Fireworks
100.00%Context1M
Max output131.1K
p50 latency372 ms
Throughput161.0 t/s
Input price$4.5
Output price$22.5
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
moonshotai/kimi-k3-fast
Kimi K3 Fast
Fast version of Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.
Input / 1M tokens$4.5
Output / 1M tokens$22.5
Maximum context1M
Inference providers2
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Morph
100.00%Context1M
Max output1M
p50 latency1,880 ms
Throughput16.5 t/s
Input price$6
Output price$22.5
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Fireworks | 1M | 131.1K | 372 ms | 161.0 t/s | 100.000% | $4.5 | $22.5 | |
Morph | 1M | 1M | 1,880 ms | 16.5 t/s | 100.000% | $6 | $22.5 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageFileAdvanced reasoningTool useAutomatic cachingFile inputVisionTools
Reasoning options
LowHighMax
Technical profile
- Model type
- Language model
- Release date
- Jul 27, 2026
- Knowledge cutoff
- —
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Not supported
Model identifier
moonshotai/kimi-k3-fastModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.