MoonshotAI Kimi K3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
MoonshotAI Kimi K3 costs $0.504 per 1M input tokens and $8.10 per 1M output tokens at the standard tier, the lowest default-region price among the 18 providers SF·SIX tracks, from Sail Research (fp4). On Moonshot AI’s own API it costs $3.00 / $15.00. Cached input reads cost $0.18 per 1M tokens. Updated ; prices checked .
- Developer
- Moonshot AI
- Input modalities
- text, image, video
- Output modalities
- text
- Context tokens
- 1,048,576
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.504 input / $8.10 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| Sail ResearchOpenRouter | $0.504 | $8.10 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| InferenceNetOpenRouter | $0.304 | $11.94 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| RelaceOpenRouter | $0.27 | $14.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| ChutesOpenRouter | $1.85 | $9.50 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| MorphOpenRouter | $0.80 | $14.90 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| MakoraOpenRouter | $1.53 | $12.75 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AkashMLOpenRouter | $1.20 | $14.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| PhalaOpenRouter | $2.55 | $12.75 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DigitalOceanOpenRouter | $2.55 | $12.95 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepInfraOpenRouter | $2.85 | $14.25 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| BasetenOpenRouter | $3.00 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Fireworks AIOpenRouter | $3.00 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| ModalOpenRouter | $3.00 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Moonshot AIOpenRouter | $3.00 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| ParasailOpenRouter | $3.00 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Together AIOpenRouter | $3.00 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| WaferOpenRouter | $0.28 | $24.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AlibabaOpenRouter | $3.45 | $17.25 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| WaferOpenRouter · US region | $0.36 | $14.90 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Sail ResearchOpenRouter · US region | $0.84 | $13.50 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| InferenceNetOpenRouter · Fast tier | $2.49 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| ParasailOpenRouter · Fast tier | $3.00 | $15.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Fireworks AIOpenRouter · Fast tier | $4.50 | $22.50 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
Batch and free variants
- Kimi K3 (batch) · from $2.28 input / $11.40 output per 1M tokens
Prices by service tier
| Tier | Input / 1M | Output / 1M | Cache read / 1M | Cheapest provider | vs standard (blended) |
|---|---|---|---|---|---|
| Standard | $0.504 | $8.10 | $0.18 | Sail Research | 100% |
| BatchBatch endpoint | $2.28 | $11.40 | $0.228 | OpenRouter (auto-routed) | 190% |
| Fast | $2.49 | $15.00 | $0.35 | InferenceNet | 234% |
Each tier’s cheapest endpoint. Standard is the default-region headline; flex and batch trade speed or latency for a lower price, priority and fast cost more for faster service.
Regional endpoints
| Provider and region | Input / 1M | Output / 1M |
|---|---|---|
| WaferUS regionmxfp4 | $0.36 | $14.90 |
| Sail ResearchUS regionfp4 | $0.84 | $13.50 |
Data-residency endpoints in a named region; they are never used as the headline while a default-region price exists.
Speed by provider
| Provider and terms | Throughput | Latency | Uptime | Input / 1M |
|---|---|---|---|---|
| Makorafp4 | 153 tok/s | 812 ms | Not reported | $1.53 |
| InferenceNetFast tierfp4 | 104 tok/s | 658 ms | 100.0% | $2.49 |
| Basetenfp8 | 90 tok/s | 1.50 s | 100.0% | $3.00 |
| Fireworks AIFast tier | 87 tok/s | 1.32 s | 100.0% | $4.50 |
| WaferUS regionmxfp4 | 85 tok/s | 778 ms | 100.0% | $0.36 |
| Morphfp8 | 84 tok/s | 1.49 s | 100.0% | $0.80 |
| InferenceNetfp4 | 83 tok/s | 879 ms | 100.0% | $0.304 |
| Sail ResearchUS regionfp4 | 82 tok/s | 1.20 s | 100.0% | $0.84 |
| Phala | 74 tok/s | 1.65 s | 100.0% | $2.55 |
| Sail Researchfp4 | 74 tok/s | 1.74 s | 100.0% | $0.504 |
| Wafermxfp4 | 74 tok/s | 963 ms | 100.0% | $0.28 |
| Modalmxfp4 | 66 tok/s | 735 ms | 100.0% | $3.00 |
Previous 30 minutes; reported by OpenRouter. Fastest first.
Usage on OpenRouter
| UTC day | Tokens |
|---|---|
| 2026-10-10 | 307,169,340,883 |
| 2026-10-11 | 308,653,041,997 |
| 2026-10-12 | 452,261,046,008 |
| 2026-10-13 | 497,238,529,260 |
| 2026-10-14 | 393,654,343,806 |
| 2026-10-15 | 236,085,134,296 |
| 2026-10-16 | 203,418,976,604 |
OpenRouter rankings (CC BY 4.0), named daily rows. Most-used AI models
Benchmarks
Artificial Analysis Intelligence Index 43.6, coding index 76.2, agentic index 50.0 (Artificial Analysis via OpenRouter, CC BY 4.0; not an SF·SIX measurement).
Prediction markets
MoonshotAI Kimi K3 meets the rule for SF·SIX price and usage ladders; the current average standard input price across qualifying OpenRouter endpoints is $1.83 per 1M tokens. Open MoonshotAI Kimi K3 markets (Hedera testnet, test funds only) · How AI prediction markets work
Compare and estimate
Sources and method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Prices from OpenRouter; each row below links its source and observation date. Methodology and editorial policy.
Frequently asked questions
How much does MoonshotAI Kimi K3 cost per 1M tokens?
$0.504 per 1M input tokens and $8.10 per 1M output tokens at the standard tier, the lowest default-region price SF·SIX tracks, from Sail Research (fp4). On Moonshot AI’s own API it costs $3.00 / $15.00. The cheapest batch price is $2.28 input and $11.40 output per 1M tokens.
Which providers offer MoonshotAI Kimi K3?
18 providers with 23 priced endpoints: AkashML, Alibaba, Baseten, Chutes, DeepInfra, DigitalOcean, Fireworks AI, InferenceNet and others.
What is the context window of MoonshotAI Kimi K3?
1,048,576 tokens.
How fast is MoonshotAI Kimi K3?
The fastest measured endpoint is Makora (fp4) at 153 tok/s, as reported by OpenRouter for the previous 30 minutes.
How much is MoonshotAI Kimi K3 used?
203,418,976,604 tokens on 2026-10-16 (UTC) through OpenRouter, per OpenRouter’s public rankings. This is OpenRouter traffic only, not all usage.
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.