The board shows this model's cheapest measured offer ($2.47/1M); the smaller figure under it is the mean of the 50 offers listed below ($5.39/1M). Add those up and divide — it matches. 24h token volume (261B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here. Cross-check — Vercel AI Gateway: —% of gateway token volume, 5.8% of spend (2026-11-03; share-of-traffic, daily, data CC BY 4.0).
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| Relace (fp4) | OpenRouter ↗ | $0.182 | $9.34 | 1394ms | 67 | 100% | API-measured |
| Wafer (us) | OpenRouter ↗ | $0.276 | $9.60 | 668ms | 90 | 100% | API-measured |
| Sail Research (fp4/us) | OpenRouter ↗ | $0.224 | $10.72 | 806ms | 80 | 100% | API-measured |
| Sail Research (fp4) | OpenRouter ↗ | $0.224 | $10.72 | 1266ms | 81 | 100% | API-measured |
| ParetoAlpha (us) | OpenRouter ↗ | $1.00 | $11.25 | — | — | — | API-measured |
| Makora (fp4) | OpenRouter ↗ | $0.500 | $13.00 | 953ms | 83 | 100% | API-measured |
| Chutes (mxfp4) | OpenRouter ↗ | $1.85 | $9.50 | 3657ms | 19 | 100% | API-measured |
| Wafer | OpenRouter ↗ | $0.192 | $15.00 | 730ms | 88 | 100% | API-measured |
| Decart (mxfp4) | OpenRouter ↗ | $1.95 | $9.75 | 1954ms | 87 | 100% | API-measured |
| Morph (fp8) | OpenRouter ↗ | $1.42 | $12.00 | 1235ms | 79 | 100% | API-measured |
| Fireworks (spot) | OpenRouter ↗ | $2.10 | $10.50 | — | — | — | API-measured |
| InferenceNet (us) | OpenRouter ↗ | $0.234 | $16.50 | 750ms | 47 | 100% | API-measured |
| InferenceNet (fp4) | OpenRouter ↗ | $0.234 | $16.50 | 726ms | 45 | 100% | API-measured |
| AkashML (fp4) | OpenRouter ↗ | $1.20 | $14.00 | 1125ms | 53 | 100% | API-measured |
| sail | Pricebook (LiteLLM) ↗ | $2.50 | $12.50 | — | — | — | Official list |
| Phala | OpenRouter ↗ | $2.55 | $12.75 | 3681ms | 28 | 100% | API-measured |
| DigitalOcean | OpenRouter ↗ | $2.55 | $12.95 | 1916ms | 21 | 100% | API-measured |
| aiand | Pricebook (LiteLLM) ↗ | $3.00 | $12.50 | — | — | — | Official list |
| Wafer (fast) | OpenRouter ↗ | $0.152 | $22.00 | 676ms | 87 | 100% | API-measured |
| scx-ai | Pricebook (LiteLLM) ↗ | $2.83 | $14.13 | — | — | — | Official list |
| deepinfra | Pricebook (LiteLLM) ↗ | $2.85 | $14.25 | — | — | — | Official list |
| deepinfra | HuggingFace Router ↗ | $2.85 | $14.25 | 833ms | 16 | — | API-measured |
| DeepInfra (mxfp4) | OpenRouter ↗ | $2.85 | $14.25 | 1496ms | 22 | 100% | API-measured |
| InferenceNet (us/fast) | OpenRouter ↗ | $0.500 | $22.00 | 584ms | 79 | 100% | API-measured |
| InferenceNet (fast) | OpenRouter ↗ | $0.500 | $22.00 | 587ms | 80 | 100% | API-measured |
| github_copilot | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| moonshot | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| nebius | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| together_ai | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| tencent | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| fireworks_ai | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| novita | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| aihubmix | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| baseten | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| opencode_go | Pricebook (LiteLLM) ↗ | $3.00 | $15.00 | — | — | — | Official list |
| baseten | HuggingFace Router ↗ | $3.00 | $15.00 | 773ms | 73 | — | API-measured |
| novita-ai | Novita AI ↗ | $3.00 | $15.00 | — | — | — | API-measured |
| requesty | Requesty ↗ | $3.00 | $15.00 | — | — | — | API-measured |
| Amazon Bedrock (us-east-2) | OpenRouter ↗ | $3.00 | $15.00 | 3905ms | 28 | 100% | API-measured |
| Parasail (fp4) | OpenRouter ↗ | $3.00 | $15.00 | 1565ms | 62 | 100% | API-measured |
Volume trend
Last 30 days: 225B → 261B (+16%); range 180B–497B tokens/day. Source: OpenRouter public rankings; refreshed hourly.
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/kimi-k3.json. Free reuse requires attribution to tkx.org.
About
Kimi K3 is a machine-learning system that serves as a large language model, designed to process and generate human-like text based on input data. It is listed under the organization tag "moonshotai" and is available on AI model marketplaces for various inference providers to utilize.
AI-generated summary from public information — is this yours?
FAQ
How much does Kimi K3 (batch) cost?
Cheapest measured offer right now: $0.1824/1M input, $9.3388/1M output via Relace (fp4) — across 33 tracked providers, refreshed hourly.
Who serves Kimi K3 (batch)?
33 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is Kimi K3 (batch) used?
Kimi K3 (batch) routed 261B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.