Chat Completions (OpenAI-compatible)
OpenAI-compatible chat completions endpoint. Works with the standard OpenAI SDK — just change the base URL and API key.
Supports text, vision (image URLs and base64), and audio input in the standard OpenAI multimodal message format. Supports both streaming (Server-Sent Events) and non-streaming responses.
OpenAI SDK Compatibility
This endpoint is fully compatible with the OpenAI SDK. Just change thebaseURL and apiKey:
Authentication
This endpoint supports two authentication methods:- x-api-key header:
x-api-key: YOUR_API_KEY - Authorization header:
Authorization: Bearer YOUR_API_KEY(OpenAI SDK default)
Supported Models
| Provider | Model ID | Description |
|---|---|---|
gemini-3-flash | Gemini 3 Flash — fast and efficient (default) | |
gemini-3-pro | Gemini 3 Pro — advanced reasoning | |
gemini-3.1-pro | Gemini 3.1 Pro — latest Gemini | |
| Anthropic | claude-opus-4-6 | Claude Opus 4.6 — most capable |
| Anthropic | claude-sonnet-4-6 | Claude Sonnet 4.6 — balanced |
| Anthropic | claude-haiku-4-5 | Claude Haiku 4.5 — fast |
| OpenAI | gpt-5 | GPT-5 — latest flagship |
| OpenAI | gpt-5-mini | GPT-5 Mini — smaller, fast |
| OpenAI | gpt-5.4-instant | GPT-5.4 Instant — fast |
| OpenAI | gpt-5.4-thinking | GPT-5.4 Thinking — reasoning |
| OpenAI | gpt-5.4-pro | GPT-5.4 Pro — most capable |
| DeepSeek | deepseek-v3 | DeepSeek V3 |
| Kimi | kimi-k2.5 | Kimi K2.5 |
| GLM | glm-5 | GLM-5 |
| MiniMax | minimax-m2p5 | MiniMax M2.5 |
| xAI | grok-4 | Grok 4 |
Multimodal Messages
You can send images and audio alongside text using the OpenAI multimodal message format.Vision (Image Input)
Send images as URLs or base64 data URIs:Audio Input
Send audio as base64-encoded data (mp3, wav, webm, mp4):Streaming
Whenstream: true, the response uses Server-Sent Events in OpenAI chunk format:
Authorizations
API key for authentication. Get yours at https://easy-peasy.ai/settings/api
Headers
Your API key. Alternatively, use the Authorization: Bearer header.
Bearer token authentication (alternative to x-api-key). Format: Bearer YOUR_API_KEY
Body
Array of message objects for the conversation
Model to use for the completion. See the models table below for all supported models.
gemini-3-flash, gemini-3-pro, gemini-3.1-pro, claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5, gpt-5, gpt-5-mini, gpt-5.4-instant, gpt-5.4-thinking, gpt-5.4-pro, deepseek-v3, kimi-k2.5, glm-5, minimax-m2p5, grok-4 Enable Server-Sent Events streaming
Sampling temperature (0-2)
Maximum tokens to generate
Nucleus sampling parameter
Stop sequences
