# Inception Platform

- [Inception Platform](https://docs.inceptionlabs.ai/index.md): Build with Mercury — the fastest reasoning and code models, served through an OpenAI-compatible API.
- [Quick Start](https://docs.inceptionlabs.ai/get-started.md): Create an account, generate an API key, and send your first request to Mercury 2.5.
- [Authentication](https://docs.inceptionlabs.ai/get-started/authentication.md): Generate API keys in the Inception Platform dashboard.
- [Models](https://docs.inceptionlabs.ai/get-started/models.md): Compare models, capabilities, and pricing.
- [SDKs](https://docs.inceptionlabs.ai/get-started/sdks.md): Official Python and TypeScript client libraries for the Inception API.
- [Rate Limits](https://docs.inceptionlabs.ai/get-started/rate-limits.md): Per-minute request, input token, and output token rate limits for the Inception API across the Free, Pay As You Go, and Enterprise tiers.
- [Create a decision](https://docs.inceptionlabs.ai/api-reference/decisions/create-a-decision.md): Evaluate named questions against a shared state with Mercury Decide. Supports binary probability (`noul`), categorical choice, and ordinal score questions. Returns answers and token usage. Streaming is not supported.
- [Create a chat completion](https://docs.inceptionlabs.ai/api-reference/chat/create-a-chat-completion.md): Generate a chat completion from a sequence of messages. Returns a `ChatCompletion` object, or a server-sent events stream of `ChatCompletionChunk` deltas when `stream=true`. Supports tool calling, structured output via `response_format`, and reasoning controls.
- [Create a fill-in-the-middle completion](https://docs.inceptionlabs.ai/api-reference/fim/create-a-fill-in-the-middle-completion.md): Generate a code completion given a `prompt` (prefix) and optional `suffix`. Designed for IDE-style inline completion. Returns a `FimCompletion` object, or a server-sent events stream of `FimCompletionChunk` deltas when `stream=true`. Tool calling and function calling are not supported.
- [Create a code edit completion](https://docs.inceptionlabs.ai/api-reference/edit/create-a-code-edit-completion.md): Generate an edit to a code region given the surrounding context. The request must contain a single user message whose content includes the required edit prompt tags (e.g. `<|code_to_edit|>`, `<|cursor|>`, `<|current_file_content|>`). Returns an `EditCompletion` object. Streaming and tool calling are…
- [List available models](https://docs.inceptionlabs.ai/api-reference/models/list-available-models.md): List the models currently available through the API.
- [List chat models](https://docs.inceptionlabs.ai/api-reference/models/list-chat-models.md): List models available for chat completions.
- [List FIM models](https://docs.inceptionlabs.ai/api-reference/models/list-fim-models.md): List models available for fill-in-the-middle completions.
- [List Edit models](https://docs.inceptionlabs.ai/api-reference/models/list-edit-models.md): List models available for edit completions.
- [Reasoning Efforts](https://docs.inceptionlabs.ai/capabilities/reasoning-efforts.md): Choose how much Mercury reasoning models deliberate before responding, from near-instant answers to deeper multi-step reasoning.
- [Streaming & Diffusion](https://docs.inceptionlabs.ai/capabilities/streaming.md): Stream Mercury 2.5 chat completions or enable the diffusion mode to visualize how the model iteratively denoises text into the final answer.
- [Tool Use](https://docs.inceptionlabs.ai/capabilities/tool-use.md): Use tool calling on the Mercury 2.5 chat completions endpoint to let the model invoke functions, fetch data, and orchestrate multi-step agent workflows.
- [Structured Outputs](https://docs.inceptionlabs.ai/capabilities/structured-outputs.md): Constrain Mercury 2.5 chat completions to a JSON schema using structured outputs, so your application receives typed, machine-parseable responses.
- [Decisions](https://docs.inceptionlabs.ai/capabilities/decisions.md): Use Mercury Decide to classify, score, and make structured decisions over shared context.
- [Autocomplete (FIM)](https://docs.inceptionlabs.ai/capabilities/fim.md): Generate inline code autocomplete suggestions with the Inception fill-in-the-middle (FIM) endpoint, powered by the Mercury Edit 2 code model.
- [Next Edit](https://docs.inceptionlabs.ai/capabilities/next-edit.md): Predict a developer's next code edit with the Inception Next Edit endpoint and Mercury Edit 2 using recent snippets, file context, and edit history.
- [Prompt Guide](https://docs.inceptionlabs.ai/resources/prompt-guide.md): Practical prompting techniques for Mercury 2.5 across voice, tool-calling, search, and code agents.
- [Voice Quickstart](https://docs.inceptionlabs.ai/usecases/voice.md): Get started with Mercury 2.5 for voice applications.
- [Search Agent: Mercury 2.5 + Web Search](https://docs.inceptionlabs.ai/cookbooks/search-agent-mercury.md): Build an iterative web search agent that plans, searches, and synthesizes cited answers with Mercury 2.5.
- [Voice Customer Support Agent: Mercury 2.5 + Tool Calling + Voice](https://docs.inceptionlabs.ai/cookbooks/customer-support-agent-mercury.md): Build a voice-enabled dental clinic support agent that uses Mercury 2.5 tool calling to read and write a live appointment database, with ElevenLabs speech-to-text and text-to-speech.
- [Realtime Voice Assistant: Mercury 2.5 + ElevenLabs](https://docs.inceptionlabs.ai/cookbooks/realtime-voice-assistant.md): Stream Mercury 2.5 in ElevenLabs for a low-latency voice assistant.
- [Natural Language SQL Agent: Mercury 2.5 + Tool Calling](https://docs.inceptionlabs.ai/cookbooks/natural-language-sql-agent.md): Build a natural language SQL agent that uses Mercury 2.5.
- [Coding Agent: Mercury 2.5 + Tool Calling](https://docs.inceptionlabs.ai/cookbooks/coding-agent-mercury-tool-calling.md): A minimal, runnable coding agent built on Mercury 2.5 tool calling.
- [Claude Code](https://docs.inceptionlabs.ai/integrations/claude-code.md): Run Claude Code with Mercury 2.5 through a local LiteLLM bridge.
- [Hermes Agent](https://docs.inceptionlabs.ai/integrations/hermes.md): Run Hermes Agent with Mercury 2.5 through Inception's API.
- [Cursor](https://docs.inceptionlabs.ai/integrations/cursor.md): Set up Cursor to use Mercury 2.5.
- [Zed](https://docs.inceptionlabs.ai/integrations/zed.md): Configure the Zed editor's Edit Predictions feature with your Inception API key to receive next-edit suggestions powered by Mercury Edit 2.
- [Kilo Code](https://docs.inceptionlabs.ai/integrations/kilo-code.md): Run Kilo Code with Mercury 2.5 through Inception's API.
- [OpenCode](https://docs.inceptionlabs.ai/integrations/opencode.md): Run OpenCode with Mercury 2.5 through Inception's API.
- [OpenClaw](https://docs.inceptionlabs.ai/integrations/open-claw.md): Configure OpenClaw to use Mercury 2.5.
- [LangChain](https://docs.inceptionlabs.ai/integrations/langchain.md): Call Mercury 2.5 from LangChain.
- [ElevenLabs](https://docs.inceptionlabs.ai/integrations/elevenlabs.md): Wire Mercury 2.5 into the ElevenLabs Agents platform as a custom LLM.
- [Vapi](https://docs.inceptionlabs.ai/integrations/vapi.md): Build a low-latency voice agent in Vapi using Mercury 2.5.
- [Inception Chat](https://docs.inceptionlabs.ai/resources/chat.md)
- [Error Codes](https://docs.inceptionlabs.ai/resources/error-codes.md): Reference for HTTP status codes returned by the Inception API.
- [Frequently Asked Questions](https://docs.inceptionlabs.ai/resources/faq.md): Answers to common questions about the Inception API.
- [Contact Support](https://docs.inceptionlabs.ai/support/support.md)
- [Terms of Use](https://docs.inceptionlabs.ai/support/tou.md)
- [Privacy Policy](https://docs.inceptionlabs.ai/support/privacy.md)

## OpenAPI Specs

- [openapi](https://api.inceptionlabs.ai/openapi.json)


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