# RunBridge AI

> RunBridge AI developer documentation for LLM text APIs, GPT Image, Google Nano Banana, and Grok image generation and editing.

- [RunBridge AI documentation](https://docs.runbridge.ai/index.md): RunBridge AI documentation for LLM requests and image generation with GPT Image, Google Nano Banana, and Grok.
- [Start with RunBridge AI: create an API key and make your first call](https://docs.runbridge.ai/overview/quick-start.md): Start with RunBridge AI by creating an API key, setting the base URL, and sending your first curl, Python, or Node.js API request.
- [Configure RunBridge AI account, billing, and base URL](https://docs.runbridge.ai/overview/important-guidelines.md): Configure RunBridge AI account basics: review your balance, create API keys, choose text or image model IDs, set the base URL, and review usage logs.
- [List available RunBridge AI models](https://docs.runbridge.ai/overview/models.md): Use GET /api/models to fetch the RunBridge AI model catalog and choose model IDs for text and image requests.
- [Model API quickstarts: build with RunBridge AI models](https://docs.runbridge.ai/quickstarts/index.md): Choose a RunBridge AI quickstart for text requests, GPT Image, or Google Nano Banana with curl, Python, and Node.js examples.
- [OpenAI-compatible API quickstart: Send Chat Completions requests with RunBridge AI](https://docs.runbridge.ai/quickstarts/text/openai-compatible-api.md): Use RunBridge AI as an OpenAI API-compatible base URL for Chat Completions requests with curl, Python, Node.js, and OpenAI SDKs.
- [Claude API quickstart: Send Messages requests with RunBridge AI](https://docs.runbridge.ai/quickstarts/text/claude-api.md): Call Claude models through RunBridge AI's Anthropic-compatible Messages API with curl, Python, and Node.js.
- [Gemini API quickstart: Use native and OpenAI-compatible requests with RunBridge AI](https://docs.runbridge.ai/quickstarts/text/gemini-api.md): Call Gemini text models through RunBridge AI with native generateContent requests or OpenAI-compatible Chat Completions requests.
- [GPT Image API quickstart: Generate images with RunBridge AI](https://docs.runbridge.ai/quickstarts/image/gpt-image-api.md): Generate a GPT image through RunBridge AI, decode b64_json, and save the result with curl, Python, or Node.js.
- [Gemini image API quickstart: Generate Nano Banana images with RunBridge AI](https://docs.runbridge.ai/quickstarts/image/gemini-image-api.md): Generate images with Gemini image models through RunBridge AI, including Nano Banana model families, and save inlineData output with curl, Python, or Node.js.
- [Use RunBridge AI with OpenAI SDKs](https://docs.runbridge.ai/guides/use-runbridge-with-openai-sdk.md): Configure the OpenAI Python and Node.js SDKs for RunBridge AI by setting the RunBridge AI API key and base URL.
- [Change the base URL to RunBridge AI](https://docs.runbridge.ai/guides/change-base-url-to-runbridge.md): Route an OpenAI-compatible client or direct HTTP request to RunBridge AI by setting the base URL to https://api.runbridge.ai/v1.
- [Build model and provider fallback with RunBridge AI](https://docs.runbridge.ai/guides/model-fallback-with-runbridge.md): Keep RunBridge AI as the primary route, switch models inside RunBridge AI first, and use an official provider as an optional final fallback.
- [Handle API errors and retries with RunBridge AI](https://docs.runbridge.ai/guides/error-codes-and-retry-strategy.md): Handle RunBridge AI errors by separating request-shape problems, authentication failures, rate limits, and retryable platform failures.
- [Handle rate limits and concurrency](https://docs.runbridge.ai/guides/rate-limits-and-concurrency.md): Handle RunBridge AI rate limits by capping request concurrency, retrying 429 responses with jitter, and monitoring usage by model and route.
- [List available RunBridge AI models](https://docs.runbridge.ai/guides/how-to-list-available-models.md): List available RunBridge AI models with the model catalog endpoint and use the model directory to confirm capabilities and pricing.
- [Estimate request cost before calling a model](https://docs.runbridge.ai/guides/how-to-estimate-cost-before-calling-a-model.md): Estimate RunBridge AI request cost before a model call by combining model directory pricing with input size, output limits, or task count.
- [Use RunBridge AI docs with LLMs](https://docs.runbridge.ai/guides/how-to-use-runbridge-docs-with-llms.md): Use RunBridge AI llms.txt and llms-full.txt with coding assistants, retrieval systems, and model prompts.
- [Handle error codes](https://docs.runbridge.ai/errors/error-codes-handling.md): Use this guide to classify RunBridge AI error responses and apply retry or fix steps for common request failures.
- [Help Center](https://docs.runbridge.ai/support/help-center.md): RunBridge AI Help Center for rate multipliers, pricing updates, concurrency limits, maintenance windows, error handling, and privacy logging policies.
- [Interface stability](https://docs.runbridge.ai/support/interface-stability.md): Understand request, token, and image throughput metrics and handle RunBridge AI rate-limit responses.
- [Common Misconceptions](https://docs.runbridge.ai/support/common-misconceptions.md): Fix RunBridge AI token and Key issues: remove token quota limits, set correct Base URL, avoid invalid token errors, and understand concurrency RPM/TPM behavior.
- [Usage FAQ](https://docs.runbridge.ai/support/confusion-about-use.md): Common RunBridge AI questions about text and image models, Anthropic Messages, Gemini input, API errors, and account basics.
- [Text and chat APIs](https://docs.runbridge.ai/api/text/index.md): Choose the RunBridge AI text and chat API that fits your request format: Chat Completions, Responses, Anthropic Messages, or Gemini content generation.
- [Create a chat completion](https://docs.runbridge.ai/api/text/chat.md): Use RunBridge AI POST /v1/chat/completions to send multi-message conversations to chat models with streaming, structured output, and tool calling.
- [Create a model response](https://docs.runbridge.ai/api/text/responses.md): Use RunBridge AI POST /v1/responses to create multimodal model responses and conversation history with built-in tools and function calling.
- [Create a Message](https://docs.runbridge.ai/api/text/anthropic-messages.md): Call Claude through the RunBridge AI Messages endpoint with text and image input, adaptive thinking, prompt caching, streaming, and tools.
- [Generate content](https://docs.runbridge.ai/api/text/gemini-generating-content.md): Use the Gemini native API format through RunBridge AI for text generation, video input, thinking summaries, Google Search grounding, JSON output, and streaming.
- [Image generation and editing APIs](https://docs.runbridge.ai/api/image/index.md): Choose RunBridge AI image generation and editing routes for GPT Image, Google Nano Banana, and Grok.
- [Create an image](https://docs.runbridge.ai/api/image/openai/images.md): Use RunBridge AI POST /v1/images/generations to create GPT images with output-format, quality, background, streaming, and async controls.
- [Retrieve an image generation task](https://docs.runbridge.ai/api/image/openai/image-generation-task.md): Poll an async GPT image generation task on RunBridge AI and retrieve its final Base64 image data.
- [Create image edit](https://docs.runbridge.ai/api/image/openai/image-editing.md): Use POST /v1/images/edits in RunBridge AI to edit images with multipart uploads, masks, GPT image models, and encoded image output controls.
- [Generate images with Gemini](https://docs.runbridge.ai/api/image/gemini/gemini-generates-image.md): Generate and edit Nano Banana images through RunBridge AI with the Gemini generateContent API, image options, and final inlineData output.
- [Use Nano Banana image models](https://docs.runbridge.ai/api/image/gemini/generate-image-guide.md): Call Gemini image models (Nano Banana 2 / Pro) on RunBridge AI using the Google Gen AI SDK for text-to-image, image-to-image, and multi-image composition.
- [Generate images with Grok](https://docs.runbridge.ai/api/image/grok/image-generation.md): Generate images with Grok Imagine Image 2.0, including quality, aspect ratio, resolution, image-count, and response-format controls.
- [Edit images with Grok](https://docs.runbridge.ai/api/image/grok/image-editing.md): Edit one or more images with Grok by sending image URLs or data URIs in a JSON request.
- [Get current API key](https://docs.runbridge.ai/api/api-keys/get-current-api-key.md): Use RunBridge AI GET /api/usage/token to retrieve quota, usage, expiration, and model-limit details for the bearer API key.
- [List API keys](https://docs.runbridge.ai/api/api-keys/list-api-keys.md): Use RunBridge AI GET /api/token/ to list API keys for the authenticated account with pagination.
- [Create an API key](https://docs.runbridge.ai/api/api-keys/create-api-key.md): Use RunBridge AI POST /api/token/ to create an API key for the authenticated account.
- [Retrieve an API key](https://docs.runbridge.ai/api/api-keys/get-api-key.md): Use RunBridge AI GET /api/token/{id} to retrieve one API key record by ID for the authenticated account.
- [Delete an API key](https://docs.runbridge.ai/api/api-keys/delete-api-key.md): Use RunBridge AI DELETE /api/token/{id} to delete one API key by ID for the authenticated account.
- [Update an API key](https://docs.runbridge.ai/api/api-keys/update-api-key.md): Use RunBridge AI PUT /api/token/ to update an API key by ID with editable fields in the JSON body.
- [Connect your tools to RunBridge AI](https://docs.runbridge.ai/integrations/index.md): Configure RunBridge AI in Codex, Claude Code, OpenCode, Hermes Agent, OpenClaw, Gemini CLI, Cline, and Continue.
- [Use Codex with RunBridge AI](https://docs.runbridge.ai/integrations/codex.md): Configure a custom Codex provider with the Responses API and your RunBridge AI key.
- [Use Claude Code with RunBridge AI](https://docs.runbridge.ai/integrations/claude-code.md): Connect Claude Code to the Anthropic Messages API with a RunBridge AI gateway credential.
- [Use OpenCode with RunBridge AI](https://docs.runbridge.ai/integrations/opencode.md): Configure OpenCode with a custom OpenAI-compatible provider for RunBridge AI Chat Completions.
- [Use Gemini CLI with RunBridge AI](https://docs.runbridge.ai/integrations/gemini-cli.md): Use Gemini CLI gateway mode with the RunBridge AI Gemini-compatible endpoint.
- [Use Hermes Agent with RunBridge AI](https://docs.runbridge.ai/integrations/hermes-agent.md): Configure a custom Hermes Agent provider for RunBridge AI Chat Completions.
- [Use OpenClaw with RunBridge AI](https://docs.runbridge.ai/integrations/openclaw.md): Register a RunBridge AI custom provider and choose it as the default OpenClaw model.
- [Use Cline with RunBridge AI](https://docs.runbridge.ai/integrations/cline.md): Set up Cline with a RunBridge AI OpenAI-compatible endpoint, model, and capabilities.
- [Use Continue with RunBridge AI](https://docs.runbridge.ai/integrations/continue.md): Add RunBridge AI to Continue through the OpenAI provider and a local YAML configuration.

## OpenAPI Specs

- [create-api-key.openapi](/api/openapi/api-keys/create-api-key.openapi.json)
- [delete-api-key.openapi](/api/openapi/api-keys/delete-api-key.openapi.json)
- [get-api-key.openapi](/api/openapi/api-keys/get-api-key.openapi.json)
- [get-current-api-key.openapi](/api/openapi/api-keys/get-current-api-key.openapi.json)
- [list-api-keys.openapi](/api/openapi/api-keys/list-api-keys.openapi.json)
- [update-api-key.openapi](/api/openapi/api-keys/update-api-key.openapi.json)
- [post-gemini-generates-image.openapi](/api/openapi/image/gemini/post-gemini-generates-image.openapi.json)
- [post-image-editing.openapi](/api/openapi/image/grok/post-image-editing.openapi.json)
- [post-image-generation.openapi](/api/openapi/image/grok/post-image-generation.openapi.json)
- [get-image-generation-task.openapi](/api/openapi/image/openai/get-image-generation-task.openapi.json)
- [post-image-editing.openapi](/api/openapi/image/openai/post-image-editing.openapi.json)
- [post-images.openapi](/api/openapi/image/openai/post-images.openapi.json)
- [get-models.openapi](/api/openapi/overview/get-models.openapi.json)
- [post-anthropic-messages.openapi](/api/openapi/text/post-anthropic-messages.openapi.json)
- [post-chat.openapi](/api/openapi/text/post-chat.openapi.json)
- [post-gemini-generating-content.openapi](/api/openapi/text/post-gemini-generating-content.openapi.json)
- [post-responses.openapi](/api/openapi/text/post-responses.openapi.json)


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