Kimi K2 Thinking pricing
Kimi K2 Thinking, Reasoning-tier from Novita AI, costs $0.60 per 1M input tokens and $2.50 per 1M output tokens.
Input$0.60per 1M tokens
Output$2.50per 1M tokens
Context window256Ktokens
TierReasoningNovita AI
Price your own workload against Kimi K2 Thinking in the calculator →
Specs and pricing
| Provider | Novita AI |
| Tier | Reasoning |
| Context window | 256K tokens |
| Max output | — |
| Input price | $0.60 / 1M tokens |
| Output price | $2.50 / 1M tokens |
| Cache read | $0.15 / 1M tokens |
| Modalities | text |
Note. Serverless per-token pricing on Novita's model catalog; dedicated GPU deployments are billed per hour instead.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.60 | $0.63 | $1.23 |
| 10,000,000 in / 2,500,000 out | $6.00 | $6.25 | $12.25 |
| 100,000,000 in / 25,000,000 out | $60.00 | $62.50 | $122.50 |
Cheaper alternatives
Same tier (Reasoning), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Trinity Large (Thinking) | Parasail | $0.22 | $0.85 | 64.7% cheaper blended |
| GPT-5.1-codex-mini | Azure OpenAI Service | $0.25 | $2.00 | 38.8% cheaper blended |
| QwQ 32B | Cloudflare Workers AI | $0.66 | $1.00 | 25.7% cheaper blended |
| DeepSeek-R1-Distill-Llama-70B | SambaNova | $0.70 | $1.40 | 14.3% cheaper blended |