Daily-updated pricing across all major LLM providers. Source: github.com/llerandi/llm-price-tracker
| Provider ↕ | Model ↕ | Input $/1M ↕ | Output $/1M ↕ | Context ↕ | Tier ↕ | Capabilities | Est. Cost ↕ | Badge |
|---|
Batch requests are processed asynchronously (within 24 hours) at reduced rates. Cache read prices apply to tokens served from the prompt cache.
| Provider | Model | Batch Input $/1M | Batch Output $/1M | Cache Read $/1M | Cache Write $/1M |
|---|
Track how input and output prices have changed over time. Select a model to plot its history.
Prices in USD per 1M tokens. Updated daily by GitHub Actions.
Aggregate pricing and capabilities per provider across all tracked models.
| Provider | Models | Cheapest model | Input range $/1M | Output range $/1M | Max context | Capabilities |
|---|
Embedding models generate vector representations of text. Priced on input tokens only - no output tokens.
| Provider | Model | Input $/1M | Context | Notes |
|---|
Recent price changes and model additions detected by the daily update workflow.
Select two models to see a side-by-side breakdown of pricing and capabilities.