Models API

Query the model registry to discover available LLM models and their capabilities

Overview

The Models API provides access to Adaptive’s comprehensive model registry, which contains detailed information about available LLM models including pricing, capabilities, context limits, and provider details.

Use this API to:

• Discover available models across all providers
• Get detailed pricing and capability information
• Filter models by provider
• Retrieve specific model details for integration

Registry Model System

Adaptive maintains a centralized Model Registry that tracks comprehensive information about LLM models from multiple providers (OpenAI, Anthropic, Google, DeepSeek, Groq, and more).

What is a Registry Model?

A Registry Model is a comprehensive data structure containing:

• Identity: Provider, model name, OpenRouter ID
• Pricing: Input/output token costs, per-request costs
• Capabilities: Context length, supported parameters, tool calling support
• Architecture: Modality, tokenizer, instruction format
• Provider Info: Top provider configuration, available endpoints
• Metadata: Display name, description, timestamps

How the Registry Works

1. Centralized Data Source: The registry service maintains up-to-date model information
2. Automatic Lookups: When you specify a provider or model, Adaptive queries the registry
3. Auto-Fill: Known models automatically get pricing and capability data filled in

Endpoints

List All Models

provider · string

Optional provider filter (e.g., “openai”, “anthropic”, “google”)

Advanced Filtering

The Models API supports comprehensive filtering with repeatable query parameters:

author · string[]

Filter by model author (repeatable). Example: ?author=openai&author=anthropic

model_name · string[]

Filter by model name (repeatable). Example: ?model_name=gpt-4&model_name=claude-3

input_modality · string[]

Filter by input modality (repeatable). Example: ?input_modality=text&input_modality=image

output_modality · string[]

Filter by output modality (repeatable). Example: ?output_modality=text

min_context_length · integer

Filter by minimum context length. Example: ?min_context_length=128000

max_prompt_cost · string

Filter by maximum prompt cost. Example: ?max_prompt_cost=0.00001

supported_param · string[]

Filter by required parameters (repeatable). Example: ?supported_param=tools&supported_param=vision

status · integer

Filter by endpoint status (0=active). Example: ?status=0

quantization · string[]

Filter by model quantization (repeatable). Example: ?quantization=fp16

Advanced Filter Examples

# Find vision-capable OpenAI models with large context
curl "https://api.llmadaptive.uk/v1/models?author=openai&supported_param=vision&min_context_length=100000" \
  -H "Authorization: Bearer apk_123456"

# Find cost-effective models with multimodal input
curl "https://api.llmadaptive.uk/v1/models?input_modality=text&input_modality=image&max_prompt_cost=0.00001" \
  -H "Authorization: Bearer apk_123456"

# Find active models from multiple providers with tool support
curl "https://api.llmadaptive.uk/v1/models?provider=openai&provider=anthropic&supported_param=tools&status=0" \
  -H "Authorization: Bearer apk_123456"

Query Parameter Syntax: For multiple values, repeat the parameter name:

• ✅ Correct: ?author=openai&author=anthropic
• ❌ Incorrect: ?author=openai,anthropic (comma-separated not supported)

List All Models

curl https://api.llmadaptive.uk/v1/models \
  -H "Authorization: Bearer apk_123456"

200 Success

[
  {
    "id": 123,
    "author": "openai",
    "model_name": "gpt-5-mini",
    "display_name": "GPT-5 Mini",
    "description": "Affordable and intelligent small model for fast, lightweight tasks",
    "context_length": 128000,
    "pricing": {
      "prompt_cost": "0.00015",
      "completion_cost": "0.0006",
      "request_cost": "0",
      "image_cost": "0",
      "web_search_cost": "0",
      "internal_reasoning_cost": "0"
    },
    "architecture": {
      "modality": "text",
      "tokenizer": "cl100k_base",
      "instruct_type": "chat",
      "modalities": [
        {
          "modality_type": "input",
          "modality_value": "text"
        },
        {
          "modality_type": "output",
          "modality_value": "text"
        }
      ]
    },
    "top_provider": {
      "context_length": 128000,
      "max_completion_tokens": 16384,
      "is_moderated": "true"
    },
    "supported_parameters": [
      {
        "parameter_name": "temperature"
      },
      {
        "parameter_name": "top_p"
      },
      {
        "parameter_name": "max_tokens"
      },
      {
        "parameter_name": "tools"
      }
    ],
    "default_parameters": {
      "parameters": {
        "temperature": 1.0,
        "top_p": 1.0,
        "max_tokens": 4096
      }
    },
    "providers": [
      {
        "name": "openai",
        "endpoint_model_name": "gpt-5-mini",
        "context_length": 128000,
        "provider_name": "OpenAI",
        "tag": "openai",
        "quantization": "",
        "max_completion_tokens": 16384,
        "max_prompt_tokens": 128000,
        "status": 0,
        "uptime_last_30m": "99.9%",
        "supports_implicit_caching": "true",
        "is_zdr": "false",
        "pricing": {
          "prompt_cost": "0.00015",
          "completion_cost": "0.0006",
          "request_cost": "0",
          "image_cost": "0.2890",
          "input_cache_read_cost": "0",
          "input_cache_write_cost": "0"
        }
      }
    ]
  }
]

Get Model by Name

id · string · required

Model identifier (e.g., “gpt-5-mini”, “claude-sonnet-4-5”)

cURL

curl https://api.llmadaptive.uk/v1/models/gpt-5-mini \
  -H "Authorization: Bearer apk_123456"

200 Success

{
  "id": 123,
  "author": "openai",
  "model_name": "gpt-5-mini",
  "display_name": "GPT-5 Mini",
  "description": "Affordable and intelligent small model for fast, lightweight tasks",
  "context_length": 128000,
  "pricing": {
    "prompt_cost": "0.00015",
    "completion_cost": "0.0006",
    "request_cost": "0",
    "image_cost": "0",
    "web_search_cost": "0",
    "internal_reasoning_cost": "0"
  },
  "architecture": {
    "modality": "text",
    "tokenizer": "cl100k_base",
    "instruct_type": "chat",
    "modalities": [
      {
        "modality_type": "input",
        "modality_value": "text"
      },
      {
        "modality_type": "output",
        "modality_value": "text"
      }
    ]
  },
  "top_provider": {
    "context_length": 128000,
    "max_completion_tokens": 16384,
    "is_moderated": "true"
  },
  "supported_parameters": [
    {
      "parameter_name": "temperature"
    },
    {
      "parameter_name": "top_p"
    },
    {
      "parameter_name": "max_tokens"
    },
    {
      "parameter_name": "tools"
    }
  ],
  "default_parameters": {
    "parameters": {
      "temperature": 1.0,
      "top_p": 1.0,
      "max_tokens": 4096
    }
  },
  "providers": [
    {
      "name": "openai",
      "endpoint_model_name": "gpt-5-mini",
      "context_length": 128000,
      "provider_name": "OpenAI",
      "tag": "openai",
      "quantization": "",
      "max_completion_tokens": 16384,
      "max_prompt_tokens": 128000,
      "status": 0,
      "uptime_last_30m": "99.9%",
      "supports_implicit_caching": "true",
      "is_zdr": "false",
      "pricing": {
        "prompt_cost": "0.00015",
        "completion_cost": "0.0006",
        "request_cost": "0",
        "image_cost": "0.2890",
        "input_cache_read_cost": "0",
        "input_cache_write_cost": "0"
      }
    }
  ]
}

Response Schema

RegistryModel Object

Field	Type	Description
id	integer	Database ID (internal use)
author	string	Model author/organization (e.g., “openai”, “anthropic”)
model_name	string	Model identifier for API calls
display_name	string	Human-readable model name
description	string	Model description and use cases
context_length	integer	Maximum context window size in tokens
pricing	object	Pricing information (see below)
architecture	object	Model architecture details (see below)
top_provider	object	Top provider configuration (see below)
supported_parameters	array	Supported API parameters (see below)
default_parameters	object	Default parameter values (see below)
providers	array	Available provider endpoints (see below)

Pricing Object

Field	Type	Description
prompt_cost	string	Cost per input token (USD, string format)
completion_cost	string	Cost per output token (USD, string format)
request_cost	string	Cost per request (optional)
image_cost	string	Cost per image (optional)
web_search_cost	string	Cost for web search (optional)
internal_reasoning_cost	string	Cost for internal reasoning tokens (optional)

Note: Pricing is in string format to preserve precision. Multiply by 1M for cost per million tokens.

Architecture Object

Field	Type	Description
modality	string	Primary modality (e.g., “text”, “multimodal”)
tokenizer	string	Tokenizer used (e.g., “cl100k_base”, “o200k_base”)
instruct_type	string	Instruction format (e.g., “chat”, null)
modalities	array	Supported input/output modalities (see below)

ArchitectureModality Object

Field	Type	Description
modality_type	string	”input” or “output”
modality_value	string	Modality value (e.g., “text”, “image”)

TopProvider Object

Field	Type	Description
context_length	integer	Provider’s context limit
max_completion_tokens	integer	Maximum output tokens
is_moderated	string	Whether content is moderated (“true” or “false”)

ModelSupportedParameter Object

Field	Type	Description
parameter_name	string	Name of supported parameter (e.g., “temperature”, “tools”)

ModelDefaultParameters Object

Field	Type	Description
parameters	object	Default parameter values (see DefaultParametersValues below)

DefaultParametersValues Object

Contains strongly typed default parameter values including sampling, penalty, token, and control parameters.

ModelProvider Object

Field	Type	Description
name	string	Provider name
endpoint_model_name	string	Model name at the endpoint
context_length	integer	Context length for this provider
provider_name	string	Human-readable provider name
tag	string	Provider tag/slug
quantization	string	Model quantization (optional)
max_completion_tokens	integer	Max completion tokens
max_prompt_tokens	integer	Max prompt tokens
status	integer	Status code (0 = active)
uptime_last_30m	string	Uptime percentage last 30 minutes
supports_implicit_caching	string	Implicit caching support (“true” or “false”)
is_zdr	string	Zero-downtime routing support (“true” or “false”)
pricing	object	Provider-specific pricing (see ProviderPricing below)

ProviderPricing Object

Field	Type	Description
prompt_cost	string	Cost per input token
completion_cost	string	Cost per output token
request_cost	string	Cost per request
image_cost	string	Cost per image
image_output_cost	string	Cost per image output
audio_cost	string	Cost per audio
input_audio_cache_cost	string	Cost for cached input audio
input_cache_read_cost	string	Cost to read from input cache
input_cache_write_cost	string	Cost to write to input cache
discount	string	Discount applied

Integration with Other APIs

Use with Chat Completions

Combine with the Chat Completions API for intelligent routing:

import requests

# 1. Query registry for available models
models_response = requests.get(
    "https://api.llmadaptive.uk/v1/models?provider=openai&provider=anthropic",
    headers={"Authorization": f"Bearer {api_key}"}
)
available_models = models_response.json()

# 2. Use models in chat completion with intelligent routing
chat_response = requests.post(
    "https://api.llmadaptive.uk/v1/chat/completions",
    headers={"Authorization": f"Bearer {api_key}"},
    json={
        "model": "adaptive/auto",  # Empty for intelligent routing
        "messages": [{"role": "user", "content": "Hello"}],
        "model_router": {
            "models": [
                f"{m['provider']}:{m['model_name']}"
                for m in available_models[:3]  # Use top 3 models
            ]
        }
    }
)

Use with Select Model API

Combine with the Select Model API for explicit selection:

import requests

# 1. Get models from registry with filtering
models_response = requests.get(
    "https://api.llmadaptive.uk/v1/models?supported_param=tools&min_context_length=100000",
    headers={"Authorization": f"Bearer {api_key}"}
)
models = models_response.json()

# 2. Use select-model to choose best model for prompt
selection_response = requests.post(
    "https://api.llmadaptive.uk/v1/select-model",
    headers={"Authorization": f"Bearer {api_key}"},
    json={
        "prompt": "Write a Python function to process CSV files",
        "models": [
            f"{m['provider']}/{m['model_name']}"
            for m in models
            if "tools" in m.get("supported_parameters", [])
        ]
    }
)