Kimi K2.5 pricing across providers
Across tracked provider offerings, input runs $0.356–$0.600 per million tokens and output $1.98–$3.32 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Novita at $0.121 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 6 of 7 offerings publish a cache-read rate; 5 of 7 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Kimi K2.5
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 K2.5
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) |
|---|---|---|---|---|---|---|
| Novita promo | unknown | $0.570 | $2.85 | $0.095 | $0.121 | 100.00% |
| SiliconFlow | int4 | $0.500 | $2.50 | $0.150 | $0.170 | 100.00% |
| Atlascloud | int4 | $0.490 | $2.50 | $0.200 | $0.219 | 100.00% |
| Venice promo | unknown | $0.532 | $3.32 | $0.209 | $0.233 | 100.00% |
| Ember | — | $0.356 | $1.98 | $0.225 | $0.237 | — |
| Avian | — | $0.450 | $2.20 | $0.225 | $0.240 | — |
| Amazon | unknown | $0.600 | $3.00 | — | $0.612 | 100.00% |
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.