Baseten
99.12%Context256K
Max output256K
p50 latency493 ms
Throughput282.0 t/s
Input price$1
Output price$4.05
Zero retentionNo training
thinkingmachines/inkling
Inkling is a multimodal MoE model (975B total, 41B active, 256k context) reasoning over text, image, and audio inputs.
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 | 256K | 256K | 493 ms | 282.0 t/s | 99.115% | $1 | $4.05 | |
Modal | 262.1K | 262.1K | 372 ms | 200.5 t/s | 100.000% | $1.2 | $5 | |
Thinkingmachines | 256K | 256K | 1,816 ms | 141.5 t/s | 100.000% | $1 | $4.05 | |
Togetherai | 256K | 256K | 3,851 ms | 61.0 t/s | 98.694% | $1.2 | $4.05 |
Available modalities and capabilities across inference providers.
thinkingmachines/inklingMore options from the same creator or model category.