Estimate your workload cost
Enter the number of requests and tokens per request you want to estimate. Adjust the sample values to match your expected usage.
Tokens are pieces of text. Input is the text you send; output is the answer. Context is the amount of text a model can handle in one request.
Sample workloads are illustrative. Cache hits are assumed; cache setup, tools and non-text use may add charges.
Compare a repeatable workload, then test quality, latency and reliability before changing models.
Known token charges only; request, tool and other fees may be unknown. Validate answer quality with your own tasks. A lower price is a candidate to test, not a recommendation to switch.
Compare model prices
439 matching models
Sorted by known token charges
Select up to three models to compare above. Rates are USD per 1M tokens via OpenRouter.
| Compare / Model | Input / 1M | Output / 1M | Cache / 1M | Context | Token estimate |
|---|---|---|---|---|---|
| $0.015 | $0.045 | $0.003 | 262K | $0.900 | |
| $0.029 | $0.030 | Unknown | 131K | $1.17 | |
| $0.040 | $0 | Unknown | 1M | $1.20 | |
| $0.040 | $0 | Unknown | 1M | $1.20 | |
| $0.021 | $0.063 | $0.004 | 262K | $1.26 | |
| $0.025 | $0.092 | $0.022 | 131K | $1.67 | |
| $0.040 | $0.050 | Unknown | 8K | $1.70 | |
| $0.025 | $0.100 | $0.003 | 262K | $1.75 | |
| $0.034 | $0.083 | $0.030 | 1.0M | $1.83 | |
| $0.034 | $0.083 | $0.030 | 1.0M | $1.83 | |
| $0.024 | $0.112 | Unknown | 131K | $1.84 | |
| $0.030 | $0.130 | $0.030 | 131K | $2.20 | |
| $0.030 | $0.130 | $0.006 | 1M | $2.20 | |
| $0.030 | $0.136 | Unknown | 131K | $2.25 | |
| $0.050 | $0.080 | $0.025 | 131K | $2.30 | |
| $0.050 | $0.080 | Unknown | 33K | $2.30 | |
| $0.011 | $0.200 | $0.002 | 1.0M | $2.33 | |
| $0.011 | $0.200 | $0.002 | 1.0M | $2.33 | |
| $0.030 | $0.150 | $0.030 | 128K | $2.40 | |
| $0.035 | $0.140 | Unknown | 128K | $2.45 | |
| $0.050 | $0.100 | Unknown | 131K | $2.50 | |
| $0.037 | $0.150 | Unknown | 128K | $2.63 | |
| $0.045 | $0.135 | $0.009 | 1M | $2.70 | |
| $0.025 | $0.200 | $0.003 | 400K | $2.75 | |
| $0.027 | $0.201 | Unknown | 60K | $2.82 | |
| $0.048 | $0.144 | $0.012 | 1.0M | $2.88 | |
| $0.050 | $0.150 | Unknown | 131K | $3.00 | |
| $0.044 | $0.177 | Unknown | 8K | $3.09 | |
| $0.050 | $0.180 | $0.010 | 1.0M | $3.30 | |
| $0.050 | $0.200 | $0.012 | 1.0M | $3.50 | |
| $0.050 | $0.200 | $0.005 | 524K | $3.50 | |
| $0.070 | $0.140 | Unknown | 16K | $3.50 | |
| $0.080 | $0.110 | Unknown | 8K | $3.50 | |
| $0.060 | $0.180 | $0.012 | 131K | $3.60 | |
| $0.080 | $0.130 | $0.040 | 262K | $3.70 | |
| $0.050 | $0.230 | $0.050 | 128K | $3.80 | |
| $0.100 | $0.100 | $0.010 | 131K | $4.00 | |
| $0.100 | $0.100 | Unknown | 16K | $4.00 | |
| $0.050 | $0.250 | $0.005 | 1M | $4.00 | |
| $0.050 | $0.250 | $0.005 | 1.1M | $4.00 |
The lowest known token estimate in this filtered view is $0.900. This covers the specified text workload and known token prices, not an all-in bill. Missing cache rates, insufficient context or unpriced charges can prevent a comparison. It does not predict retries, task success or your invoice.
Analyze your AI bill
Upload supported CSV or JSON exports to review reported costs and missing data. Files are processed in browser memory.
Paying the provider directly?
Choose a provider and model to estimate the text-token charge for one request using GenAI Prices. These rates are separate from OpenRouter prices above.