Kimi K2 Thinking pricing across providers
Across tracked provider offerings, input runs $0.600–$0.600 per million tokens and output $2.50–$2.50 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 $0.173 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 2 of 2 offerings publish a cache-read rate; 1 of 2 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Kimi K2 Thinking
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 Thinking
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 | bf16 | $0.600 | $2.50 | $0.150 | $0.173 | 100.00% |
| Hyper | — | $0.600 | $2.50 | $0.300 | $0.319 | — |
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.