Models

List and retrieve information about available models. Use these endpoints to discover which models are available, their capabilities, context lengths, and pricing.

Endpoints

GET https://api.tensoras.ai/v1/models
GET https://api.tensoras.ai/v1/models/{model_id}

Authentication

Authorization: Bearer tns_your_key_here

List Models

Retrieve a list of all models currently available on the Tensoras platform.

Request

GET /v1/models

No request body is required.

Response Body

{
  "object": "list",
  "data": [
    {
      "id": "llama-3.3-70b",
      "object": "model",
      "created": 1709123456,
      "owned_by": "meta",
      "capabilities": {
        "chat_completion": true,
        "completion": true,
        "function_calling": true,
        "json_mode": true,
        "streaming": true
      },
      "context_length": 131072,
      "pricing": {
        "prompt": 0.0008,
        "completion": 0.0008,
        "unit": "per_1k_tokens"
      }
    },
    {
      "id": "llama-3.1-8b",
      "object": "model",
      "created": 1709123456,
      "owned_by": "meta",
      "capabilities": {
        "chat_completion": true,
        "completion": true,
        "function_calling": true,
        "json_mode": true,
        "streaming": true
      },
      "context_length": 131072,
      "pricing": {
        "prompt": 0.0002,
        "completion": 0.0002,
        "unit": "per_1k_tokens"
      }
    },
    {
      "id": "qwen-3-32b",
      "object": "model",
      "created": 1709123456,
      "owned_by": "alibaba",
      "capabilities": {
        "chat_completion": true,
        "completion": true,
        "function_calling": true,
        "json_mode": true,
        "streaming": true
      },
      "context_length": 32768,
      "pricing": {
        "prompt": 0.0006,
        "completion": 0.0006,
        "unit": "per_1k_tokens"
      }
    }
  ]
}

Field	Type	Description
`object`	string	Always `"list"`.
`data`	array	A list of model objects.
`data[].id`	string	The model identifier used in API requests.
`data[].object`	string	Always `"model"`.
`data[].created`	integer	Unix timestamp of when the model was added.
`data[].owned_by`	string	The organization that created the model.
`data[].capabilities`	object	Describes what the model supports.
`data[].capabilities.chat_completion`	boolean	Whether the model supports chat completions.
`data[].capabilities.completion`	boolean	Whether the model supports legacy completions.
`data[].capabilities.function_calling`	boolean	Whether the model supports function/tool calling.
`data[].capabilities.json_mode`	boolean	Whether the model supports JSON mode output.
`data[].capabilities.streaming`	boolean	Whether the model supports streaming responses.
`data[].context_length`	integer	Maximum context length in tokens.
`data[].pricing`	object	Pricing information.
`data[].pricing.prompt`	number	Cost per unit for prompt tokens.
`data[].pricing.completion`	number	Cost per unit for completion tokens.
`data[].pricing.unit`	string	The pricing unit, e.g. `"per_1k_tokens"`.

Available Models

Model	Provider	Context Length	Description
`llama-3.3-70b`	Meta	131,072	High-performance general-purpose model with excellent reasoning.
`llama-3.1-8b`	Meta	131,072	Fast and cost-effective model for simpler tasks.
`qwen-3-32b`	Alibaba	32,768	Strong multilingual model with broad capabilities.
`mistral-7b-instruct`	Mistral	32,768	Efficient instruction-following model.
`deepseek-r1-distill-70b`	DeepSeek	65,536	Reasoning-focused model with chain-of-thought capabilities.
`codestral-latest`	Mistral	32,768	Specialized model for code generation and understanding.

Get Model

Retrieve details about a specific model.

Request

GET /v1/models/{model_id}

Parameter	Type	Required	Description
`model_id`	string	Yes	The ID of the model to retrieve (path parameter).

Response Body

{
  "id": "llama-3.3-70b",
  "object": "model",
  "created": 1709123456,
  "owned_by": "meta",
  "capabilities": {
    "chat_completion": true,
    "completion": true,
    "function_calling": true,
    "json_mode": true,
    "streaming": true
  },
  "context_length": 131072,
  "pricing": {
    "prompt": 0.0008,
    "completion": 0.0008,
    "unit": "per_1k_tokens"
  }
}

Examples

List All Models

curl

curl https://api.tensoras.ai/v1/models \
  -H "Authorization: Bearer tns_your_key_here"

Python

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.tensoras.ai/v1",
    api_key="tns_your_key_here",
)
 
models = client.models.list()
 
for model in models.data:
    print(f"{model.id} (owned by {model.owned_by})")

Node.js

import OpenAI from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.tensoras.ai/v1",
  apiKey: "tns_your_key_here",
});
 
const models = await client.models.list();
 
for (const model of models.data) {
  console.log(`${model.id} (owned by ${model.owned_by})`);
}

Get Model Details

curl

curl https://api.tensoras.ai/v1/models/llama-3.3-70b \
  -H "Authorization: Bearer tns_your_key_here"

Python

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.tensoras.ai/v1",
    api_key="tns_your_key_here",
)
 
model = client.models.retrieve("llama-3.3-70b")
 
print(f"Model: {model.id}")
print(f"Owner: {model.owned_by}")

Node.js

import OpenAI from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.tensoras.ai/v1",
  apiKey: "tns_your_key_here",
});
 
const model = await client.models.retrieve("llama-3.3-70b");
 
console.log(`Model: ${model.id}`);
console.log(`Owner: ${model.owned_by}`);

Error Handling

{
  "error": {
    "message": "Model 'nonexistent-model' not found",
    "type": "not_found_error",
    "param": "model_id",
    "code": "model_not_found"
  }
}

Rerank Files