Kimi K3 is Moonshot (Kimi)'s most capable model, priced at $3.00/MTok input and $15.00/MTok output with a 1M context window. Prices from platform.kimi.ai (read 2026-10-11). Cache hit: $0.30/MTok input. Kimi K3 is a 2.8T-parameter open-weight MoE model. No batch discount published yet. Not yet benchmarked, so never recommended.
Input $/MTok
$3.00
Output $/MTok
$15.00
Context window
1M
Cache read discount
90% off
| Rate | Input $/MTok | Output $/MTok |
|---|---|---|
| Standard | $3.00 | $15.00 |
| Cached read (90% off input) | $0.30 | - |
| Cached write (no surcharge) | $3.00 | - |
| Batch (0% off) | $3.00 | $15.00 |
All rates in USD per million tokens. Prices verified against provider documentation.
Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 88 models.
Not benchmarked. The third-party benchmark source used for confidence scores does not cover Moonshot (Kimi) models yet. Scores will appear here once independent benchmarks are published.
Estimated cost per API call using default token counts for each workload.
| Use case | Input tokens | Output tokens | Cost / call |
|---|---|---|---|
| Code Generation | 2,000 | 4,000 | $0.0660 |
| Unit Test Generation | 3,000 | 5,000 | $0.0840 |
| SQL Generation | 1,500 | 1,000 | $0.0195 |
| API Generation | 3,000 | 6,000 | $0.0990 |
| Code Refactoring | 4,000 | 4,000 | $0.0720 |
| Code Review | 5,000 | 2,000 | $0.0450 |
| PR Review | 8,000 | 3,000 | $0.0690 |
| Security Review | 6,000 | 2,500 | $0.0555 |
| Bug Detection | 5,000 | 2,000 | $0.0450 |
| Document Summarization | 10,000 | 1,000 | $0.0450 |
| PDF Summarization | 15,000 | 1,500 | $0.0675 |
| Meeting Notes | 8,000 | 2,000 | $0.0540 |
Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).
| Calls / month | Without caching | With caching (90% read discount) |
|---|---|---|
| 1K | $66 | $62.22 |
| 10K | $660 | $622.2 |
| 100K | $6,600 | $6,222 |
| 500K | $33,000 | $31,110 |
| 1M | $66,000 | $62,220 |
Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.
Same-tier models from other providers, sorted by input price.
| Model | Provider | Input $/MTok | Output $/MTok | Input savings |
|---|---|---|---|---|
| MiniMax M3 | MiniMax | $0.30 | $1.20 | 90% cheaper |
| DeepSeek V4 Pro | DeepSeek | $0.66 | $1.98 | 78% cheaper |
| GPT 6 Sol | GPT | $2.00 | $10.00 | 33% cheaper |
| GPT 6.1 Sol | GPT | $2.00 | $10.00 | 33% cheaper |
| Grok 4.6 | Grok | $2.00 | $6.00 | 33% cheaper |
| Grok 4.5 | Grok | $2.00 | $6.00 | 33% cheaper |
| Grok 4.7 | Grok | $2.00 | $6.00 | 33% cheaper |
| Qwen 3.8 Max | Alibaba (Qwen) | $2.00 | $6.00 | 33% cheaper |
| Claude Opus 5.5 | Claude | $4.00 | $20.00 | 33% more |
| GPT 5.6 Sol | GPT | $4.00 | $20.00 | 33% more |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 67% more |
| Claude Opus 5 | Claude | $5.00 | $25.00 | 67% more |
| Claude Opus 4.7 | Claude | $5.00 | $25.00 | 67% more |
| Claude Opus 4.6 | Claude | $5.00 | $25.00 | 67% more |
| Claude Opus 4.5 | Claude | $5.00 | $25.00 | 67% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 67% more |
| GPT 4o (2024-05-13) | GPT | $5.00 | $15.00 | 67% more |
| Claude Fable 5.1 | Claude | $10.00 | $50.00 | 233% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 233% more |
| Claude Mythos 5.1 | Claude | $10.00 | $50.00 | 233% more |
| Claude Mythos 5 | Claude | $10.00 | $50.00 | 233% more |
| GPT 4 Turbo (2024-04-09) | GPT | $10.00 | $30.00 | 233% more |
| GPT 4 Turbo | GPT | $10.00 | $30.00 | 233% more |
| GPT 6 Astra | GPT | $10.00 | $50.00 | 233% more |
| GPT 5 Pro | GPT | $15.00 | $120.00 | 400% more |
| o1 | GPT | $15.00 | $60.00 | 400% more |
| o3 Pro | GPT | $20.00 | $80.00 | 567% more |
| GPT 5.2 Pro | GPT | $21.00 | $168.00 | 600% more |
| GPT 4 (0613) | GPT | $30.00 | $60.00 | 900% more |
| GPT 4 | GPT | $30.00 | $60.00 | 900% more |
| GPT 5.4 Pro | GPT | $30.00 | $180.00 | 900% more |
| GPT 5.5 Pro | GPT | $30.00 | $180.00 | 900% more |
| o1 Pro | GPT | $150.00 | $600.00 | 4900% more |
See exactly how much you spend on Kimi K3 and where you can save. Two-line wrapper install, no API keys shared.