Explore models.

KTKotoba Text-to-Speech

Streams Japanese speech over its own WebSocket protocol so playback can begin before the full utterance is generated.

KTKotoba Realtime Speech-to-Text

Live transcription over WebSocket, with partial results as the speaker talks.

KTKotoba Realtime Speech Translation

Streams translated text and 24 kHz speech together over WebSocket, including Japanese–English and Korean–English pairs.

UNPareto Latest

This model always redirects to the latest model in the Pareto family.

UNPareto 26.9

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

HEHeyGen: HeyGen Voice

HeyGen Voice is a text-to-speech model from HeyGen. It comes with 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams...

HEHeyGen: HeyGen Voice Turbo

HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones...

LILiquidAI: LFM2.5-24B-A2B

24B total, 2.45B active parameters; always reasons before answering, with GGUF and MLX releases for local deployment.

Fish Audio: Drama 3

Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as `[nervous,...

Google: Gemini 4 Argon (batch)

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep…

SCScaleDown: Summarize

Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...

SCScaleDown: Extract

Define entity types in plain English; returns matching spans, confidence and character offsets, with built-in scan/PDF OCR.

SCScaleDown: Classify-1

Classify-1 is a structured decision model from ScaleDown, served through OpenRouter's Decisions API. It scores text or a document against caller-defined choice, yes/no, and ordered-scale questions and…

INLing-3.1-flash

Switch reasoning on or off; hybrid linear attention and multi-token prediction support long-context self-hosted inference.

NANace.AI: Drex v2.0

Self-hosted decision scoring via Python or dedicated llama.cpp/Ollama forks; returns option probabilities without prose.

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4

Meta: Muse Wonder

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

Bria Expand (FIBO-Edit-1.5)

Expand to a custom canvas under 25MP while preserving original pixels; new areas generate near 1MP and are then scaled.

Bria Guided Remove Background

Name the objects to keep or remove; returns the original pixels with an alpha channel, without repainting the subject.

Microsoft: Microsoft-Decision-1

Microsoft-Decision-1 is a small model built for fast decision-making. Instead of generating text, it reads the provided content and returns a calibrated probability for each fixed answer option, so the...