# Zurelay

> One OpenAI- and Anthropic-compatible API for Claude, GPT, Gemini, Grok, DeepSeek, Nano Banana, GPT Image, Seedance, Kling, Wan, Grok Imagine, Vidu and PixVerse, at a fraction of each lab's price.

Zurelay is a drop-in API: keep the OpenAI or Anthropic SDK you use and change the base URL and the key.

- OpenAI-compatible base URL: https://api.zurelay.com/v1 (chat, images, video, speech, embeddings, models)
- Anthropic-compatible base URL: https://api.zurelay.com (POST /v1/messages, for Claude models)
- Authentication: `Authorization: Bearer zr_live_…` or `x-api-key: zr_live_…`
- Model IDs and what each reads: GET https://api.zurelay.com/v1/models. With live prices: https://zurelay.com/docs/models.md
- Every docs page in one file: https://zurelay.com/llms-full.txt

## In short

- What it is: an API that sells access to the major labs' models (Anthropic, OpenAI, Google, xAI, DeepSeek, Alibaba and more) at up to 90% below each lab's list price, through OpenAI- and Anthropic-compatible endpoints.
- Who it suits: developers and teams who want the same models for less, on one key, without a subscription. It works with the OpenAI and Anthropic SDKs, Claude Code, OpenCode, Aider, Continue, Zed and any OpenAI-compatible app.
- Pricing: pay as you go from prepaid credit (from $10), with no subscription or minimum spend. Live prices are on every model page and at https://zurelay.com/models.
- Why it's cheaper: sellers offer model capacity bought ahead below list price. Zurelay tests every route before it serves requests and every day after, and pools several routes per model: https://zurelay.com/docs/verification
- Reliability: failed attempts move to another route and aren't billed, and videos are charged only once they're delivered. Live health: https://zurelay.com/status

## Get started

- [Introduction](https://zurelay.com/docs.md): One OpenAI- and Anthropic-compatible API for Claude, GPT, Gemini, Grok, DeepSeek, Nano Banana, GPT Image, Seedance, Kling, Wan, Grok Imagine, Vidu and PixVerse, at a fraction of each lab's price.
- [Quickstart](https://zurelay.com/docs/quickstart.md): Make your first request in two minutes: create a key, point an SDK at Zurelay, send a message.
- [API keys and authentication](https://zurelay.com/docs/authentication.md): How to send your API key, keep it safe, and what each key can be limited to.
- [Models](https://zurelay.com/docs/models.md): Every model on Zurelay with its ID, what it reads (images, PDFs, audio, video), its context window and its price.

## Chat

- [Chat completions](https://zurelay.com/docs/chat.md): POST /v1/chat/completions: messages, streaming, tool calling, structured output, reasoning effort and usage.
- [Zurelay Auto](https://zurelay.com/docs/auto.md): zurelay-auto picks the model that fits each request and bills that model's price: how it picks, what you pay, which model answered and how it falls back.
- [Images, PDFs, audio and video input](https://zurelay.com/docs/multimodal.md): Send pictures, documents, recordings and clips to the models that read them, as data or links, in OpenAI or Anthropic format.
- [Anthropic Messages and Claude Code](https://zurelay.com/docs/anthropic.md): POST /v1/messages for Claude models with the Anthropic SDKs, Claude Code and anything else that speaks Anthropic's API.

## Images

- [Image generation](https://zurelay.com/docs/images.md): POST /v1/images/generations: prompts, resolutions, aspect ratios, pixel sizes, response formats and prices.
- [Image editing and reference images](https://zurelay.com/docs/image-editing.md): Edit a picture or combine several: POST /v1/images/edits (OpenAI's multipart form or JSON) and reference images on generations.
- [Nano Banana](https://zurelay.com/docs/nano-banana.md): Everything about Nano Banana Pro, Nano Banana 2.1, Nano Banana 2 and Nano Banana 2 Lite on Zurelay: sizes, prices, up to 14 reference images, editing, text in images and prompting.
- [GPT Image](https://zurelay.com/docs/gpt-image.md): GPT Image 2, 2.5 Flare and 2.5 Sunburst on Zurelay: sizes, quality, editing with up to 16 images.
- [Grok Imagine Image](https://zurelay.com/docs/grok-imagine-image.md): Grok Imagine Image 2.0 on Zurelay: 1K and 2K images in 8 shapes, editing with up to 3 images, prices and prompting.
- [FLUX 3 Image](https://zurelay.com/docs/flux.md): FLUX 3 Image on Zurelay: 1K, 2K and 4K images in 15 shapes, text in images, editing, prices and prompting.

## Video

- [Video generation](https://zurelay.com/docs/video.md): POST /v1/videos and polling for Seedance, Kling, Wan, Grok Imagine, MiniMax H3, Veo, Vidu and PixVerse: prompts, length, resolution, aspect ratio, sound, start and end frames, reference images and prices.
- [Seedance](https://zurelay.com/docs/seedance.md): Seedance 2.5, 2.0, 2.0 Fast and 2.0 Mini on Zurelay: which to pick, image-to-video, up to 9 reference images and prompting.
- [Kling](https://zurelay.com/docs/kling.md): Kling 4.0 and 3.0 on Zurelay: which to pick, 3 to 30 second clips with sound, first and last frames, up to 10 reference images, and cheaper silent video.
- [Wan](https://zurelay.com/docs/wan.md): Wan 3.0 on Zurelay: 480p to 1080p clips in every common shape, sound included, and up to 10 reference images.
- [Grok Imagine](https://zurelay.com/docs/grok-imagine.md): Grok Imagine Video 1.5 on Zurelay: 480p and 720p clips with sound, 1 to 15 seconds, from a prompt, a start image or up to 3 reference images.
- [Omni Flash](https://zurelay.com/docs/omni-flash.md): Gemini Omni Flash on Zurelay: 360p to 4K clips with sound, 4 to 10 seconds, from a prompt, a start image, a start and end image, up to 10 reference images or 3 reference videos to edit.
- [Veo](https://zurelay.com/docs/veo.md): Google's Veo 3.1 Fast on Zurelay: 8 second 720p clips with dialogue and sound, from a prompt or a start image.
- [MiniMax H3](https://zurelay.com/docs/minimax-h3.md): MiniMax H3 (Hailuo 03) on Zurelay: 768p and 2K clips with sound, 4 to 15 seconds, from a prompt and up to 9 reference images, 3 reference videos and 3 voice or music clips.
- [Vidu](https://zurelay.com/docs/vidu.md): Vidu Q3 Turbo on Zurelay: fast 540p to 1080p clips with sound, 1 to 16 seconds, from a prompt, a start image or a start and end image.
- [PixVerse](https://zurelay.com/docs/pixverse.md): PixVerse V6 on Zurelay: fast, low-cost 360p to 1080p clips, 1 to 15 seconds, negative prompts, and cheaper silent video.

## Speech

- [Text to speech](https://zurelay.com/docs/speech.md): POST /v1/audio/speech: Gemini text-to-speech through OpenAI's speech API, with 30 voices, styles in plain words, MP3, WAV or PCM, and prices.

## Embeddings

- [Embeddings](https://zurelay.com/docs/embeddings.md): POST /v1/embeddings: OpenAI's text-embedding-3-small and text-embedding-3-large with OpenAI's request and response, the same vectors, 50% below OpenAI's price. Batching, dimensions, base64, semantic search, RAG, LangChain, LlamaIndex and the AI SDK.

## Decisions

- [OpenAI Decisions API](https://zurelay.com/docs/openai-decisions.md): POST /v1/decisions: GPT-6 Luna Decisions answers predicate, choice and score questions about text and images with probabilities, through OpenAI's own SDKs. Request shape, limits, refusals and prices.
- [Decisions (Jev)](https://zurelay.com/docs/decisions.md): POST /v1/systemone: TypeSafe's Jev answers yes/no, choice and score questions about your data with calibrated probabilities. Request shape, limits, SDKs and prices.

## Platform

- [Smart routing](https://zurelay.com/docs/smart-routing.md): When a model is down, its closest alternative answers instead of an error. Automatic or your own rules, per key or per request.
- [Callbacks (webhooks)](https://zurelay.com/docs/webhooks.md): Get images and videos pushed to your server when they're ready: callback_url, signed Standard Webhooks deliveries, retries, and verifying the signature.
- [Key limits and rules](https://zurelay.com/docs/key-rules.md): Monthly and daily budgets, rate limits, expiry, allowed models and allowed IP addresses for each API key.
- [Errors](https://zurelay.com/docs/errors.md): Every error Zurelay returns, what it means and what to do about it.
- [Reliability, retries and timeouts](https://zurelay.com/docs/reliability.md): How Zurelay keeps requests answered, how long it waits, and when your client should retry.
- [Model verification](https://zurelay.com/docs/verification.md): Why prices are lower, the checks every route passes before it serves requests and every day after, and what they mean for you.
- [Pricing and billing](https://zurelay.com/docs/billing.md): Prepaid credit, how tokens, images, media and video seconds are counted, failed requests, and the request log.

## Tools

- [Integrations](https://zurelay.com/docs/integrations.md): Set up Claude Code, Cursor, Cline, the OpenAI and Anthropic SDKs, LangChain, n8n and more with Zurelay.
- [MCP server: images, video and speech in AI apps](https://zurelay.com/docs/mcp.md): Connect Claude, ChatGPT, Cursor, VS Code and other MCP apps to Nano Banana, GPT Image, Seedance, Kling and Gemini TTS: sign in or use a key, the tools, prices and security.
- [Claude Code](https://zurelay.com/docs/integrations/claude-code.md): Anthropic’s coding agent for the terminal and IDE.
- [OpenCode](https://zurelay.com/docs/integrations/opencode.md): Open-source coding agent for the terminal.
- [Cursor](https://zurelay.com/docs/integrations/cursor.md): The AI code editor. Chat and agent on your key.
- [Cline](https://zurelay.com/docs/integrations/cline.md): Autonomous coding agent for VS Code and JetBrains.
- [Kilo Code](https://zurelay.com/docs/integrations/kilo-code.md): Open-source coding agent for VS Code and CLI.
- [Continue](https://zurelay.com/docs/integrations/continue.md): Open-source assistant for VS Code and JetBrains.
- [Aider](https://zurelay.com/docs/integrations/aider.md): AI pair programming in your terminal.
- [Zed](https://zurelay.com/docs/integrations/zed.md): The fast editor with a built-in agent panel.
- [Grok Bot](https://zurelay.com/docs/integrations/grok-bot.md): SpaceXAI’s always-on Bots, each with its own cloud computer.
- [OpenAI dots](https://zurelay.com/docs/integrations/openai-dots.md): Always-on agents in ChatGPT, with their own computer and browser.
- [Meta Muse](https://zurelay.com/docs/integrations/meta-muse.md): Meta’s AI agent, on the web, on phones and in WhatsApp.
- [Gemini Spark](https://zurelay.com/docs/integrations/gemini-spark.md): Google’s 24/7 personal agent in the Gemini app.
- [OpenClaw](https://zurelay.com/docs/integrations/openclaw.md): Open-source personal assistant on your devices.
- [Hermes Agent](https://zurelay.com/docs/integrations/hermes-agent.md): Nous Research’s agent for the terminal and chat apps.
- [Manus](https://zurelay.com/docs/integrations/manus.md): The general AI agent that works on its own cloud computer.
- [Perplexity](https://zurelay.com/docs/integrations/perplexity.md): Perplexity and its agents, with your own remote connectors.
- [Other agents](https://zurelay.com/docs/integrations/any-agent.md): Any agent that can read a web page and run commands, or add MCP servers.
- [Claude](https://zurelay.com/docs/integrations/claude-connector.md): Make images, videos and speech in Claude chats, on the web, desktop and phone.
- [ChatGPT](https://zurelay.com/docs/integrations/chatgpt-connector.md): Make images, videos and speech in ChatGPT through developer mode.
- [Grok](https://zurelay.com/docs/integrations/grok-connector.md): Make images, videos and speech in Grok chats.
- [Claude Code (MCP)](https://zurelay.com/docs/integrations/claude-code-mcp.md): Let Claude Code make images, videos and voiceovers for your project.
- [Cursor (MCP)](https://zurelay.com/docs/integrations/cursor-mcp.md): Images, video and speech from Cursor’s agent, for your app’s assets.
- [OpenAI Node SDK](https://zurelay.com/docs/integrations/openai-node.md): Official OpenAI library for TypeScript and JS.
- [OpenAI Python SDK](https://zurelay.com/docs/integrations/openai-python.md): Official OpenAI library for Python.
- [Anthropic SDK](https://zurelay.com/docs/integrations/anthropic-sdk.md): Official Claude libraries for Python and TS.
- [Vercel AI SDK](https://zurelay.com/docs/integrations/vercel-ai-sdk.md): Streaming, tools and UI hooks for TypeScript.
- [LangChain](https://zurelay.com/docs/integrations/langchain.md): Agents and LangGraph, in Python or JavaScript.
- [LlamaIndex](https://zurelay.com/docs/integrations/llamaindex.md): RAG and document agents over your own data.
- [cURL](https://zurelay.com/docs/integrations/curl.md): Plain HTTP, for any language or a quick test.
- [Open WebUI](https://zurelay.com/docs/integrations/open-webui.md): Self-hosted, ChatGPT-style chat for your team.
- [LibreChat](https://zurelay.com/docs/integrations/librechat.md): Open-source, multi-user chat with agents.
- [LobeHub](https://zurelay.com/docs/integrations/lobehub.md): Open-source AI workspace, formerly LobeChat.
- [Cherry Studio](https://zurelay.com/docs/integrations/cherry-studio.md): A desktop AI client for Windows, macOS and Linux.
- [SillyTavern](https://zurelay.com/docs/integrations/sillytavern.md): Local-first frontend for character chat.
- [n8n](https://zurelay.com/docs/integrations/n8n.md): Workflow automation with AI agent nodes.
- [Dify](https://zurelay.com/docs/integrations/dify.md): AI workflows, agents and RAG on a canvas.

## Models

- [Zurelay Auto API](https://zurelay.com/models/zurelay-auto): `zurelay-auto`, from $0.025 / $0.12 per 1M tokens
- [Claude Opus 5.5 API](https://zurelay.com/models/claude-opus-5-5): `claude-opus-5-5`, $1.40 / $7.00 per 1M tokens
- [GPT-6 Astra API](https://zurelay.com/models/gpt-6-astra): `gpt-6-astra`, $2.50 / $12.50 per 1M tokens
- [Nano Banana 2.1 API](https://zurelay.com/models/nano-banana-2.1): `nano-banana-2.1`, from $0.03 per image
- [Nano Banana Pro API](https://zurelay.com/models/nano-banana-pro): `nano-banana-pro`, from $0.035 per image
- [Nano Banana 2 API](https://zurelay.com/models/nano-banana-2): `nano-banana-2`, from $0.025 per image
- [Nano Banana 2 Lite API](https://zurelay.com/models/nano-banana-2-lite): `nano-banana-2-lite`, $0.016 per image
- [Claude Sonnet 5.5 API](https://zurelay.com/models/claude-sonnet-5-5): `claude-sonnet-5-5`, $0.79 / $3.95 per 1M tokens
- [Claude Haiku 5.5 API](https://zurelay.com/models/claude-haiku-5-5): `claude-haiku-5-5`, $0.04 / $0.20 per 1M tokens
- [GPT-6.1 Sol API](https://zurelay.com/models/gpt-6.1-sol): `gpt-6.1-sol`, $0.50 / $2.50 per 1M tokens
- [GPT-6.1 Terra API](https://zurelay.com/models/gpt-6.1-terra): `gpt-6.1-terra`, $0.25 / $1.25 per 1M tokens
- [GPT-6 Sol API](https://zurelay.com/models/gpt-6-sol): `gpt-6-sol`, $0.50 / $2.50 per 1M tokens
- [GPT-6 Luna API](https://zurelay.com/models/gpt-6-luna): `gpt-6-luna`, $0.025 / $0.125 per 1M tokens
- [Grok 4.7 API](https://zurelay.com/models/grok-4.7): `grok-4.7`, $0.70 / $2.10 per 1M tokens
- [Muse Wonder API](https://zurelay.com/models/muse-wonder-1.0): `muse-wonder-1.0`, $1.20 / $6.00 per 1M tokens
- [MiMo V2.6 Pro API](https://zurelay.com/models/mimo-v2.6-pro): `mimo-v2.6-pro`, $0.32 / $0.64 per 1M tokens
- [MiMo V2.6 Flash API](https://zurelay.com/models/mimo-v2.6-flash): `mimo-v2.6-flash`, $0.075 / $0.15 per 1M tokens
- [DeepSeek V4.1 Flash 1017 API](https://zurelay.com/models/deepseek-v4.1-flash-1017): `deepseek-v4.1-flash-1017`, $0.03 / $0.12 per 1M tokens
- [DeepSeek V4.1 Flash API](https://zurelay.com/models/deepseek-v4.1-flash): `deepseek-v4.1-flash`, $0.03 / $0.12 per 1M tokens
- [DeepSeek V4 Flash API](https://zurelay.com/models/deepseek-v4-flash): `deepseek-v4-flash`, $0.03 / $0.12 per 1M tokens
- [DeepSeek V4 Flash 0731 API](https://zurelay.com/models/deepseek-v4-flash-0731): `deepseek-v4-flash-0731`, $0.029 / $0.087 per 1M tokens
- [DeepSeek V4 Pro 0813 API](https://zurelay.com/models/deepseek-v4-pro-0813): `deepseek-v4-pro-0813`, $0.23 / $0.62 per 1M tokens
- [Claude Fable 5.1 API](https://zurelay.com/models/claude-fable-5-1): `claude-fable-5-1`, $3.50 / $17.50 per 1M tokens
- [Claude Fable 5 API](https://zurelay.com/models/claude-fable-5): `claude-fable-5`, $3.50 / $17.50 per 1M tokens
- [Claude Opus 5 API](https://zurelay.com/models/claude-opus-5): `claude-opus-5`, $1.75 / $8.75 per 1M tokens
- [Claude Opus 4.8 API](https://zurelay.com/models/claude-opus-4-8): `claude-opus-4-8`, $2.40 / $12.00 per 1M tokens
- [Claude Opus 4.7 API](https://zurelay.com/models/claude-opus-4-7): `claude-opus-4-7`, $1.78 / $8.93 per 1M tokens
- [Claude Opus 4.6 API](https://zurelay.com/models/claude-opus-4-6): `claude-opus-4-6`, $2.40 / $12.00 per 1M tokens
- [Claude Haiku 4.5 API](https://zurelay.com/models/claude-haiku-4-5): `claude-haiku-4-5`, $0.54 / $2.70 per 1M tokens
- [GPT-5.6 Sol API](https://zurelay.com/models/gpt-5.6-sol): `gpt-5.6-sol`, $1.14 / $5.70 per 1M tokens
- [GPT-5.6 Terra API](https://zurelay.com/models/gpt-5.6-terra): `gpt-5.6-terra`, $0.54 / $3.26 per 1M tokens
- [GPT-5.6 Luna API](https://zurelay.com/models/gpt-5.6-luna): `gpt-5.6-luna`, $0.08 / $0.49 per 1M tokens
- [Gemini 4 Argon API](https://zurelay.com/models/gemini-4-argon): `gemini-4-argon`, $0.80 / $4.00 per 1M tokens
- [Gemini 3.1 Pro API](https://zurelay.com/models/gemini-3.1-pro): `gemini-3.1-pro`, $0.50 / $3.45 per 1M tokens
- [Gemini 3.8 Flash API](https://zurelay.com/models/gemini-3.8-flash): `gemini-3.8-flash`, $0.22 / $1.10 per 1M tokens
- [Gemini 3.7 Flash API](https://zurelay.com/models/gemini-3.7-flash): `gemini-3.7-flash`, $0.32 / $1.59 per 1M tokens
- [Gemini 3.5 Flash-Lite API](https://zurelay.com/models/gemini-3.5-flash-lite): `gemini-3.5-flash-lite`, $0.12 / $1.04 per 1M tokens
- [Gemini 3.1 Flash-Lite API](https://zurelay.com/models/gemini-3.1-flash-lite): `gemini-3.1-flash-lite`, $0.10 / $0.59 per 1M tokens
- [GLM-5.3 API](https://zurelay.com/models/glm-5.3): `glm-5.3`, $0.38 / $1.21 per 1M tokens
- [GLM-5.2 API](https://zurelay.com/models/glm-5.2): `glm-5.2`, $0.38 / $1.21 per 1M tokens
- [GLM-5.3 Flash API](https://zurelay.com/models/glm-5.3-flash): `glm-5.3-flash`, $0.058 / $0.19 per 1M tokens
- [GLM-5.3 FlashX API](https://zurelay.com/models/glm-5.3-flashx): `glm-5.3-flashx`, $0.12 / $0.40 per 1M tokens
- [Kimi K3.1 Pro API](https://zurelay.com/models/kimi-k3.1-pro): `kimi-k3.1-pro`, $0.80 / $4.00 per 1M tokens
- [Kimi K3.1 Pro Highspeed API](https://zurelay.com/models/kimi-k3.1-pro-highspeed): `kimi-k3.1-pro-highspeed`, $3.30 / $16.50 per 1M tokens
- [Kimi K3 API](https://zurelay.com/models/kimi-k3): `kimi-k3`, $1.27 / $6.37 per 1M tokens
- [Qwen 3.8 Max API](https://zurelay.com/models/qwen3.8-max): `qwen3.8-max`, $1.20 / $3.60 per 1M tokens
- [Qwen 3.8 Flash API](https://zurelay.com/models/qwen3.8-flash): `qwen3.8-flash`, $0.07 / $0.22 per 1M tokens
- [Qwen 3.8 Omni Flash API](https://zurelay.com/models/qwen3.8-omni-flash): `qwen3.8-omni-flash`, $0.075 / $0.235 per 1M tokens
- [MiniMax M3.1 Flash API](https://zurelay.com/models/minimax-m3.1-flash): `minimax-m3.1-flash`, $0.06 / $0.24 per 1M tokens
- [MiniMax M3 API](https://zurelay.com/models/minimax-m3): `minimax-m3`, $0.13 / $0.51 per 1M tokens
- [Step 5 Preview API](https://zurelay.com/models/step-5-preview): `step-5-preview`, $0.25 / $0.68 per 1M tokens
- [GPT Image 2.5 Flare API](https://zurelay.com/models/gpt-image-2.5-flare): `gpt-image-2.5-flare`, from $0.028 per image
- [GPT Image 2.5 Sunburst API](https://zurelay.com/models/gpt-image-2.5-sunburst): `gpt-image-2.5-sunburst`, from $0.026 per image
- [GPT Image 2 API](https://zurelay.com/models/gpt-image-2): `gpt-image-2`, $0.02 per image
- [Grok Imagine Image 2.0 API](https://zurelay.com/models/grok-imagine-image-2.0): `grok-imagine-image-2.0`, from $0.045 per image
- [FLUX 3 Image API](https://zurelay.com/models/flux-3-image): `flux-3-image`, from $0.04 per image
- [Seedance 2.5 API](https://zurelay.com/models/seedance-2.5): `seedance-2.5`, from $0.135 per second
- [Seedance 2.0 API](https://zurelay.com/models/seedance-2.0): `seedance-2.0`, from $0.097 per second
- [Seedance 2.0 Fast API](https://zurelay.com/models/seedance-2.0-fast): `seedance-2.0-fast`, from $0.074 per second
- [Kling 4.0 API](https://zurelay.com/models/kling-4.0): `kling-4.0`, from $0.15 per second
- [Seedance 2.0 Mini API](https://zurelay.com/models/seedance-2.0-mini): `seedance-2.0-mini`, from $0.047 per second
- [Kling 3.0 API](https://zurelay.com/models/kling-3.0): `kling-3.0`, from $0.125 per second
- [Gemini Omni Flash API](https://zurelay.com/models/gemini-omni-flash): `gemini-omni-flash`, from $0.042 per second
- [Wan 3.0 API](https://zurelay.com/models/wan-3.0): `wan-3.0`, from $0.039 per second
- [Grok Imagine Video 1.5 API](https://zurelay.com/models/grok-imagine-video-1.5): `grok-imagine-video-1.5`, from $0.071 per second
- [Veo 3.1 Fast API](https://zurelay.com/models/veo-3.1-fast): `veo-3.1-fast`, from $0.025 per second
- [Vidu Q3 Turbo API](https://zurelay.com/models/vidu-q3-turbo): `vidu-q3-turbo`, from $0.03 per second
- [PixVerse V6 API](https://zurelay.com/models/pixverse-v6): `pixverse-v6`, from $0.019 per second
- [MiniMax H3 API](https://zurelay.com/models/minimax-h3): `minimax-h3`, from $0.039 per second
- [Gemini 3.8 Flash TTS API](https://zurelay.com/models/gemini-3.8-flash-tts): `gemini-3.8-flash-tts`, $0.30 / $5.40 per 1M tokens
- [Gemini 3.1 Flash TTS API](https://zurelay.com/models/gemini-3.1-flash-tts): `gemini-3.1-flash-tts`, $0.60 / $12.00 per 1M tokens
- [Gemini 2.5 Pro TTS API](https://zurelay.com/models/gemini-2.5-pro-tts): `gemini-2.5-pro-tts`, $0.60 / $12.00 per 1M tokens
- [Gemini 2.5 Flash TTS API](https://zurelay.com/models/gemini-2.5-flash-tts): `gemini-2.5-flash-tts`, $0.30 / $6.00 per 1M tokens
- [GPT-6 Luna Decisions API](https://zurelay.com/models/gpt-6-luna-decisions): `gpt-6-luna-decisions`, $0.04 per 1M input tokens
- [Jev 1.14 API](https://zurelay.com/models/jev-1.14): `jev-1.14`, $0.024 per 1M input tokens
- [Jev 1.13 API](https://zurelay.com/models/jev-1.13): `jev-1.13`, $0.035 per 1M input tokens
- [Kimi K2.6 API](https://zurelay.com/models/kimi-k2.6): `kimi-k2.6`, $0.30 / $1.30 per 1M tokens
- [Kimi K2.5 API](https://zurelay.com/models/kimi-k2.5): `kimi-k2.5`, $0.20 / $0.95 per 1M tokens
- [MiniMax M2.5 API](https://zurelay.com/models/minimax-m2.5): `minimax-m2.5`, $0.10 / $0.39 per 1M tokens
- [Ministral 3 3B API](https://zurelay.com/models/ministral-3-3b): `ministral-3-3b`, $0.03 / $0.03 per 1M tokens
- [Ministral 3 14B API](https://zurelay.com/models/ministral-3-14b): `ministral-3-14b`, $0.06 / $0.06 per 1M tokens
- [Muse Spark 1.3 Contributor API](https://zurelay.com/models/muse-spark-1.3-contributor): `muse-spark-1.3-contributor`, $0.04 / $0.08 per 1M tokens
- [Abliterated Large V2 API](https://zurelay.com/models/abliterated-large-v2): `abliterated-large-v2`, $2.90 / $4.85 per 1M tokens
- [Text Embedding 3 Small API](https://zurelay.com/models/text-embedding-3-small): `text-embedding-3-small`, $0.01 per 1M input tokens
- [Text Embedding 3 Large API](https://zurelay.com/models/text-embedding-3-large): `text-embedding-3-large`, $0.065 per 1M input tokens

## Pricing and comparisons

- [Claude API pricing](https://zurelay.com/claude-api): every Claude model with Anthropic's list price beside Zurelay's
- [GPT API pricing](https://zurelay.com/gpt-api): every GPT model with OpenAI's list price beside Zurelay's
- [Gemini API pricing](https://zurelay.com/gemini-api): every Gemini model with Google's list price beside Zurelay's
- [DeepSeek API pricing](https://zurelay.com/deepseek-api): every DeepSeek model with DeepSeek's list price beside Zurelay's
- [Grok API pricing](https://zurelay.com/grok-api): every Grok model, for chat, images and video, with Zurelay's prices
- [Qwen API pricing](https://zurelay.com/qwen-api): every Qwen model with Alibaba's list price beside Zurelay's
- [GLM API pricing](https://zurelay.com/glm-api): every GLM model with Z.ai's list price beside Zurelay's
- [MiniMax API pricing](https://zurelay.com/minimax-api): every MiniMax model, for chat and video, with Zurelay's prices
- [MiMo API pricing](https://zurelay.com/mimo-api): every MiMo model with Xiaomi's list price beside Zurelay's
- [Kimi API pricing](https://zurelay.com/kimi-api): every Kimi model with Moonshot AI's list price beside Zurelay's
- [Nano Banana API pricing](https://zurelay.com/nano-banana-api): every Nano Banana model with its price per image
- [GPT Image API pricing](https://zurelay.com/gpt-image-api): every GPT Image model with its price per image
- [Seedance API pricing](https://zurelay.com/seedance-api): every Seedance model with its price per second of video
- [Text-to-speech API pricing](https://zurelay.com/text-to-speech-api): every text-to-speech model with its price per minute of speech
- [AI image API pricing](https://zurelay.com/ai-image-api): every AI image model with its price per image
- [AI video API pricing](https://zurelay.com/ai-video-api): every AI video model with its price per second of video
- [Cheapest LLM APIs, compared](https://zurelay.com/cheapest-llm-api): every chat model ranked by what a typical workload costs, beside each lab's list price
- [Claude Code pricing](https://zurelay.com/claude-code): what Claude Code costs on Claude's Pro, Max, Team and Enterprise plans and on the API, Zurelay's prices beside Anthropic's (cache prices included), and the setup
- [OpenAI-compatible base URLs](https://zurelay.com/openai-compatible-base-urls): the base_url for every major provider that takes the OpenAI SDK, and the ANTHROPIC_BASE_URL values for Claude Code, each from the provider's own docs
- [LLM API cost calculator](https://zurelay.com/llm-cost-calculator): a month of any workload priced on every chat model, at list price and on Zurelay
- [Is Claude down? Claude status](https://zurelay.com/claude-status): Anthropic's live status for claude.ai, the Claude API and Claude Code, its recent incidents, and how each Claude model is answering on Zurelay
- [Is ChatGPT down? OpenAI status](https://zurelay.com/chatgpt-status): OpenAI's live status for ChatGPT, the OpenAI API and Codex, its recent incidents, and how each GPT model is answering on Zurelay
- [Token counter](https://zurelay.com/token-counter): count a text's tokens with OpenAI's o200k_base tokenizer in the browser, with estimated Claude and Gemini counts and its cost on every chat model
- [Anthropic API alternative](https://zurelay.com/anthropic-api-alternative), [OpenAI API alternative](https://zurelay.com/openai-api-alternative), [fal.ai alternative](https://zurelay.com/fal-ai-alternative): prices side by side, and when to go direct instead
- [Price data](https://zurelay.com/prices.json) ([CSV](https://zurelay.com/prices.csv)): every model's live price and list price, free to reuse with a link back (CC BY 4.0); daily history on GitHub at https://github.com/zutrue/llm-api-prices
- [Compare models head to head](https://zurelay.com/compare): Claude Opus 5.5 vs GPT-6 Astra and other pairs, specs and live prices
- [LLM API price widget](https://zurelay.com/price-widget): a free, embeddable table of live model prices for blogs and docs
- [What cheap AI APIs are really selling](https://zurelay.com/research/fake-models): 142 blocked listings, the six kinds of fake, and five checks for any API
- [Claude vs GPT API pricing](https://zurelay.com/claude-vs-gpt): Anthropic's and OpenAI's models matched tier by tier
- [Claude vs Gemini](https://zurelay.com/claude-vs-gemini), [GPT vs Gemini](https://zurelay.com/gpt-vs-gemini), [DeepSeek vs Claude](https://zurelay.com/deepseek-vs-claude): the same, for each pairing
- [OpenRouter alternative](https://zurelay.com/openrouter-alternative): Zurelay and OpenRouter compared, prices and fees

## AI agents

- [Zurelay skill for AI agents](https://zurelay.com/skill.md): an Agent Skill (SKILL.md) that teaches any agent to connect (a link its person approves, no key to copy) and make videos, images and speech, with live models and prices
- [Connecting an AI agent](https://zurelay.com/docs/authentication#connecting-an-ai-agent): POST https://api.zurelay.com/connect for an approval link, then POST /connect/key for the agent's own key
- [AI agents](https://zurelay.com/agents): connecting Grok Bot, OpenAI dots, Meta Muse, Gemini Spark, OpenClaw, Hermes Agent, Manus and Perplexity
- [Grok Bot with Zurelay](https://zurelay.com/agents/grok-bot): Give Grok Bot video, image and voiceover tools: paste one message, sign in to Zurelay, and your Bots make Seedance, Kling and Veo videos and Nano Banana images from your prepaid balance.
- [OpenAI dots with Zurelay](https://zurelay.com/agents/openai-dots): Let your OpenAI dot make videos, images and voiceovers: add Zurelay as a ChatGPT plugin, or paste one message and approve the link it sends. Seedance, Kling, Veo and Nano Banana, prepaid.
- [Meta Muse with Zurelay](https://zurelay.com/agents/meta-muse): Add Zurelay to Meta Muse as a custom connector and make videos, images and voiceovers in any chat, on the web, in the app or in WhatsApp. Seedance, Kling, Veo and Nano Banana, prepaid.
- [Gemini Spark with Zurelay](https://zurelay.com/agents/gemini-spark): Add Zurelay to Gemini Spark as a custom app and your 24/7 agent can make videos, images and voiceovers with Seedance, Kling, GPT Image and more, from a prepaid balance.
- [OpenClaw with Zurelay](https://zurelay.com/agents/openclaw): Paste one message into OpenClaw and it can make videos, images and voiceovers, and run on Claude, GPT, Gemini or DeepSeek below list price. Approve one link, no key to copy.
- [Hermes Agent with Zurelay](https://zurelay.com/agents/hermes-agent): Install Zurelay’s skill in Hermes Agent with one command to make videos, images and voiceovers, and run Hermes on Claude, GPT, Gemini or DeepSeek with the same key.
- [Manus with Zurelay](https://zurelay.com/agents/manus): Add Zurelay to Manus as a custom MCP server and it can make videos, images and voiceovers inside any task: Seedance, Kling, Veo, Nano Banana and Gemini voices, paid per use.
- [Perplexity with Zurelay](https://zurelay.com/agents/perplexity): Add Zurelay to Perplexity as a remote custom connector and make videos, images and voiceovers in a thread, with Seedance, Kling, Veo, Nano Banana and Gemini voices.

## Guides

- [How to get a Claude API key](https://zurelay.com/guides/claude-api-key): Get a Claude API key from the Claude Console in four steps, what it costs, why Claude Pro doesn't include the API, the API credits in Max and Team, and keys for Claude Code.
- [How to get an OpenAI API key](https://zurelay.com/guides/openai-api-key): Get an OpenAI API key in a few steps: the API keys page, project keys and permissions, the $5 minimum credit, usage tiers, and why ChatGPT Plus doesn't include the API.
- [How to get a Gemini API key](https://zurelay.com/guides/gemini-api-key): Get a Gemini API key in Google AI Studio, what the free tier covers and what Google does with free-tier prompts, how to turn on billing, and the new auth keys.
- [How to get a DeepSeek API key](https://zurelay.com/guides/deepseek-api-key): Get a DeepSeek API key on the DeepSeek Platform, top up by card, PayPal, Alipay or WeChat Pay, use it with the OpenAI SDK or Claude Code, and pay less at off-peak hours.
- [Claude Code Router: run Claude Code on DeepSeek, GPT and other models](https://zurelay.com/guides/claude-code-router): Set up Claude Code Router 3 so Claude Code runs on DeepSeek, GPT, Gemini or any OpenAI-compatible model: install, provider, the protocol setting that breaks it, profiles, and what a task cost in our test.
- [OpenRouter pricing explained: fees, free models and promo codes](https://zurelay.com/guides/openrouter-pricing): What OpenRouter really costs: the 5.5% and 8% credit fees, BYOK, free model limits (50 or 1,000 requests a day), whether credits expire, promo codes, and what the same models cost below list.
- [How much does Claude Code cost on the API?](https://zurelay.com/guides/claude-code-cost): What Claude Code costs on the API: the four kinds of tokens it bills, a worked monthly example on Opus, Sonnet and Haiku, and how to spend less.
- [Prompt caching explained: how it cuts LLM API bills](https://zurelay.com/guides/prompt-caching): How prompt caching works, what cached tokens cost on Claude, GPT, Gemini and DeepSeek, how to structure prompts to hit the cache, and how to check it worked.
- [How to cut your LLM API bill: seven ways that work](https://zurelay.com/guides/cut-llm-api-costs): Seven ways to spend less on LLM APIs: the right model tier, prompt caching, capped output, less context, routing, fewer retries and a lower price per token.
- [What is an OpenAI-compatible API? How to switch providers in one line](https://zurelay.com/guides/openai-compatible-api): What an OpenAI-compatible API is, how to point the OpenAI SDK at another provider by changing the base URL, and what to check before you switch.

## Optional

- [Model pages](https://zurelay.com/models): one page per model with prices, speed, status and examples.
- [Support](https://zurelay.com/support): questions and sales, answered by email. Customers can also use Support in the dashboard.