Baseten
99.95%Context1M
Max output1M
p50 latency206 ms
Throughput370.0 t/s
Input price$0.5
Output price$1.2
Zero retentionNo trainingCaching
thinkingmachines/inkling-small
Inkling-Small is a lighter-weight model with 12B active parameters, trained with a similar recipe, to Inkling that achieves strong performance with even lower cost and latency.
USD per one million tokens, using current provider data.
Last-hour p50 in milliseconds; lower is better.
Reported availability over the last 24 hours; not a contractual SLA.
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Baseten | 1M | 1M | 206 ms | 370.0 t/s | 99.951% | $0.5 | $1.2 | |
Deepinfra | 1M | 1M | 278 ms | 230.0 t/s | 100.000% | $0.58 | $1.44 | |
Thinkingmachines | 64K | 64K | 1,642 ms | 309.5 t/s | 100.000% | $0.3 | $1.2 | |
Togetherai | 1M | 1M | 270 ms | 309.0 t/s | 100.000% | $0.5 | $1.2 |
Available modalities and capabilities across inference providers.
thinkingmachines/inkling-smallMore options from the same creator or model category.