Kimi K3 pricing
Kimi K3, Flagship-tier from inference.net, costs $3.00 per 1M input tokens and $15.00 per 1M output tokens.
Input$3.00per 1M tokens
Output$15.00per 1M tokens
Context window1.05Mtokens
TierFlagshipinference.net
Specs and pricing
| Provider | inference.net |
| Tier | Flagship |
| Context window | 1.05M tokens |
| Max output | 1.05M tokens |
| Input price | $3.00 / 1M tokens |
| Output price | $15.00 / 1M tokens |
| Cache read | $0.30 / 1M tokens |
| Modalities | text |
Note. Inference.net gateway price for Kimi K3 (Moonshot AI), converted from the site's published per-token rate (costInputPerToken=0.000003, costOutputPerToken=0.000015 USD/token) to USD per 1M tokens: $3.0/1M input, $15.0/1M output, $0.3/1M cache read.
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 | $3.00 | $3.75 | $6.75 |
| 10,000,000 in / 2,500,000 out | $30.00 | $37.50 | $67.50 |
| 100,000,000 in / 25,000,000 out | $300.00 | $375.00 | $675.00 |
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 |
|---|---|---|---|---|
| Qwen3 235B A22B Instruct 2507 | Novita AI | $0.09 | $0.58 | 96.5% cheaper blended |
| GPT-OSS 120B | Groq | $0.15 | $0.60 | 95.6% cheaper blended |
| Qwen3 235B-A22B (2507) | Parasail | $0.14 | $0.80 | 95% cheaper blended |
| Llama 4 Maverick | Together AI | $0.27 | $0.85 | 92.9% cheaper blended |
| Llama 4 Maverick Instruct | Novita AI | $0.27 | $0.85 | 92.9% cheaper blended |