Skip to main content
Pass any model ID below as the model field of the OpenAI-compatible endpoint that matches its modality: The list below is a snapshot — the live source of truth is GET /v1/models.

​
Chat / LLM

GPT Models

OpenAI · GPT-5 (5.2 / 5.4), GPT-4 (4o / 4.1) and the o-series

Claude Models

Anthropic · Opus, Sonnet, Haiku and Fable

Gemini Models

Google · Gemini 2.5 and 3.x

GLM Models

Z.ai · GLM-4.5 / 4.6 / 4.7 and GLM-5

Kimi Models

Moonshot · Kimi K2, K2.5 and K2.6

DeepSeek Models

DeepSeek · V4, V3.x and R1

MiniMax Models

MiniMax · M2 series and M1-80k

​
Video Generation

Seedance

ByteDance Doubao-Seedance 2.0 · text/image-to-video with a Fast tier

Kling

Kuaishou Kling 3.0 · 4K text/image-to-video and motion control

Wan

Alibaba Wan 2.7 · text, image, reference and video edit

Veo

Google Veo 3.1 · high-quality text and image-to-video

Sora

OpenAI Sora 2 and Sora 2 Pro · synchronized audio

Vidu

Vidu Q1 / Q2 / Q3 · text, image, reference with native audio

​
Image Generation

Nano Banana Pro

Google Gemini 3 Pro Image · flagship text-to-image and editing up to 4K

Gemini 3.1 Flash Image

Google · fast text-to-image and natural-language editing

Nano Banana

Google Gemini 2.5 Flash Image · fast, cost-efficient generation and editing

GPT Image 2

OpenAI · text-to-image and image editing with quality tiers

​
Audio / Music

ElevenLabs Models

Audio isolation, sound effects, speech-to-text, dialogue, multilingual TTS, turbo TTS

Suno Models

Music generation, extension, covers, lyrics, WAV conversion, stem separation, MIDI, music video

​
Quick Reference