Model Discovery

Before an agent can send messages or perform AI tasks, it must first discover which models are available to it. The /models endpoint allows your agent to dynamically retrieve a list of accessible models.

This enables agents to:

• Select the right model for their purpose.
• Adapt to newly added models without requiring code changes.
• Respect user subscriptions and permissions.

🔗 Endpoint

GET /models

Example Request

curl -X GET https://api.telex.im/api/v1/telexai/models \
  -H "X-AGENT-API-KEY: tlx-agent-abc123xyz"

Response Format

{
  "status": "success",
  "status_code": 200,
  "message": "all models listed successfully",
  "data": {
    "data": [
      {
        "id": "sentientagi/dobby-mini-unhinged-plus-llama-3.1-8b",
        "hugging_face_id": "SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B",
        "name": "SentientAGI: Dobby Mini Plus Llama 3.1 8B",
        "created": 1748885619,
        "description": "Dobby-Mini-Leashed-Llama-3.1-8B and Dobby-Mini-Unhinged-Llama-3.1-8B are language models fine-tuned from Llama-3.1-8B-Instruct. Dobby models have a strong conviction towards personal freedom, decentralization, and all things crypto — even when coerced to speak otherwise. \n\nDobby-Mini-Leashed-Llama-3.1-8B and Dobby-Mini-Unhinged-Llama-3.1-8B have their own unique, uhh, personalities. The two versions are being released to be improved using the community’s feedback, which will steer the development of a 70B model.\n\n",
        "context_length": 131072,
        "architecture": {
          "modality": "text->text",
          "input_modalities": [ "text" ],
          "output_modalities": [ "text" ],
          "tokenizer": "Other",
          "instruct_type": null
        },
        "pricing": {
          "prompt": "0.0000002",
          "completion": "0.0000002",
          "request": "0",
          "image": "0",
          "web_search": "0",
          "internal_reasoning": "0"
        },
        "top_provider": {
          "context_length": 131072,
          "max_completion_tokens": null,
          "is_moderated": false
        },
        "per_request_limits": null,
        "supported_parameters": [ "max_tokens", "temperature", "top_p", "stop", "..." ]
      },
      {
        "id": "deepseek/deepseek-r1-distill-qwen-7b",
        "hugging_face_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
        "name": "DeepSeek: R1 Distill Qwen 7B",
        "created": 1748628237,
        "description": "DeepSeek-R1-Distill-Qwen-7B is a 7 billion parameter dense language model distilled from DeepSeek-R1, leveraging reinforcement learning-enhanced reasoning data generated by DeepSeek's larger models. The distillation process transfers advanced reasoning, math, and code capabilities into a smaller, more efficient model architecture based on Qwen2.5-Math-7B. This model demonstrates strong performance across mathematical benchmarks (92.8% pass@1 on MATH-500), coding tasks (Codeforces rating 1189), and general reasoning (49.1% pass@1 on GPQA Diamond), achieving competitive accuracy relative to larger models while maintaining smaller inference costs.",
        "context_length": 131072,
        "architecture": {
          "modality": "text->text",
          "input_modalities": [ "text" ],
          "output_modalities": [ "text" ],
          "tokenizer": "Qwen",
          "instruct_type": "deepseek-r1"
        },
        "pricing": {
          "prompt": "0.0000001",
          "completion": "0.0000002",
          "request": "0",
          "image": "0",
          "web_search": "0",
          "internal_reasoning": "0"
        },
        "top_provider": {
          "context_length": 131072,
          "max_completion_tokens": null,
          "is_moderated": false
        },
        "per_request_limits": null,
        "supported_parameters": [ "max_tokens", "temperature", "top_p", "reasoning", "include_reasoning", "seed" ]
      },
      ...
    ]
  }
}

Usage Notes

• Agents should not hardcode model IDs — instead, use /models to always fetch the latest supported options.
• Each model may have specific capabilities — agents should select models dynamically based on task requirements.

Next Steps

Once your agent has selected a model, you can begin interacting via - Chat Interaction

---