Get Models V2

GET

platform

models

Get models v2

curl --request GET \
  --url https://platform.ai.gloo.com/platform/v2/models

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://platform.ai.gloo.com/platform/v2/models",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.ai.gloo.com/platform/v2/models"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://platform.ai.gloo.com/platform/v2/models")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body

{
  "object": "list",
  "data": [
    {
      "id": "gloo-openai-gpt-5-mini",
      "provider_id": "openai/gpt-5-mini",
      "name": "GPT-5 Mini",
      "family": "OpenAI",
      "description": "Balanced small model providing strong reasoning at minimal compute.",
      "context_window": 400000,
      "max_input_tokens": 400000,
      "max_output_tokens": 128000,
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "speed": 4,
      "supports_tools": true,
      "supports_streaming": true,
      "supports_reasoning": true,
      "supports_vision": true,
      "knowledge_cutoff": "May 2024",
      "reasoning_level": 3,
      "reasoning": {
        "effort_levels": [
          "minimal",
          "low",
          "medium",
          "high"
        ],
        "returns_summary": true,
        "thinks_by_default": true,
        "can_disable": false
      },
      "is_deprecated": false,
      "pricing": {
        "input": {
          "rate_per_1k_tokens": "0.000250",
          "rate_per_1m_tokens": "0.250000"
        },
        "output": {
          "rate_per_1k_tokens": "0.002000",
          "rate_per_1m_tokens": "2.000000"
        }
      }
    },
    {
      "id": "gloo-anthropic-claude-sonnet-5.5",
      "provider_id": "anthropic/claude-sonnet-5.5",
      "name": "Claude Sonnet 5.5",
      "family": "Anthropic",
      "description": "The best combination of speed and intelligence for well-scoped everyday work, succeeding Claude Sonnet 5.",
      "context_window": 1000000,
      "max_input_tokens": 1000000,
      "max_output_tokens": 128000,
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "speed": 3,
      "supports_tools": true,
      "supports_streaming": true,
      "supports_reasoning": true,
      "supports_vision": true,
      "knowledge_cutoff": "Jun 2026",
      "reasoning_level": 4,
      "reasoning": {
        "effort_levels": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "returns_summary": true,
        "thinks_by_default": true,
        "can_disable": false
      },
      "is_deprecated": false,
      "pricing": {
        "input": {
          "rate_per_1k_tokens": "0.002000",
          "rate_per_1m_tokens": "2.000000"
        },
        "output": {
          "rate_per_1k_tokens": "0.010000",
          "rate_per_1m_tokens": "10.000000"
        }
      }
    }
  ]
}

{
  "detail": "Something went wrong while fetching models."
}

Returns all available Gloo AI models with metadata and pricing. No authentication required. Each model includes:

Identification — Gloo model ID (for API requests), provider ID, name, and family
Capabilities — Context window, max input/output tokens, input and output modalities, generation capabilities, and (for embedding models) native vector dimensions
Reasoning — supports_reasoning is true for every model that reasons, and a reasoning object (null when the model doesn’t reason) lists the efforts Gloo forwards to the model (effort_levels), whether a request with an effort gets reasoning text back (returns_summary), whether the model reasons with no effort sent (thinks_by_default), and whether "none" turns reasoning off (can_disable). Where returns_summary is true, every chat and Responses endpoint returns the text on streamed and non-streamed requests. On Responses endpoints, also set reasoning.summary. reasoning_level is an overall quality rating, not a reasoning measure. See Reasoning for how to pick an effort from it.
Pricing — Per-1K and per-1M token list rates for input and output (and cache segments where applicable)

The rates returned here are list prices. Guarded generation endpoints are priced at these rates plus 6.5%, the guarded platform price. Direct endpoints, including Embeddings, bill at the published rate.

Use output_modalities to identify the model type. Use generation model IDs with Direct Responses, Direct Completions, Guarded Responses, or Completions V2, and embedding model IDs with Direct Embeddings. Embedding entries include their native vector width in dimensions.

Response

Successful response

object

string

Object type, always "list".

data

ModelV2Response · object[]

Show child attributes

⌘I

Get models v2

curl --request GET \
  --url https://platform.ai.gloo.com/platform/v2/models

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://platform.ai.gloo.com/platform/v2/models",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.ai.gloo.com/platform/v2/models"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://platform.ai.gloo.com/platform/v2/models")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body

{
  "object": "list",
  "data": [
    {
      "id": "gloo-openai-gpt-5-mini",
      "provider_id": "openai/gpt-5-mini",
      "name": "GPT-5 Mini",
      "family": "OpenAI",
      "description": "Balanced small model providing strong reasoning at minimal compute.",
      "context_window": 400000,
      "max_input_tokens": 400000,
      "max_output_tokens": 128000,
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "speed": 4,
      "supports_tools": true,
      "supports_streaming": true,
      "supports_reasoning": true,
      "supports_vision": true,
      "knowledge_cutoff": "May 2024",
      "reasoning_level": 3,
      "reasoning": {
        "effort_levels": [
          "minimal",
          "low",
          "medium",
          "high"
        ],
        "returns_summary": true,
        "thinks_by_default": true,
        "can_disable": false
      },
      "is_deprecated": false,
      "pricing": {
        "input": {
          "rate_per_1k_tokens": "0.000250",
          "rate_per_1m_tokens": "0.250000"
        },
        "output": {
          "rate_per_1k_tokens": "0.002000",
          "rate_per_1m_tokens": "2.000000"
        }
      }
    },
    {
      "id": "gloo-anthropic-claude-sonnet-5.5",
      "provider_id": "anthropic/claude-sonnet-5.5",
      "name": "Claude Sonnet 5.5",
      "family": "Anthropic",
      "description": "The best combination of speed and intelligence for well-scoped everyday work, succeeding Claude Sonnet 5.",
      "context_window": 1000000,
      "max_input_tokens": 1000000,
      "max_output_tokens": 128000,
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "speed": 3,
      "supports_tools": true,
      "supports_streaming": true,
      "supports_reasoning": true,
      "supports_vision": true,
      "knowledge_cutoff": "Jun 2026",
      "reasoning_level": 4,
      "reasoning": {
        "effort_levels": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "returns_summary": true,
        "thinks_by_default": true,
        "can_disable": false
      },
      "is_deprecated": false,
      "pricing": {
        "input": {
          "rate_per_1k_tokens": "0.002000",
          "rate_per_1m_tokens": "2.000000"
        },
        "output": {
          "rate_per_1k_tokens": "0.010000",
          "rate_per_1m_tokens": "10.000000"
        }
      }
    }
  ]
}

{
  "detail": "Something went wrong while fetching models."
}

General

Models

Responses & Completions

Embeddings

Content

Data Engine Content Controls

Legacy / Deprecated APIs

Get Models V2

Response