Search the full model catalog.

fable-5

claude

Claude Fable 5 is a frontier text model with vision and PDF support. It handles 1M-token context for deep reasoning, coding, and document analysis.

opus-5

claude

Claude Opus 5 is a premium text model with vision for agentic coding and document work. Upload images or PDFs and get long, detailed answers.

sonnet-5

claude

Claude Sonnet 5 is an agent-ready text model for coding, reasoning, and long-context work. It can read images and PDFs and returns text answers.

gpt-realtime-whisper

OpenAI’s GPT Realtime Whisper turns live audio into streaming transcript updates. Adjust delay levels to trade latency for higher transcription accuracy.

gpt-realtime-translate

Stream live speech and get translated speech plus live captions with low delay. Made by OpenAI for calls, meetings, broadcasts, and video chat translation.

Speech to Speech

gpt-realtime-2.1-mini

Build low-latency voice agents with OpenAI’s GPT‑Realtime 2.1 Mini. It takes live audio or text and replies with spoken audio plus a transcript. ([developers.openai.com](https://developers.openai.com/api/docs/models/gpt-realtime-2.1-mini))

Speech to Speech

gpt-realtime-2.1

OpenAI's GPT Realtime 2.1 runs speech-to-speech conversations with configurable reasoning and tool calls. It’s built for voice agents that handle noise and interruptions.

Speech to Speech

gpt-live-transcribe

Low-latency speech-to-text for live streams, calls, and meetings. Add context, expected terms, and language hints to improve accuracy.

gemini-3.7-flash

google

Google’s Gemini 3.7 Flash is a multimodal model built for coding and agent workflows. It takes text plus images, audio, or video and returns text.

Partner LLMgoogle

Chatconversational text-generation-inference

Qwen3.8-27B

Qwen

Qwen3.8-27B is a 27B-parameter chat model from Qwen with optional thinking traces and 262k native context for long-form coding, analysis, and agent workflows.

Chatconversational text-generation-inference

Qwen3.8-27B-Uncensored

Qwen

Chat model based on Qwen 3.8 27B with refusal behavior reduced through direction removal. Its 262k context fits long documents, code, and chats.

seed-v2.1-turbo

ByteDance

Seed v2.1 Turbo by ByteDance is a 256K-context reasoning model for coding and agent workflows. It can use images for understanding and returns text or JSON.

seed-v2-pro

ByteDance

Seed V2 Pro is ByteDance’s Seed2.0 Pro-class model for long-horizon reasoning, agent-style task planning, and image-grounded Q&A in chat workflows. ([seed.bytedance.com](https://seed.bytedance.com/en/seed2?utm_source=openai))

seed-v2-pro-uncensored

ByteDance

ByteDance Seed V2 Pro Uncensored is a long-context multimodal chat model for complex reasoning and image Q&A. It generates detailed text answers from prompts and images.