Documentation
From quick start to API reference: setup, billing and common questions. These articles are also available through Documentation in the console.
Getting started
Agent image generationSet up the image-generation Skill once, then ask your AI to create an image or edit an existing one through Yomi API.Quick startWelcome to Yomi API! This guide walks you through signing up, adding credit, creating a key and making your first model call in minutes.Platform featuresGetting started Platform features OpenAI-compatible access Yomi API provides OpenAI-compatible access to leading models worldwide through a single int…PricingGetting started Pricing Pricing principles Yomi API offers competitive prices while maintaining service quality: International model pricing: Prices f…Asynchronous image generationGetting started Asynchronous image generation Submit an image task to receive a task ID, query its status, then download the images. You can also rece…
Connect an agent
Claude Code CLIClaude Code is an AI coding assistant that runs in your terminal. Set a few environment variables to call claude-sonnet-5 and claude-opus-4-8 through …Codex CLICodex is an AI coding agent that runs in your terminal. Point its provider to Yomi API in config.toml to use models such as gpt-5.6-sol and gpt-5.6-te…DeepSeek HarnessDeepSeek Harness (command: dsh) is an AI coding agent released by DeepSeek on August 13, 2026, with a web interface, session management and tool calli…OpenClawOpenClaw is an open-source AI assistant gateway and bot framework with OpenAI-compatible API support. Point its model provider to Yomi API to use all …CC-SwitchCC-Switch manages provider switching for CLI tools including Claude Code, Codex, Gemini CLI and Grok Build. Add Yomi API as a custom provider to switc…WorkBuddyWorkBuddy is a desktop AI work assistant with custom API support. Enter the Yomi API address, key and model ID to use the platform's chat models in Wo…VSCode + ClineCline is an AI coding agent extension for VS Code. Point its API provider to Yomi API to read and modify code in your editor using models such as clau…Cherry StudioCherry Studio is a cross-platform desktop AI client with custom model provider support. Add Yomi API as a provider to call models from different provi…Other OpenAI-compatible toolsAny tool supporting OpenAI-compatible or custom APIs can connect to Yomi API with three values: the API address, API key and model ID.
API reference
API overview and authenticationThis article explains Yomi API's basics: the service address, authentication, available endpoints and common error codes. See the individual articles …Image understanding (vision)Vision uses multimodal Chat Completions messages. Include text and images together for visual questions, OCR and scene descriptions, without a separat…Video understandingVideo understanding also uses Chat Completions. Supply video content parts in a message for multimodal content recognition, scene description and key-…Chat CompletionsChat Completions is the platform's most commonly used endpoint for multi-turn conversations and text generation. It is fully compatible with the OpenA…Image generationThe Images API generates and edits images using the OpenAI-compatible images format. This article covers general usage. See the Media generation secti…Embeddings and moderationThis article covers two endpoints. Embeddings converts text into semantic vectors for semantic search and RAG applications. Moderations detects policy…List and query modelsUse the Models API to query models available to the current key, display model choices dynamically or validate a model ID.Choosing a modelA quick guide to choosing models by use case and budget. Refer to the Model Catalog (Models in the console) for capabilities and current prices.
Media generation
Nano Banana generation and editingNano Banana is an image generation and editing model family based on Google's Gemini image capabilities (an industry model). Check the Model Catalog (…GPT Image 2.5 generationGPT Image is OpenAI's image generation and editing model family, known for precise text rendering inside images and compatibility with the OpenAI Imag…Veo 4 video generationVeo is a video-generation model family known for consistency across long shots and physical realism. It supports text-to-video and image-to-video thro…
Developer integration
SDK integrationYomi API is fully compatible with the OpenAI API standard. Use the official OpenAI SDK and change only base_url and api_key to access all platform mod…OpenAI Responses APIResponses API is OpenAI's interface for agent applications, adding tool calling and other agent capabilities to conversational generation. Yomi API su…Using Claude modelsYomi API offers Claude models through both OpenAI-compatible and native Anthropic formats. Choose the format that fits your existing stack.Gemini native formatYomi API supports Gemini's native generateContent format through /v1beta routes for projects using the provider's native SDK style. See the Model Cata…Switching modelsYomi API's main advantage is one codebase for multiple models. After setting up the OpenAI format, change only the model parameter to switch models.
Help and support
Frequently asked questionsHelp and support Frequently asked questions How do I switch models? Change the model parameter in your request; the rest of the code stays the same. F…Accounts and API keysHelp and support Accounts and API keys How do I sign in and manage my account? Sign-in methods: Sign in with an email verification code (an account is…Billing and concurrencyHelp and support Billing and concurrency How do key billing modes differ? Billing basis: Text models are billed separately for input and output tokens…Network and securityHelp and support Network and security Do I need a proxy to use the API? No. Yomi API offers direct global access from both mainland China and abroad…
Knowledge base
Large language model basicsThis article introduces the fundamentals of large language models and LLM APIs to provide useful background before you integrate them.Model familiesKnowledge base Model families Leading international providers OpenAI (GPT and o series) OpenAI's GPT family established the industry pattern of pre-tr…Technical conceptsKnowledge base Technical concepts Mixture of Experts (MoE) Mixture of Experts (MoE) is a sparsely activated neural-network architecture. It combines s…Advanced guideKnowledge base Advanced guide Processing long text Current mainstream models have substantial context windows. Among models offered by the platform, c…GlossaryKnowledge base Glossary Text and generation Token The smallest unit of text processed by a model. Text is split into tokens, then converted to vectors…