
- [Rerank documents](https://docs.kymaapi.com/api-reference/rerank.md): Score a list of documents against a query, so only the best few reach your model.
- [Make a decision](https://docs.kymaapi.com/api-reference/decisions.md): Ask a model to pick one option per question, with a confidence. No prose, no parsing.
- [Create a completion (legacy)](https://docs.kymaapi.com/api-reference/completions.md): OpenAI's deprecated text-completion shape, served for compatibility.
- [Image Generations](https://docs.kymaapi.com/api-reference/images-generations.md): Generate or edit images. Asynchronous — returns 202 with a job id; poll GET /v1/jobs/{id} for the result.
- [Video Generations](https://docs.kymaapi.com/api-reference/videos-generations.md): Generate video clips with veo-3.1-fast, kling-3-pro or kling-avatar-v2-pro. Async, billed per second of footage.
- [Audio Transcriptions](https://docs.kymaapi.com/api-reference/audio-transcriptions.md): Speech-to-text. Two input modes — multipart file (25 MB, OpenAI Whisper compatible) or JSON audio_url (Kyma extension; 100 MB on whisper-v3-turbo, 25 MB on other models). Synchronous, billed per second with a 10-second minimum per request.
- [Audio Speech (TTS)](https://docs.kymaapi.com/api-reference/audio-speech.md): Text-to-speech. Synchronous, returns audio bytes, billed per character. Several voice models, 3,000+ pre-made voices.
- [Audio Music](https://docs.kymaapi.com/api-reference/audio-music.md): Generate a full song with vocals from a prompt and your own lyrics. Synchronous, returns MP3 bytes, flat price per song.
- [Audio Voices](https://docs.kymaapi.com/api-reference/audio-voices.md): Browse the available voice library across both providers. Pick a voice_id for /v1/audio/speech.
- [List Models](https://docs.kymaapi.com/api-reference/models-list.md): List all available models, and filter them by type, capability, or use case.
- [Recommend a model](https://docs.kymaapi.com/api-reference/models-recommend.md): A short list of models for a use case, or a ready config for a coding agent. Public, no key needed.
- [Pricing Catalog](https://docs.kymaapi.com/api-reference/pricing-catalog.md): Public pricing catalog. Single round-trip returns every active SKU with per-call cost detail. Cached 60s.
- [Tier Matrix](https://docs.kymaapi.com/api-reference/limits-tiers.md): Public tier matrix. Returns the full TIERS array — deposit threshold, RPM, TPM, image/video/audio concurrency caps per tier. Cached 5 min.
- [Credit balance](https://docs.kymaapi.com/api-reference/credits-balance.md): Your spendable balance, lifetime totals and rate-limit tier.
- [Register](https://docs.kymaapi.com/api-reference/auth-register.md): Create a new account and get an API key.
- [Login](https://docs.kymaapi.com/api-reference/auth-login.md): Sign in and get a session token.
- [Get User Info](https://docs.kymaapi.com/api-reference/auth-me.md): Who am I: account identity for the authenticated caller.
- [Manage API Keys](https://docs.kymaapi.com/api-reference/auth-keys.md): Create, list, disable, and delete API keys.
- [Usage by model](https://docs.kymaapi.com/api-reference/auth-usage-models.md): Per-model request, token and cost totals for your account, plus your latest requests and latency.
- [Usage by day](https://docs.kymaapi.com/api-reference/auth-usage-daily.md): Spend, charged requests and tokens per day for your account, bucketed in your timezone.
- [GET /v1/auth/limits](https://docs.kymaapi.com/api-reference/auth-limits.md): Check your tier, rate limits, and current usage.
- [All Models](https://docs.kymaapi.com/models/overview.md): Browse Kyma's active models by capability, cost, latency, and use case.
- [Which model should I use?](https://docs.kymaapi.com/models/recommended.md): Choose the right Kyma model by task, constraint, and tradeoff.
- [Alibaba](https://docs.kymaapi.com/models/text/alibaba.md): Alibaba's text & code models on Kyma — Qwen 3.8 Flash, Qwen 3.8 27B, Qwen 3.8 Max and 6 more.
- [Anthropic](https://docs.kymaapi.com/models/text/anthropic.md): Anthropic's text & code models on Kyma — Claude Haiku 5.5, Claude Sonnet 5.5, Claude Opus 5.5 and 7 more.
- [DeepSeek](https://docs.kymaapi.com/models/text/deepseek.md): DeepSeek's text & code models on Kyma — DeepSeek V4.1 Flash, DeepSeek V4 Flash Vision, DeepSeek V4 Flash and 2 more.
- [Google](https://docs.kymaapi.com/models/text/google.md): Google's text & code models on Kyma — Gemini 4 Argon, Gemini 3.8 Flash, Gemini 3.7 Flash and 6 more.
- [Meta](https://docs.kymaapi.com/models/text/meta.md): Meta's text & code models on Kyma — Muse Spark Open, Muse Wonder, Muse Spark 1.3 and 5 more.
- [MiniMax](https://docs.kymaapi.com/models/text/minimax.md): MiniMax's text & code models on Kyma — MiniMax M3.1 Flash, MiniMax M3, MiniMax M2.7 and 1 more.
- [Moonshot](https://docs.kymaapi.com/models/text/moonshot.md): Moonshot's text & code models on Kyma — Kimi K3.1 Pro, Kimi K3, Kimi K2.7 Code and 1 more.
- [NVIDIA](https://docs.kymaapi.com/models/text/nvidia.md): NVIDIA's text & code models on Kyma — Nemotron 3.5 Super VL, Nemotron 3 Ultra 550B.
- [OpenAI](https://docs.kymaapi.com/models/text/openai.md): OpenAI's text & code models on Kyma — GPT-6.1 Sol, GPT-6 Luna, GPT-6 Astra and 7 more.
- [Perplexity](https://docs.kymaapi.com/models/text/perplexity.md): Perplexity's text & code models on Kyma — Sonar, Sonar Pro.
- [StepFun](https://docs.kymaapi.com/models/text/stepfun.md): StepFun's text & code models on Kyma — Step 5 Preview, Step 3.7 Flash.
- [Tencent](https://docs.kymaapi.com/models/text/tencent.md): Tencent's text & code models on Kyma — Hy4 Preview, Hunyuan 3.
- [TypeSafe](https://docs.kymaapi.com/models/text/typesafe.md): TypeSafe's text & code models on Kyma — Jev 1.13.
- [xAI](https://docs.kymaapi.com/models/text/xai.md): xAI's text & code models on Kyma — Grok 4.7, Grok 4.6, Grok 4.5 and 4 more.
- [Xiaomi](https://docs.kymaapi.com/models/text/xiaomi.md): Xiaomi's text & code models on Kyma — MiMo V2.6 Flash, MiMo V2.6 Pro, MiMo V2.5.
- [Zhipu AI](https://docs.kymaapi.com/models/text/zhipu.md): Zhipu AI's text & code models on Kyma — GLM 5.3 Flash, GLM 5.3, GLM 5.2 and 3 more.
- [Image Generation](https://docs.kymaapi.com/models/image-generation.md): 10 image models on one async endpoint. Photo, edit, typography, vector, native edit-mode — pay per image, per megapixel, or per quality tier.
- [Black Forest Labs](https://docs.kymaapi.com/models/image/bfl.md): Black Forest Labs's image models on Kyma — FLUX.2 Pro, FLUX.1 Kontext Pro.
- [Google](https://docs.kymaapi.com/models/image/google.md): Google's image models on Kyma — Nano Banana 3 Flash.
- [Ideogram](https://docs.kymaapi.com/models/image/ideogram.md): Ideogram's image models on Kyma — Ideogram V3.
- [MiniMax](https://docs.kymaapi.com/models/image/minimax.md): MiniMax's image models on Kyma — MiniMax Image 01.
- [OpenAI](https://docs.kymaapi.com/models/image/openai.md): OpenAI's image models on Kyma — GPT Image 2.5 Flare, GPT Image 2.
- [Recraft](https://docs.kymaapi.com/models/image/recraft.md): Recraft's image models on Kyma — Recraft V4, Recraft V4 Pro, Recraft V4 Vector.
- [Video Generation](https://docs.kymaapi.com/models/video-generation.md): 3 video models — Veo 3.1 Fast (720p with native speech and sound), Kling 3 Pro (silent cinematic) and Kling AI Avatar v2 Pro (a portrait lip-synced to your own audio). Billed per second of footage.
- [Google](https://docs.kymaapi.com/models/video/google.md): Google's video models on Kyma — Veo 3.1 Fast.
- [Kuaishou](https://docs.kymaapi.com/models/video/kuaishou.md): Kuaishou's video models on Kyma — Kling 3 Pro, Kling AI Avatar v2 Pro.
- [Audio](https://docs.kymaapi.com/models/audio.md): 10 audio models, four ways in. Transcription billed per second (10-second minimum); audio understanding, speech synthesis and realtime priced by their own units.
- [ElevenLabs](https://docs.kymaapi.com/models/audio/elevenlabs.md): ElevenLabs's audio models on Kyma — ElevenLabs Flash v2.5, ElevenLabs Turbo v2.5, ElevenLabs Multilingual v2.
- [Google](https://docs.kymaapi.com/models/audio/google.md): Google's audio models on Kyma — Lyria 3.5, Gemini 3.5 Transcribe.
- [MiniMax](https://docs.kymaapi.com/models/audio/minimax.md): MiniMax's audio models on Kyma — MiniMax Speech HD, MiniMax Speech Turbo.
- [OpenAI](https://docs.kymaapi.com/models/audio/openai.md): OpenAI's audio models on Kyma — GPT Transcribe, Whisper Large v3 Turbo, GPT-4o mini Transcribe.
- [Alibaba](https://docs.kymaapi.com/models/retrieval/alibaba.md): Alibaba's retrieval models on Kyma — Qwen3 Embedding 8B, Qwen3 Embedding 0.6B, Qwen3 Embedding 4B and 2 more.
- [BAAI](https://docs.kymaapi.com/models/retrieval/baai.md): BAAI's retrieval models on Kyma — BGE-M3, BGE Large EN v1.5, BGE Base EN v1.5.
- [Google](https://docs.kymaapi.com/models/retrieval/google.md): Google's retrieval models on Kyma — EmbeddingGemma 300M.
- [Microsoft](https://docs.kymaapi.com/models/retrieval/microsoft.md): Microsoft's retrieval models on Kyma — Multilingual E5 Large.
- [Sentence Transformers](https://docs.kymaapi.com/models/retrieval/sentence-transformers.md): Sentence Transformers's retrieval models on Kyma — all-MiniLM-L12-v2, all-MiniLM-L6-v2.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.