Models
106 models, one API key. Compare them by what they do and what they cost.
| Compare | Model | Precision | Capabilities | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 500K | $2.16 | $6.48 | $0.54 | 100% | ||||||
| 32K | $0.0567 | $0.00 | — | 100% | ||||||
| 1M | $0.1048 | $0.3141 | — | fp4 | 36tok/s | 1.19s | 100% | |||
| — | $0.019 / image | 10s/img | 10.10s | |||||||
| — | $0.108 / song | |||||||||
| 1M | $13.50 | $67.50 | $1.35 | 4.3% | ||||||
| 1M | $1.013 $2.026 | $5.063 $10.126 | — | 57tok/sfrom traffic, 7d | 17.29sfrom traffic, 7d | 99.4% | ||||
| 1M | $1.688 | $5.738 | — | |||||||
| 1M | $13.50 | $67.50 | — | |||||||
| — | $0.006075 / min | 0.61sfrom traffic, 7d | 100% | |||||||
| — | $0.00675 / min | 85.7% | ||||||||
| 1M | $0.2045 | $0.641 | — | 56tok/sfrom traffic, 7d | 14.60sfrom traffic, 7d | 85.3% | ||||
| 1M | $0.1791 | $0.5972 | — | 77tok/sfrom traffic, 7d | 5.36sfrom traffic, 7d | 99.8% | ||||
| 1M | $0.2514 | $0.7542 | — | 76tok/sfrom traffic, 7d | 7.14sfrom traffic, 7d | 99.1% | ||||
| 1M | $1.178 | $3.702 | — | 100% | ||||||
| 1M | $0.3576 | $2.554 | — | 98.1% | ||||||
| 1M | $1.013 $2.026 | $5.063 $10.126 | $0.050625 | 96tok/sfrom traffic, 7d | 5.92sfrom traffic, 7d | 98.4% | ||||
| 500K | $2.758 | $8.274 | — | |||||||
| 131K | $0.405 | $1.62 | — | 100% | ||||||
| 1M | $1.773 | $6.025 | — | |||||||
| 1M | $2.228 | $6.684 | $0.2781 | |||||||
| 1M | $0.1859 | $0.3718 | — | 100% | ||||||
| 1M | $0.0504 | $0.2187 | $0.0081 | 73tok/sfrom traffic, 7d | 48.02sfrom traffic, 7d | 98.5% | ||||
| 1M | $6.75 | $33.75 | $0.675 | |||||||
| 1M | $1.013 | $5.063 | $0.10125 | 87.0% | ||||||
| 1M | $0.405 | $3.375 | $0.0405 | 48tok/s | 1.29s | 99.3% | ||||
| 1M | $1.542 | $5.243 | — | |||||||
| 1M | $3.768 | $18.837 | $0.405 | 52tok/sfrom traffic, 7d | 2.98sfrom traffic, 7d | 100% | ||||
| 1M | $2.70 $5.40 | $13.50 $27.00 | $0.3375 | |||||||
| 1M | $3.151 $5.40 | $15.753 $27.00 | $0.393875 | 58tok/sfrom traffic, 7d | 14.68sfrom traffic, 7d | 99.2% | ||||
| 1M | $2.70 | $16.20 | $0.27 | |||||||
| 1M | $2.70 | $16.20 | $0.27 | |||||||
| 1M | $0.3127 | $1.877 | $0.027 | 81tok/sfrom traffic, 7d | 6.03sfrom traffic, 7d | 98.9% | ||||
| 1M | $0.1548 | $0.9288 | $0.027 | 97.4% | ||||||
| 500K | $2.73 | $8.189 | — | 100% | ||||||
| 262K | $0.108 | $0.4455 | — | 100% | ||||||
| 1M | $2.70 | $13.50 | $0.27 | 73tok/sfrom traffic, 7d | 10.36sfrom traffic, 7d | 100% | ||||
| 1M | $1.101 | $3.76 | $0.29835 | fp4 · fp8 | 67tok/s | 3.60s | 100% | |||
| 262K | $1.009 | $4.774 | — | |||||||
| 1M | $13.50 | $67.50 | — | |||||||
| 1M | $0.675 | $3.375 | $0.135 | fp4 · fp8 | ||||||
| 1M | $0.4431 | $1.773 | $0.0864 | 44tok/sfrom traffic, 7d | 12.94sfrom traffic, 7d | 100% | ||||
| 1M | $0.405 | $1.62 | $0.0756 | fp4 · fp8 | 100% | |||||
| 256K | $0.27 | $1.552 | $0.054 | fp8 | 100% | |||||
| 1M | $1.863 | $5.586 | $0.16875 | |||||||
| 256K | $1.389 | $2.777 | $0.27 | |||||||
| 1M | $1.928 | $11.563 | $0.2025 | 96.2% | ||||||
| 1M | $1.92 | $3.838 | $0.27 | |||||||
| 1M | $0.1264 | $0.2526 | $0.0243 | 22tok/s | 1.85s | 100% | ||||
| — | $0.072 / image | 37s/img | 36.85s | 97.0% | ||||||
| 262K | $0.7856 | $3.667 | — | 29tok/s | 1.51s | 100% | ||||
| 1M | $6.75 | $33.75 | $0.675 | |||||||
| 203K | $1.89 | $5.94 | $0.27675 | fp4 · fp8 | ||||||
| 1M | $0.454 | $2.724 | — | 52tok/s | 10.30s | 99.9% | ||||
| 128K | $0.0763 | $0.218 | $0.135 | fp4 · fp8 | 8tok/s | 6.72s | 99.6% | |||
| 2M | $1.767 | $3.534 | — | |||||||
| 2M | $1.763 | $3.528 | — | |||||||
| 205K | $0.405 | $1.62 | — | 100% | ||||||
| — | $0.061 / image | 11s/img | 10.88s | |||||||
| 1M | $2.70 | $16.20 | $0.27 | |||||||
| — | $0.108 / image | |||||||||
| 1M | $4.05 | $20.25 | $0.405 | 100% | ||||||
| — | $0.054 / image | 13s/img | 13.11s | |||||||
| — | $0.3375 / image | |||||||||
| 197K | $0.405 | $1.62 | — | 22tok/sfrom traffic, 7d | 9.39sfrom traffic, 7d | 97.3% | ||||
| — | $0.1512 / sec | |||||||||
| 203K | $0.081 | $0.54 | $0.0135 | fp8 | 100% | |||||
| 1M | $0.675 | $4.05 | $0.0675 | 39tok/s | 1.44s | 97.7% | ||||
| 160K | $0.518 | $0.7571 | — | fp4 | 96.2% | |||||
| — | $0.15525 / sec | |||||||||
| — | $0.0405 / image | 12s/img | 12.24s | |||||||
| — | $0.135 / sec | |||||||||
| 200K | $1.35 | $6.75 | $0.135 | 33tok/sfrom traffic, 7d | 2.45sfrom traffic, 7d | 100% | ||||
| 2K | $0.0027 | $0.00 | — | |||||||
| 128K | $0.0494 | $0.2406 | — | 100% | ||||||
| 131K | $0.1945 | $1.272 | $0.03375 | fp8 | 100% | |||||
| 131K | $0.3586 | $1.629 | $0.135 | fp4 · fp8 | 46tok/s | 1.11s | 99.0% | |||
| 33K | $0.0135 | $0.00 | — | 100% | ||||||
| 33K | $0.0135 | $0.00 | — | |||||||
| 33K | $0.027 | $0.00 | — | |||||||
| 41K | $0.135 | $0.00 | — | |||||||
| — | $0.054 / image | |||||||||
| 33K | $0.108 | $0.378 | — | 96.9% | ||||||
| 1M | $0.27 | $1.08 | — | fp8 | 100% | |||||
| — | $0.07 / 1K char | |||||||||
| — | $0.04 / 1K char | |||||||||
| — | $0.081 / image | |||||||||
| 200K | $4.05 | $20.25 | — | |||||||
| 127K | $1.35 | $1.35 | — | 131tok/sfrom traffic, 7d | 4.04sfrom traffic, 7d | 100% | ||||
| — | $0.005 / image | 19s/img | 19.46s | |||||||
| 64K | $0.7425 | $2.957 | — | 56tok/s | 1.55s | 100% | ||||
| 128K | $0.135 | $0.432 | — | 14tok/s | 1.15s | 85.0% | ||||
| — | $0.2025 / 1K char | |||||||||
| — | $0.0009 / min | 0.23sfrom traffic, 7d | 99.2% | |||||||
| 131K | $1.35 | $1.35 | — | fp8 | ||||||
| 131K | $0.945 | $0.945 | — | fp8 | ||||||
| — | $0.2025 / 1K char | |||||||||
| — | $0.00405 / min | 0.16sfrom traffic, 7d | 99.8% | |||||||
| 1K | $0.0135 | $0.00 | — | |||||||
| 8K | $0.0135 | $0.00 | — | |||||||
| 1K | $0.0135 | $0.00 | — | |||||||
| 1K | $0.00675 | $0.00 | — | |||||||
| — | $0.405 / 1K char | |||||||||
| 1K | $0.00675 | $0.00 | — | |||||||
| 1K | $0.00675 | $0.00 | — | |||||||
| 1K | $0.00675 | $0.00 | — | |||||||
Token models priced per 1M tokens. The cached column is what a repeated prompt prefix costs on that model — a rate of its own, read from the same source as the input rate beside it, not a fixed fraction of it. It runs from a tenth of the input rate to the full input rate depending on the model, and a dash means nobody publishes one, which is a different statement from “free”. Image, video, and audio models priced per unit (image, second, video, minute, song, call, or 1K characters). Throughput and latency are a probe with an identical input when Kyma has that sample. If a row is labeled “from traffic, 7d”, that number is production traffic instead — real prompts, not comparable across models. Image throughput is seconds per succeeded job (30-day median). Video, music and realtime stay empty until a job exists. An empty throughput, latency or uptime cell means Kyma does not yet have a number for that cell. Uptime is a percentage only after 20 observations, over 30 days, probes and real requests together, including Kyma's own accounts. Rankings demand is the same total. Precision names the numeric formats a model may be served at that are BELOW the one its creator released it in, and it is filled on the 14 models where that is true. A low format is not a downgrade when it is how the model shipped, so this is a comparison against the creator’s own model card rather than a list of small numbers. An empty precision cell means there is nothing to flag: either no route reports going under the release, or nobody could source what the release was. Those two are different answers and the model’s own page prints which one it is.
Start building with Kyma API
$0.50 signup credit for eligible free-tier models after email verification.
Create account