grandet.
中文Explore Grandet
Menu

Switch model

API PRICES

Moonshot AI · kimi-k3

Provider prices, cheapest first

Browse all models

Price comparison

Official (cash)
Input 20 / output 100 CNY/million tokens月之暗面 ·
Lowest inference provider (cash)
Input 0.239 / output 10.8 USD/million tokensOpenRouter · Aggregator ·
Lowest relay (credit)
Older reference: 20 USD credit/million total tokensnewapi.prorisehub.com "海外国产编程模" ·

Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.

All official and inference price observations

Moonshot AI · kimi-k3 official price: input 20, output 100 CNY per million tokens (月之暗面, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 0.239, output 10.8 USD per million tokens. Relays have only older quotes; the lowest is newapi.prorisehub.com, group "Overseas Chinese coding models [machine translation] (on site: 海外国产编程模)" 20 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 274 sites have comparable prices; 520 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: 1-hour cache write 40.00 CNY per 1M tokens; cacheWrite is the 5-minute write

Price ranges per million tokens

Official cash prices · Lowest 40 · median 40 · highest 40 · 1 quotes CNY / per million tokens

Inference provider cash prices · Lowest 2.8793 · median 5.85 · highest 6 · 4 quotes USD / per million tokens

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
月之暗面Standard20100220CNY / 1M tokens1-hour cache write 40.00 CNY per 1M tokens; cacheWrite is the 5-minute write
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "1-hour cache write 40.00 CNY per 1M tokens; cacheWrite is the 5-minute write"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

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

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and sourcevs official
OpenRouter · AggregatorStandard0.23910.80.21—USD / 1M tokens
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000021",
    "input": "0.000000239",
    "output": "0.0000108"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
DeepInfraStandard2.8514.250.285—USD / 1M tokens
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Novita AIStandard3150.3—USD / 1M tokens
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Together AIStandard3150.3—USD / 1M tokens
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Other tariffs and prices to review

Inference providers

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
Fireworks AIStandard3150.3—USD / 1M tokensStandard processing · processingMode: STANDARD
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "processingMode: STANDARD"
  ],
  "contextTier": null,
  "processingMode": "standard",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Fireworks AIOther tariff3.7518.750.375—USD / 1M tokensPriority processing · processingMode: PRIORITY
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "processingMode: PRIORITY"
  ],
  "contextTier": null,
  "processingMode": "priority",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Fireworks AIStandard4.522.50.45—USD / 1M tokensStandard processing · processingMode: STANDARD
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "processingMode: STANDARD"
  ],
  "contextTier": null,
  "processingMode": "standard",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Fireworks AIOther tariff5.62528.1250.5625—USD / 1M tokensPriority processing · processingMode: PRIORITY
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "processingMode: PRIORITY"
  ],
  "contextTier": null,
  "processingMode": "priority",
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
OpenRouter · AggregatorBatch2.2811.40.228—USD / 1M tokensOpenRouter batch variant
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000228",
    "input": "0.00000228",
    "output": "0.0000114"
  },
  "conditions": [
    "OpenRouter batch variant"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source
Older official and inference provider prices

Earlier price observations and their original conditions

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
月之暗面Standard20100220CNY / 1M tokens1-hour cache write 40.00 CNY per 1M tokens; cacheWrite is the 5-minute write
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "1-hour cache write 40.00 CNY per 1M tokens; cacheWrite is the 5-minute write"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Inference providers

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
OpenRouter · AggregatorStandard0.30411.9360.21—USD / 1M tokens
Full price conditions
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.00000021",
    "input": "0.000000304",
    "output": "0.000011936"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "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.

Filtering by provider: newapi.prorisehub.com

Searching…

Browse all providers
Clear filters

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

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

sites have comparable prices274520 sites list this model; approximately 1 operators
Older lowest input price (reference)10USD credits / 1M
Median of each provider’s lowest price10USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Older price
01newapi.prorisehub.comAsk or discussCollected:
Carried previous price
Not updated this time; showing the previous price
View 3 plans		Overseas Chinese coding models [machine translation]Group on site: 海外国产编程模
[Stability ⭐⭐⭐⭐⭐] Overseas open-source model channel, full-strength relay, full-strength coding models [machine translation]Original: 【稳定性⭐⭐⭐⭐⭐】海外开源模型渠道满血中转，满血版本编程模型
Operator pending verification		1050120Full prices and sources
02newapi.prorisehub.comAsk or discussCollected:
Carried previous price
Not updated this time; showing the previous price
View 3 plans		default
⚠️ Default general group: can call every model on the site, don't use it if you don't understand!!! Billing is very expensive!!! [machine translation]Original: ⚠️ 默认通用分组：可调用全站所有模型，不懂别用！！！计费很贵！！！
Operator pending verification		20100240Full prices and sources
03newapi.prorisehub.comAsk or discussCollected:
Carried previous price
Not updated this time; showing the previous price
View 3 plans		OpenRouter-official relay [machine translation]Group on site: OpenRouter-官转
[Stability ⭐⭐⭐⭐⭐] openrouter official relay group, official not-dumbed-down full-strength experience [machine translation]Original: 【稳定性⭐⭐⭐⭐⭐】openrouter官方中转分组，官方不降智满血级体验
Operator pending verification		241202.448Full prices and sources
Special groups · 7 rows · not ranked

These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.

  • test or debug group: 3 rows
  • Free declaration, listed separately: 2 rows
  • near-zero-ratio group: 2 rows
  • zero-ratio group: 2 rows
  • api.wapq.cn · Perk [machine translation]Group on site: 福利 · kimi-k3 · Input 0 / Output 0 USD credits / 1M
  • wqdsjhaoai.site · Free 1 yi (100 million) token daily, shared site-wide [machine translation]Group on site: 每日免费1亿token，全站共享 · kimi-k3 · Input 0 / Output 0 USD credits / 1M
  • moyuu.cc · 🥚 · kimi-k3 · Input 0.1 / Output 0.5 USD credits / 1M
  • liangxinapi.top · free · kimi-k3 · Input 0.2 / Output 1 USD credits / 1M
  • moyuu.cc · 🥚 test [machine translation]Group on site: 🥚测 · kimi-k3 · Input 1 / Output 5 USD credits / 1M
  • ai.daoyivip.com · Chinese models test [machine translation]Group on site: 国模测试 · kimi-k3 · Input 2 / Output 10 USD credits / 1M
  • test-api.apiqik.online · default · kimi-k3 · Input 3 / Output 15 USD credits / 1M
View all 7 rows →
How this ranking works

All per-token prices: 93,968 prices from 854 sites (about 751 companies). 84,786 are ranked, from 838 sites (about 736 companies); 9,182 more are listed separately and not ranked. Prices collected up to 2026-10-24.

This model has 905 recorded prices; 445 can be compared directly (436 ranked, 9 listed separately). Not comparable yet: price not parsed yet 189, tiered by rules (see Tiered prices) 146, new price under review; showing the previous one 48, ratio looks unset 24, display unit not confirmed 21, billed per request or another unit 14, scope of the official doc price not confirmed 8

0 recent · 3 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Only older prices are available, so the statistics are for reference only. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.

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 →

Sources not accepted this cycle and reasons

FAQ

Which API is cheapest for Moonshot AI · kimi-k3?

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

What is the official price for Moonshot AI · kimi-k3?

Input 20, output 100 CNY per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 0.239, output 10.8 USD per million tokens.

How do I use Moonshot AI · kimi-k3 in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest Moonshot AI · kimi-k3 API to Claude Code for me". Install Skill →