API catalogue

Build with language and speech.

Choose a capability, check its limits and start with a working request. One tokenflow key connects your application.

Language & chat

LLM

gemma4-12b

Smaller and faster. Good for short chat, extraction and image questions.

Text & images · 16 inline images maximum

Contact us for pricing

View API →

LLM

gemma4-12b-direct

Gemma 4 12B with an adapter that declines fewer requests.

Text & images · 16 inline images maximum

Contact us for pricing

View API →

LLM

qwen3.8-27b

General chat, coding agents and tool use. Our default model.

Text & images · 16 inline images maximum

Contact us for pricing

View API →

LLM

qwen3.8-27b-cute

The direct model with a casual, short, emoji-friendly chat persona.

Text & images · 16 inline images maximum

Contact us for pricing

For conversation, not strict JSON or classification.

View API →

LLM

qwen3.8-27b-direct

Qwen3.8 27B with an adapter that declines fewer requests.

Text & images · 16 inline images maximum

Contact us for pricing

View API →

Speech to text

Text to speech

TTS

tokenflow-tts-1

Generate speech from text using preset or described voices.

Up to 4,000 characters / request

$1.00 / audio hour

View API →

These are published products, not a live capacity or personal-quota display. See language model performance →

For developers and agents

Choose your way in

Human guides and machine-readable contracts describe the same APIs.

Need runtime observations? Use the public discovery API. Tenant access and quotas require your API key.