Skip to main content
GET
https://api.assisters.dev
/
v1
/
models
List Models
curl --request GET \
  --url https://api.assisters.dev/v1/models
{
  "object": "<string>",
  "data": [
    {
      "id": "<string>",
      "object": "<string>",
      "created": 123,
      "owned_by": "<string>",
      "category": "<string>",
      "capabilities": {},
      "pricing": {},
      "specifications": {},
      "status": "<string>"
    }
  ]
}

​
List Models

Retrieve information about all available models, including their capabilities, pricing, and specifications.

​
Endpoint

GET https://api.assisters.dev/v1/models

​
Request

No request body required. Authentication is optional for this endpoint. 
from openai import OpenAI

client = OpenAI(
    api_key="ask_your_api_key",
    base_url="https://api.assisters.dev/v1"
)

models = client.models.list()

for model in models.data:
    print(f"{model.id}: {model.owned_by}")

​
Response

{
  "object": "list",
  "data": [
    {
      "id": "llama-3.1-8b",
      "object": "model",
      "created": 1704067200,
      "owned_by": "meta",
      "category": "chat",
      "version": "3.1",
      "capabilities": {
        "chat_completion": true,
        "streaming": true,
        "function_calling": false
      },
      "pricing": {
        "input_price_per_million": 0.10,
        "output_price_per_million": 0.10,
        "currency": "usd"
      },
      "specifications": {
        "context_window": 128000,
        "max_output_tokens": 8192,
        "training_cutoff": "2024-03"
      },
      "status": "active"
    },
    {
      "id": "e5-large-v2",
      "object": "model",
      "created": 1704067200,
      "owned_by": "microsoft",
      "category": "embedding",
      "version": "2.0",
      "capabilities": {
        "embeddings": true
      },
      "pricing": {
        "price_per_million_tokens": 0.01,
        "currency": "usd"
      },
      "specifications": {
        "max_tokens": 512,
        "output_dimensions": 1024
      },
      "status": "active"
    }
  ]
}

​
Response Fields

​
object
string
Always list
​
data
array
Array of model objects with the following fields:

​
Get Single Model

Retrieve information about a specific model: 
GET https://api.assisters.dev/v1/models/{model_id}

model = client.models.retrieve("llama-3.1-8b")
print(f"Context window: {model.specifications.context_window}")

​
Available Models by Category

​
Chat Models

ModelProviderContextPrice (per M tokens)
llama-3.1-8bMeta128K$0.10
llama-3.1-70bMeta128K$0.90
mistral-7bMistral AI32K$0.10
qwen2-7bAlibaba32K$0.10
gemma-2-9bGoogle8K$0.15
phi-3-miniMicrosoft4K$0.08

​
Embedding Models

ModelProviderDimensionsPrice (per M tokens)
e5-large-v2Microsoft1024$0.01
bge-base-enBAAI768$0.01
jina-embeddings-v2Jina AI768$0.02
nomic-embed-textNomic AI768$0.01
gte-largeAlibaba1024$0.01

​
Moderation Models

ModelProviderPrice (per M tokens)
llama-guard-3Meta$0.20
shieldgemmaGoogle$0.15

​
Reranking Models

ModelProviderPrice (per M tokens)
bge-reranker-v2BAAI$0.05
jina-rerankerJina AI$0.08

Detailed Model Comparison

See full specifications and benchmarks for all models

​
Filtering Models

Filter models by category in your code: 
models = client.models.list()

# Get only chat models
chat_models = [m for m in models.data if m.category == "chat"]

# Get only embedding models
embedding_models = [m for m in models.data if m.category == "embedding"]

# Get active models only
active_models = [m for m in models.data if m.status == "active"]

​
Model Status

StatusDescription
activeFully available and recommended for use
betaAvailable but may change without notice
deprecatedStill available but will be removed; migrate to alternatives
We announce deprecations at least 3 months in advance. Check the changelog for updates.

​
Caching

The models endpoint has a 5-minute cache. For real-time availability, check the status page. 
Cache-Control: public, max-age=300