For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DocsAPI ReferenceSDKs
DocsAPI ReferenceSDKs
  • Overview
    • API reference
  • Mesh API
      • GETList Models
      • GETList Free Models
      • GETList Paid Models
LogoLogo
Mesh APIModels

List Models

||View as Markdown|
GET
https://api.meshapi.ai/v1/models
GET
/v1/models
$curl https://api.meshapi.ai/v1/models \
>     -H "Authorization: Bearer <token>" \
>     -H "Content-Type: application/json"
1[
2  {
3    "id": "gpt-4o-mini",
4    "name": "GPT-4o Mini",
5    "context_length": 8192,
6    "is_free": false,
7    "pricing": {
8      "prompt_usd_per_1k": "0.0030",
9      "completion_usd_per_1k": "0.0040",
10      "prompt_usd_per_1m": "3.00",
11      "completion_usd_per_1m": "4.00",
12      "image_usd_per_image": null,
13      "audio_input_usd_per_1m": null,
14      "audio_output_usd_per_1m": null,
15      "cached_audio_input_usd_per_1m": null,
16      "cached_text_input_usd_per_1m": null,
17      "discount_pct": "15",
18      "prompt_usd_per_1k_discounted": "0.00255",
19      "completion_usd_per_1k_discounted": "0.00340",
20      "prompt_usd_per_1m_discounted": "2.55",
21      "completion_usd_per_1m_discounted": "3.40"
22    },
23    "supports_thinking": true,
24    "supports_completions_api": true,
25    "supports_responses_api": true,
26    "model_type": "text",
27    "input_modalities": [
28      "text"
29    ],
30    "output_modalities": [
31      "text"
32    ],
33    "provider": "openai",
34    "description": "A compact version of GPT-4 optimized for cost and speed.",
35    "supports_realtime": false,
36    "is_composite": false,
37    "composite_models": null
38  }
39]
List available models with per-user discounted pricing when applicable. Only models registered in the `models` table with is_enabled=true are returned. Accepts either a dashboard JWT or an API key. Includes pricing per 1 000 tokens and a convenience ``is_free`` flag. If the caller has an active discount, discounted prices are included. Response is cached for 5 minutes; admin writes invalidate the cache immediately.
Was this page helpful?
Previous

Cancel Batch

Next

List Free Models

Built with

List available models with per-user discounted pricing when applicable.

Only models registered in the models table with is_enabled=true are returned. Accepts either a dashboard JWT or an API key. Includes pricing per 1 000 tokens and a convenience is_free flag. If the caller has an active discount, discounted prices are included. Response is cached for 5 minutes; admin writes invalidate the cache immediately.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Query parameters

freeboolean or nullOptional

Filter: true = free models only, false = paid only, omit = all

typeenum or nullOptional

Filter by model_type: text, embedding, image, audio, video

Allowed values:
providerstring or nullOptional

Filter by provider: amazon-bedrock, vertex, openai

Response

Successful Response
idstring
namestring
context_lengthinteger or null
is_freeboolean
pricingobject
supports_thinkingboolean
supports_completions_apiboolean
supports_responses_apiboolean
model_typestring
input_modalitieslist of strings
output_modalitieslist of strings
providerstring or null
descriptionstring or null
supports_realtimebooleanDefaults to false
is_compositebooleanDefaults to false
composite_modelslist of strings or null

Errors

422
Unprocessable Entity Error