Kimi K2.6 API Pricing
Kimi K2.6 costs $0.95 per 1M input tokens and $4.00 per 1M output tokens on Kimi's API. Cached input is billed at $0.16 per 1M tokens. Prices are provider list prices in USD, refreshed as sources update; see the Kimi K2.6 model profile for capability scores.
Price List
| Rate | Price (USD) | Notes |
|---|---|---|
| Input | $0.95 | per 1M tokens |
| Output | $4.00 | per 1M tokens |
| Cached input (read) | $0.16 | per 1M tokens |
| Blended input + output | $4.95 | 1M in + 1M out at list price |
| Context window | 256K tokens |
What a Workload Costs
Computed straight from the list prices above — token counts are illustrative workload sizes, not measurements of Kimi K2.6.
| Workload | Cost | Tokens |
|---|---|---|
| Short chat turn | $0.00295 | 1K in / 500 out |
| Summarize a long document | $0.103 | 100K in / 2K out |
| Agentic coding session | $0.875 | 500K in / 100K out |
| 1M input + 1M output tokens | $4.95 | 1M in / 1M out |
Effective Cost
In AI IQ's scoring, Kimi K2.6's list price is adjusted by a token-usage multiplier of 0.91 (measured from real benchmark runs), giving an effective cost of $4.50 per 1M input + output tokens. That places it #62 of 117 models on the effective-cost ranking (lower is cheaper). Some models spend far more tokens than others on the same task, so effective cost compares what a unit of work really costs. Method details are on the methodology page; see all models on the cost charts and the falling cost of intelligence over time.
Cheaper Alternatives at Similar Capability
Models with a lower effective cost that score within a few IQ points of Kimi K2.6 (IQ 119), or better.
| Model | Provider | IQ | Effective Cost / 1M |
|---|---|---|---|
| Muse Spark 1.2 | Meta | 122 | $4.19 |
| muse-spark-1.1 | Meta | 119 | $4.19 |
| kimi-k2.7-code | Kimi | 118 | $3.73 |
| mimo-v2.5-pro | Xiaomi | 116 | $1.80 |
| gemini-3-flash | 116 | $2.74 |