Switch model

API PRICES

Moonshot AI · Kimi-K2-Instruct

Provider prices, cheapest first

Browse all models

All official and inference price observations

Moonshot AI · Kimi-K2-Instruct official price: not yet recorded. Cheapest inference provider: Novita AI, input 0.57, output 2.3 USD per million tokens. 14 sites have comparable prices; 26 sites list this model.

Price ranges per million tokens

Inference provider cash prices · Lowest 1.0025 · median 1.0276 · highest 1.0526 · 2 quotes USD / per million tokens

Each quote is blended into one price by this workload: ordinary input 75% · cache read 0% · output 25% · cache write 0%. Only prices in effect now are counted.

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Inference providers

For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.

ProviderTariffInputOutputCache readCache writeVia OpenRouter with 5% feeUnitObservedConditions and source
Novita AIStandard0.572.3——USD / 1M tokens
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
OpenRouter · Aggregator · Single priceStandard0.572.3——
Input 0.5985
Output 2.415
Original price × 1.05
USD / 1M tokensOpenRouter lists only quantized deployments of this model (fp8); they are listed separately. This is OpenRouter's single price, and it is compared.
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "input": "0.00000057",
    "output": "0.0000023"
  },
  "conditions": [
    "OpenRouter lists only quantized deployments of this model (fp8); they are listed apart from full-precision prices, so this single price is compared (R97)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Other tariffs and prices to review

Inference providers

For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.

ProviderTariffInputOutputCache readCache writeVia OpenRouter with 5% feeUnitObservedConditions and source
NovitaStandard0.572.3——
Input 0.5985
Output 2.415
Original price × 1.05
USD / 1M tokensQuantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · Same provider's price observed directly at novita.ai; that direct price is listed instead · quantization: fp8 · price listed by OpenRouter for this provider (endpoint novita/fp8)
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "input": "0.00000057",
    "output": "0.0000023"
  },
  "conditions": [
    "Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices",
    "Same provider's price observed directly at novita.ai; that direct price is listed instead"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp8",
    "price listed by OpenRouter for this provider (endpoint novita/fp8)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Searching…

Browse all providers

Blended price = input × 75% + output × 25%, without cache.

Price range: lowest — · median — · highest — (0 quotes, USD credits per million total tokens)

sites have comparable prices1426 sites list this model; approximately 0 operators
Lowest input price—USD credits / 1M
Median of each provider’s lowest price—USD credits / 1M

No comparable prices

No directly comparable prices for this model; see “How this ranking works” below for why.

View other prices and terms for this model
How this ranking works

All per-token prices: 128,524 prices from 1,383 sites (about 1,275 companies). 109,485 are ranked, from 1,349 sites (about 1,244 companies); 19,039 more are listed separately and not ranked. Prices collected up to 2026-11-15.

This model has 64 recorded prices; 24 can be compared directly. Not comparable yet: ratio looks unset 17, price not parsed yet 11, scope of the official doc price not confirmed 8, display unit not confirmed 4

0 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. No recent prices to summarize in this group.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

FAQ

Which API is cheapest for Moonshot AI · Kimi-K2-Instruct?

No valid quotes within 10 days. Older quotes are listed as reference prices.

How do I use Moonshot AI · Kimi-K2-Instruct in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest Moonshot AI · Kimi-K2-Instruct API to Claude Code for me". Install Skill →