AI APIs for Developers – Explore AI Models, LLMs, Pipelines & Functions

5.2

GLM 5.2 is a text-only MoE model with a usable 1M-token context for long-horizon coding and agent workflows. It supports thinking effort and tool calling.

Partner LLM

Run

v4-flash

deepseek

DeepSeek V4 Flash is a fast MoE text model with a 1M-token context window and optional thinking mode. It’s built for chat, coding, and agent workflows.

Partner LLM

Run

v4-pro

deepseek

DeepSeek V4 Pro (v4-pro) is a long-context text model with optional thinking mode for agentic coding, math reasoning, and large-document Q&A up to 1M tokens.

Partner LLM

Run

gemini-3.8-flash

google

Google’s Gemini 3.8 Flash reasons over text, images, audio, video, and PDFs, then returns strong text answers for long-horizon agents and coding.

Partner LLM

Run

grok-imagine-image-v2

xai

Create new images or edit a source photo with xAI’s Grok Imagine Image V2. Choose 1K or 2K output, quality level, and aspect ratio.

Text to Image

Run

p-video-edit

pruna

Pruna P Video Edit edits a short MP4 clip from one text instruction, with 1-4 reference images to guide identity or style and keep audio.

Video to Video

Run

speech-to-speech-v2

elevenlabs

Re-voice an existing recording with a chosen ElevenLabs voice while keeping the original words, timing, and delivery. Export MP3 in common 22.05 kHz and 44.1 kHz presets.

Speech to Speechelevenlabs

Run

text-to-music-v2

elevenlabs

Create original music from a plain-English brief with ElevenLabs Music v2. Choose track length, MP3 quality, and optional instrumental-only output.

Text to Musicelevenlabstext-to-music

Run

Fast-H3

FastVideo

FastH3 is a four-forward distilled MiniMax H3 model that generates synchronized video and stereo audio from a text prompt. This H200-backed Preview v1 checkpoint supports native 5.167–14.375 second T2AV clips at 24 FPS; FL2VA and Ref2VA were not distilled.

Text to Videotext-to-videoaudio-video

Run

Qwen3.8-Flash-Next-GGUF

unsloth

Run Unsloth’s GGUF quantizations of Qwen 3.8 Flash Next for long-context chat and reasoning. Includes optional thinking mode plus sampling and stop controls.

Chatconversational text-generation-inference

Run

Qwen3.8-27B-Obliterated

Qwen

Refusal-reduced variant of Qwen 3.8 27B for long-context chat and coding. It can emit or hide thinking traces and supports tight decoding controls.

Chatconversational text-generation-inference

Run

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.

Partner LLM

Run

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.

Partner LLM

Run

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.

Partner LLM

Run

gpt-realtime-whisper

openai

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

Run

gpt-realtime-translate

openai

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

Run

gpt-realtime-2.1-mini

openai

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

Run

gpt-realtime-2.1

openai

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

Run