Kimi K2 Instruct pricing
Kimi K2 Instruct, Flagship-tier from Novita AI, costs $0.57 per 1M input tokens and $2.30 per 1M output tokens.
Input$0.57per 1M tokens
Output$2.30per 1M tokens
Context window128Ktokens
TierFlagshipNovita AI
Price your own workload against Kimi K2 Instruct in the calculator →
Specs and pricing
| Provider | Novita AI |
| Tier | Flagship |
| Context window | 128K tokens |
| Max output | — |
| Input price | $0.57 / 1M tokens |
| Output price | $2.30 / 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 | $0.57 | $0.57 | $1.15 |
| 10,000,000 in / 2,500,000 out | $5.70 | $5.75 | $11.45 |
| 100,000,000 in / 25,000,000 out | $57.00 | $57.50 | $114.50 |
Cheaper alternatives
Same tier (Flagship), 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 |
|---|---|---|---|---|
| GPT-OSS 120B | Groq | $0.15 | $0.60 | 73.8% cheaper blended |
| Qwen3 235B-A22B (2507) | Parasail | $0.14 | $0.80 | 70.3% cheaper blended |
| Llama 4 Maverick | Together AI | $0.27 | $0.85 | 57.9% cheaper blended |
| GPT-OSS 120B | Cloudflare Workers AI | $0.35 | $0.75 | 53.1% cheaper blended |
| MiniMax M3 | OpenRouter | $0.30 | $1.20 | 47.6% cheaper blended |