Reference

Model Catalog

Hober routes across 17 providers. The catalog updates dynamically, adding and refreshing models without a gateway redeploy.

List All Models

curl https://api.hober.dev/v1/models \
  -H "Authorization: Bearer hb_live_your_key_here"

Providers

ProviderFormatFree via HoberNotable Models
DeepSeekOpenAI-compatibleNoneV3.2, R1, Coder
Google GeminiAdapterNone2.5 Pro, 2.5 Flash, 3 Flash
GroqOpenAI-compatibleNoneLlama 4, Qwen3, Kimi K2
MistralOpenAI-compatibleNoneNemo, Small, Large
Zhipu/GLMOpenAI-compatibleglm-4.5-flash (40 req/day)GLM-4, GLM-4.5-Flash
CohereAdapterNoneCommand R, Embed
Fireworks AIOpenAI-compatibleNoneQwen3, Llama, open-source
OpenAINativeNoneGPT-4o, GPT-4o-mini
AnthropicAdapterNoneOpus 4.6, Sonnet 4.6, Haiku 4.5
Kimi/MoonshotOpenAI-compatibleNoneKimi K2, K2-mini
Qwen/DashScopeOpenAI-compatibleNoneQwen-Max, Qwen-Plus, Qwen-Turbo

Model Response Format

{
  "object": "list",
  "data": [
    {
      "id": "deepseek/v3.2",
      "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.