API Reference
Free REST API for LLM pricing data — no authentication required
Base URL
Endpoints
Rate Limits
To keep the API available for everyone, the following limits apply per IP address:
| Window | Limit |
|---|---|
| Per second | 5 requests |
| Per minute | 60 requests |
| Per hour | 1,000 requests |
Exceeding these limits returns 429 Too Many Requests with a Retry-After header.
If you need higher limits, reach out to us.
List all models with current pricing. Optionally filter by provider name.
| Parameter | Type | Description |
|---|---|---|
| provider optional | string | Filter by provider name (e.g. Anthropic, OpenAI) |
Get current pricing for a single model by its ID.
| Parameter | Type | Description |
|---|---|---|
| model_id | string | Model ID in provider::model format (e.g. anthropic::claude-sonnet-4-20250514) |
Get the price change history for a model. Returns all historical pricing configurations ordered newest first.
| Parameter | Type | Description |
|---|---|---|
| model_id | string | Model ID in provider::model format |
Estimate costs for a given token count. Returns results sorted by total cost (cheapest first). If no output tokens are provided, defaults to half the input count.
| Parameter | Type | Description |
|---|---|---|
| input_tokens optional | integer | Number of input tokens (default: 0) |
| output_tokens optional | integer | Number of output tokens (default: half of input_tokens) |
| text optional | string | Estimate input tokens from text length (~4 chars/token) |
| models optional | string | Comma-separated model IDs to estimate (default: all models) |
Compare current pricing for selected models side by side.
| Parameter | Type | Description |
|---|---|---|
| models | string | Comma-separated model IDs to compare (required) |