LLM Model & Pricing Scraper | $3/1K
Pricing
$3.00 / 1,000 results
LLM Model & Pricing Scraper | $3/1K
Track 400+ AI models with current prices per million tokens, context lengths, tool support and modalities. Plus a price comparison across every provider hosting the same model — the same model can cost 10x more elsewhere. No API key.
LLM Model & Pricing Scraper
Track 400+ AI models with current prices, context lengths and capabilities — and compare what the same model costs across every provider hosting it.
No API key. No account. Data straight from OpenRouter's public catalogue.
Why this exists
Model prices change weekly, new models appear almost daily, and the same model can cost ten times more at one provider than another. Nobody publishes that comparison in a form you can put in a spreadsheet.
The price comparison mode returns one row per provider per model, with the price, the latency and the quantisation level — so you can see not just who is cheapest, but what you give up for it.
What you can extract
| Mode | What you get |
|---|---|
| Model catalogue with prices | Every model with input and output price per million tokens, context length, modalities, tool support, reasoning, knowledge cutoff |
| Price comparison across providers | One row per provider hosting a model: price, context limit, quantisation, latency and uptime |
| Provider directory | All 100+ providers with headquarters and datacentre locations |
Quick start
- Pick Model catalogue with prices.
- Optionally filter by lab, price, context length or tool support.
- Click Start, download as CSV or Excel.
Example inputs
The full catalogue, cheapest first
Models you can build agents on, with big context
Everything from one lab
Find the cheapest provider for a model
Free models only
Output fields
Models
| Field | Description |
|---|---|
name, modelId, author | What it is and who built it |
pricePromptPerMillion | Dollars per million input tokens |
priceCompletionPerMillion | Dollars per million output tokens |
priceCacheReadPerMillion, priceCacheWritePerMillion | Caching rates — decides whether caching pays off |
contextLength, maxCompletionTokens | How much fits in, how much comes out |
inputModalities, outputModalities | text, image, file, audio |
supportsTools | Whether you can build agents on it |
supportsReasoning, reasoningMandatory | Explicit reasoning support |
supportsStructuredOutput | Whether it can be forced into a JSON schema |
supportedParameters | Every API parameter the model accepts |
knowledgeCutoff | How current the training data is |
huggingFaceId | Where the open weights live, if published |
isModerated, isFree, createdAt, expirationDate | Status fields |
Price comparison
| Field | Description |
|---|---|
modelName, provider | Which model at which provider |
pricePromptPerMillion, priceCompletionPerMillion | What that provider charges |
quantization | How much the model was compressed — the hidden quality trade-off |
contextLength, maxPromptTokens, maxCompletionTokens | Limits at this provider |
latencyLast30m, uptimeLast30m | Recent performance |
Limits
- Prices are snapshots. They change often; schedule a run to build a history.
- Free models rarely have third-party providers, so the comparison mode returns little for them.
- The comparison mode makes one request per model, so filtering first keeps runs fast.
- Latency and uptime are OpenRouter's measurements, not independent tests.
FAQ
Do I need an API key? No. The catalogue endpoints are public.
Why do prices differ between providers for the same model? Different hardware, different quantisation, different margins. That is exactly what the comparison mode makes visible.
What is quantisation and why should I care? It is how much the model was compressed to run cheaper. Lower precision costs less and can answer slightly worse — the column lets you weigh that.
Can I track price changes over time? Yes — schedule the run and each dataset becomes a snapshot.
What formats can I export? CSV, Excel, JSON, XML, or straight from the Apify API.
Source
Data comes from OpenRouter's public model catalogue, which aggregates offerings from over 100 inference providers.
