Reference
Model Catalog
Hober routes to 200+ models across 15+ providers. The catalog is dynamic — models are added and updated without gateway redeployment.
List All Models
curl https://hober-gateway.fly.dev/v1/models \
-H "Authorization: Bearer hb_live_your_key_here"Providers
| Provider | Format | Free Tier | Notable Models |
|---|---|---|---|
| DeepSeek | OpenAI-compatible | Trial tokens | V3.2, R1, Coder |
| Google Gemini | Adapter | 1K req/day | 2.5 Pro, 2.5 Flash, 3 Flash |
| Groq | OpenAI-compatible | Rate-limited | Llama 4, Qwen3, Kimi K2 |
| Mistral | OpenAI-compatible | Free tier | Nemo, Small, Large |
| Zhipu/GLM | OpenAI-compatible | GLM-4-Flash FREE | GLM-4, GLM-4-Flash |
| Cohere | Adapter | Trial key | Command R, Embed |
| Fireworks AI | OpenAI-compatible | $1 credit | Qwen3, Llama, open-source |
| OpenAI | Native | — | GPT-4o, GPT-4o-mini |
| Anthropic | Adapter | — | Opus 4.6, Sonnet 4.6, Haiku 4.5 |
| Kimi/Moonshot | OpenAI-compatible | — | Kimi K2, K2-mini |
| Qwen/DashScope | OpenAI-compatible | — | Qwen-Max, Qwen-Plus, Qwen-Turbo |
Model Response Format
{
"object": "list",
"data": [
{
"id": "deepseek-chat",
"object": "model",
"provider": "deepseek",
"pricing": {
"input": 0.00028,
"output": 0.00042,
"currency": "USD",
"unit": "token"
},
"context_length": 128000,
"capabilities": {
"streaming": true,
"tool_use": true,
"json_mode": true
}
}
]
}The model list is always up to date. Use GET /v1/models as the source of truth for available models and pricing. Use HAR slug suffixes like :cost or :quality to let Hober pick the best model for your needs.