Kimi K3 pricing across providers
Across tracked provider offerings, input runs $0.172–$3.45 per million tokens and output $8.25–$17.25 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Sail Research at $0.172 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 36 of 36 offerings publish a cache-read rate; 14 of 36 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Kimi K3
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for Kimi K3
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Sail Research | fp4 | $0.230 | $11.00 | $0.115 | $0.172 | — |
| Relace | fp4 | $0.172 | $9.34 | $0.170 | $0.216 | 100.00% |
| Decart promo | mxfp4 | $1.65 | $8.25 | $0.165 | $0.243 | 100.00% |
| Inferencenet | fp4 | $0.239 | $10.80 | $0.210 | $0.264 | 100.00% |
| Makora | fp4 | $0.500 | $13.00 | $0.200 | $0.271 | 100.00% |
| Chutes | mxfp4 | $1.85 | $9.50 | $0.185 | $0.273 | — |
| Engy | — | $1.95 | $9.75 | $0.195 | $0.287 | — |
| Fireworks | unknown | $2.10 | $10.50 | $0.210 | $0.309 | 100.00% |
| Wafer | — | $2.00 | $15.00 | $0.250 | $0.367 | — |
| Aster Labs | — | $2.50 | $12.50 | $0.250 | $0.367 | — |
| Avian | — | $2.55 | $12.75 | $0.255 | $0.375 | — |
| Phala promo | unknown | $2.55 | $12.75 | $0.255 | $0.375 | 100.00% |
| Digitalocean | unknown | $2.55 | $12.95 | $0.255 | $0.376 | 100.00% |
| Ember | — | $2.70 | $13.50 | $0.270 | $0.397 | — |
| Singularity | — | $2.50 | $14.00 | $0.300 | $0.423 | — |
| DeepInfra | — | $2.85 | $14.25 | $0.285 | $0.437 | — |
| Neuralwatt | — | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Runpod | — | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Canopywave | — | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Runware | — | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Runanywhere | mxfp4 | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Paretoalpha | unknown | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Parasail | fp4 | $3.00 | $15.00 | $0.300 | $0.441 | 100.00% |
| Modal | mxfp4 | $3.00 | $15.00 | $0.300 | $0.441 | 100.00% |
| Together | unknown | $3.00 | $15.00 | $0.300 | $0.441 | 100.00% |
| Baseten | fp8 | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Moonshot | unknown | $3.00 | $15.00 | $0.300 | $0.441 | 100.00% |
| OpenCode | — | $3.00 | $15.00 | $0.300 | $0.441 | — |
| Morph | fp8 | $1.28 | $14.63 | $0.360 | $0.454 | 100.00% |
| Amazon | unknown | $3.00 | $15.00 | $0.300 | $0.460 | 100.00% |
| Scx Ai Gp | — | $3.14 | $15.68 | $0.319 | $0.466 | — |
| Hyper | — | $3.27 | $16.33 | $0.327 | $0.480 | — |
| Alibaba | unknown | $3.45 | $17.25 | $0.345 | $0.507 | 100.00% |
| Sference | — | $3.00 | $15.00 | $0.450 | $0.587 | — |
| Synthetic | — | $3.00 | $15.00 | $0.600 | $0.732 | — |
| Akashml | fp4 | $1.20 | $14.00 | $1.20 | $1.26 | — |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.