LMSpeed Docs

LMSpeed Models API: list and search public models

List published canonical models or search by model name, slug, or description. Use this endpoint for catalog pages, model pickers, search results, and comparison tables. The default response is compact and includes identity, localized description, aggregate speed stats, and performance summary. Use `include` to expand richer model sections only when you need them. `include=benchmarks` adds public benchmark rows, display-ready `benchmark_groups`, and `category_performance`; `include=pricing` adds public benchmark pricing metrics; `include=capabilities` adds parsed capability metadata. Public displays using this endpoint must include a visible backlink to https://lmspeed.net. Backlink example: Source: LMSpeed.net (https://lmspeed.net). Cache responses on your side and avoid sending high-volume repeated requests.

GET
/api/v1/models

List published canonical models or search by model name, slug, or description.

Use this endpoint for catalog pages, model pickers, search results, and comparison tables. The default response is compact and includes identity, localized description, aggregate speed stats, and performance summary.

Use include to expand richer model sections only when you need them. include=benchmarks adds public benchmark rows, display-ready benchmark_groups, and category_performance; include=pricing adds public benchmark pricing metrics; include=capabilities adds parsed capability metadata.

Public displays using this endpoint must include a visible backlink to https://lmspeed.net.

Backlink example: Source: LMSpeed.net (https://lmspeed.net).

Cache responses on your side and avoid sending high-volume repeated requests.

Authorization

publicApiKey
x-api-key<token>

Free public key for LMSpeed model data. Public keys never expire and are limited to 1000 requests/day.

In: header

Query Parameters

q?string

Search term matched against model names, slugs, and descriptions.

page?integer

One-based page number.

Range1 <= value
Default1
page_size?integer

Number of models per page. Values above 100 are rejected.

Range1 <= value <= 100
Default50
sort?string

Sort order for the model list. popular is the default catalog order.

Default"popular"

Value in

  • "popular"
  • "recent"
  • "newest"
  • "alphabetical"
locale?string

Language used for localized model descriptions. Numeric metrics and prices are locale-independent.

Default"en"

Value in

  • "en"
  • "zh"
  • "ru"
include?string

Comma-separated expansions. Supported for list responses: benchmarks, pricing, capabilities.

Header Parameters

x-api-key*string

Free public API key created from LMSpeed settings. Send it exactly as the x-api-key header.

Response Body

application/json

application/json

application/json

application/json

curl -X GET "https://example.com/api/v1/models?q=deepseek+v4+pro&include=" \  -H "x-api-key: string"
{  "tier": "free",  "locale": "en",  "attribution": {    "required": true,    "name": "LMSpeed",    "url": "https://lmspeed.net"  },  "data": {    "models": [      {        "id": 33442,        "slug": "deepseek-v4-pro",        "name": "DeepSeek V4 Pro",        "lmspeed_url": "https://lmspeed.net/model/deepseek-v4-pro",        "description": "DeepSeek V4 Pro is a large language model in the DeepSeek series, offering advanced reasoning, code generation, and multimodal capabilities.",        "developer": "DeepSeek",        "release_date": "2026-04-24T03:17:59.000Z",        "context_window_tokens": 1048576,        "max_output_tokens": 384000,        "documentation_url": null,        "huggingface_url": null,        "stats": {          "total_tests": 160,          "average_tokens_per_second": 49.85478210449219,          "average_first_token_latency": 7150.391125488281,          "last_test_at": "2026-05-18T13:13:55.186Z"        },        "performance_summary": {          "average_tokens_per_second": 49.85478210449219,          "average_first_token_latency": 7150.391125488281        }      }    ],    "pagination": {      "page": 1,      "page_size": 3,      "total": 1,      "total_pages": 1    }  }}
{  "error": {    "code": "string",    "message": "string",    "details": null  }}
{  "error": {    "code": "string",    "message": "string",    "details": null  }}
{  "error": {    "code": "string",    "message": "string",    "details": null  }}