TokenHub Now Supports 400+ AI Models — Llama 4, Mistral, Gemma & More

#ai #api #deepseek #opensource

TokenHub just got a lot bigger.

What's New

We've integrated a massive model catalog. You can now choose from 400+ AI models across 30+ providers, all through the same OpenAI-compatible API endpoint.

New International Models

Model	Provider	Best For
Llama 4 Maverick	Meta	General chat, coding
Mistral Large	Mistral AI	Multilingual, reasoning
Gemma 4 31B	Google	Lightweight, free
Nemotron 550B	NVIDIA	Massive-scale tasks
Kimi K2.6	MoonShot	Long context (1M+)

Still Have All The Originals

DeepSeek V3, V4 Pro, V4 Flash. Qwen 3.7 Max. GLM-4 Flash. MiniMax. 50+ Chinese models. All still available.

Pricing Has Not Changed

Starter $0.69 / Basic $7 / Pro $26 / Max $79. Same plans. More models. Better value.

Three Lines Of Code


python
from openai import OpenAI
client = OpenAI(base_url="https://t-hub.cc/v1", api_key="your-token")
response = client.chat.completions.create(model="meta-llama/llama-4-maverick", messages=[{"role":"user","content":"Hello"}])
One API key. 400+ models. No Chinese phone. Credit card accepted.

Try it: https://t-hub.cc