Access real-time rankings, scores, pricing, and reviews for 800+ AI models. Build dashboards, integrate widgets, or power your own AI comparison tool.
Make your first API call in under 2 minutes.
Every endpoint, parameter, and response type.
Embed rankings and model cards on your site.
Compare tiers, see rate limits, and pick the right plan.
All API requests go to the following base URL. Every endpoint is prefixed with /v1.
https://api.lmmarketcap.com/v1Pass your API key in the X-API-Key header with every request. You can get a free key from your developer dashboard.
curl https://api.lmmarketcap.com/v1/models \
-H "X-API-Key: YOUR_API_KEY"Every key starts on the Free tier. Upgrade anytime from your developer dashboard -- no code changes needed. The only difference between tiers is the daily request limit.
| Tier | Requests / day | Price | Best for |
|---|---|---|---|
| Free | 100 | $0 | Prototyping, personal projects |
| Dev | 10,000 | $29/mo | Production apps, startups |
| Pro | 100,000 | $199/mo | High-traffic sites, enterprise integrations |
| Enterprise | Custom | Contact us | SLA, dedicated support, custom data feeds |
Every response includes rate limit headers so you always know where you stand. Limits reset daily at midnight UTC.
| Header | Description |
|---|---|
X-RateLimit-Limit | Your plan's daily request cap |
X-RateLimit-Remaining | Requests left in the current window |
X-RateLimit-Reset | UTC epoch seconds when the window resets |
Retry-After | Seconds until you can retry (only on 429 responses) |
When you hit the limit, the API returns 429 Too Many Requests. The best practice is to check X-RateLimit-Remaining and back off before hitting zero. Our SDK handles this automatically with exponential backoff.
Get the top 5 coding models in a single request:
curl "https://api.lmmarketcap.com/v1/rankings/coding?limit=5" \
-H "X-API-Key: YOUR_API_KEY"Errors follow a consistent format. The code field is machine-readable, and message is a human-friendly explanation.
{
"error": {
"code": "not_found",
"message": "No model found with slug 'gpt-5-turbo'. Did you mean 'gpt-4-turbo'?"
}
}| Status | Code | Meaning |
|---|---|---|
400 | bad_request | Invalid parameters. Check the details field. |
401 | unauthorized | Missing or invalid API key. |
403 | forbidden | Your plan does not allow this action. |
404 | not_found | The requested resource does not exist. |
429 | rate_limited | Daily rate limit exceeded. Check Retry-After header. |
List endpoints use cursor-based pagination. Each response includes a pagination object. To get the next page, pass the next_cursor value as the cursor query parameter.
{
"data": [...],
"pagination": {
"next_cursor": "eyJpZCI6MTAxfQ==",
"has_more": true,
"total": 847
}
}When has_more is false, you have reached the last page. The default page size is 20; you can set it to anything between 1 and 100 with the limit parameter.