API PRICES

Anthropic · claude-sonnet-4-6

Provider prices, cheapest first

Browse all models

Anthropic · claude-sonnet-4-6 official price: input 3, output 15 USD per million tokens (Anthropic, observed 2026-10-16). Cheapest inference provider: DeepInfra, input 3.00, output 15.00 USD per million tokens. Relays have only older quotes; the lowest is code4ai.top, group "Super-high intelligence - kiropro - unstable [machine translation] (on site: 超高智商-kiropro-不稳定)" 1.92 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 556 sites have comparable prices; 900 sites list this model.Relay blended price uses 75% input and 25% output.

Official price

ProviderInputOutputCache readCache writeUnitObservedConditions and source
Anthropic3150.303.75USD / 1M tokens
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

ProviderInputOutputCache readCache writeUnitObservedConditions and sourcevs official
DeepInfra3.0015.00——USD / 1M tokens
Official source
Input 0% · Output 0%

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

Filtering by provider: code4ai.top

Searching…

Browse all providers
Clear filters

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

sites have comparable prices556900 sites list this model; approximately 1 operators
Older lowest input price (reference)0.96USD credits / 1M
Median of each provider’s lowest price0.96USD 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
01code4ai.topAsk or discussCollected:
View 4 plans
Super-high intelligence - kiropro - unstable [machine translation]Group on site: 超高智商-kiropro-不稳定
Unstable + super-high intelligence + high cache. Output length about 22000 with super-high intelligence, close to the performance bar of aws-claude or ccmax; often runs out of stock and gets cut off [machine translation]Original: 不稳定+超高智商+高缓。输出长度22000左右超高智商,接近aws-claude或者ccmax的性能门槛,经常容易没货拉闸
0.964.80.0961.92Full prices and sources
01code4ai.topAsk or discussCollected:
View 4 plans
High intelligence - kiropro - stable [machine translation]Group on site: 高智商-kiropro-稳定
Stable + high intelligence + high cache. Output length about 18500 with high intelligence, top choice for long tasks; unstable kiro disconnects often and costs more [machine translation]Original: 稳定+高智商+高缓。输出长度18500左右高智商,长任务首选,不稳定kiro频繁断开会花钱更多
0.964.80.0961.92Full prices and sources
03code4ai.topAsk or discussCollected:
View 4 plans
ccmax
Cache rate 99, full-strength, not dumbed down, passes almost all checks [machine translation]Original: 缓存率99,满血不降智,几乎所有检测全过
2.9414.70.2945.88Full prices and sources
03code4ai.topAsk or discussCollected:
View 4 plans
ccmax12.9414.70.2945.88Full prices and sources
Special groups · 48 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: 24 rows
  • near-zero-ratio group: 13 rows
  • marked display-only or do-not-select: 12 rows
  • internal or channel key: 5 rows
  • top-up or membership gated: 3 rows
  • api.pezayo.com · codex anthropic · claude-sonnet-4-6 · Input 0.009 / Output 0.045 USD credits / 1M
  • nty-hk.zhouyang168.top · cc8 · claude-sonnet-4-6 · Input 0.03 / Output 0.15 USD credits / 1M
  • yfy.zhouyang168.top · cc8 · claude-sonnet-4-6 · Input 0.03 / Output 0.15 USD credits / 1M
  • ainzy.net · kiro-claude · claude-sonnet-4-6 · Input 0.06 / Output 0.3 USD credits / 1M
  • newtonrouter.com · Claude Kiro · claude-sonnet-4-6 · Input 0.066 / Output 0.33 USD credits / 1M
  • 77code.cn · Perk claude [machine translation]Group on site: 福利claude · claude-sonnet-4-6 · Input 0.12 / Output 0.6 USD credits / 1M
  • 77code.fun · Perk claude [machine translation]Group on site: 福利claude · claude-sonnet-4-6 · Input 0.12 / Output 0.6 USD credits / 1M
  • code.77code.fun · Perk claude [machine translation]Group on site: 福利claude · claude-sonnet-4-6 · Input 0.12 / Output 0.6 USD credits / 1M
  • doce.77code.fun · Perk claude [machine translation]Group on site: 福利claude · claude-sonnet-4-6 · Input 0.12 / Output 0.6 USD credits / 1M
  • llmhub.ltd · Claude-Kiro-Pro · claude-sonnet-4-6 · Input 0.12 / Output 0.6 USD credits / 1M
View all 48 rows →
Related variants · 291 rows · not ranked

These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.

  • claude-sonnet-4-6-thinking (-thinking · thinking edition): 281 rows
  • claude-sonnet-4-6-max (-max · max edition): 4 rows
  • 「FZ」claude-sonnet-4-6-thinking-Token (-thinking-token · thinking edition): 3 rows
  • [kiro]claude-sonnet-4-6-thinking (-thinking · thinking edition): 1 rows
  • [低价ccmax]claude-sonnet-4-6 ([低价ccmax] · max edition): 1 rows
  • [椰果按量]claude-sonnet-4-6-thinking (-thinking · thinking edition): 1 rows
  • oojj.top · aws0-ex · claude-sonnet-4-6-thinking · Input 0.15 / Output 0.75 USD credits / 1M
  • api.mxwell.ai · Claude-kiro · claude-sonnet-4-6-thinking · Input 0.36 / Output 1.8 USD credits / 1M
  • mxwell.ai · Claude-kiro · claude-sonnet-4-6-thinking · Input 0.36 / Output 1.8 USD credits / 1M
  • oojj.top · awsq-a-ex · claude-sonnet-4-6-thinking · Input 0.36 / Output 1.8 USD credits / 1M
  • apiqd.com · Claude1 · claude-sonnet-4-6-thinking · Input 0.45 / Output 2.25 USD credits / 1M
  • 1xm.ai · cc-fast · claude-sonnet-4-6-thinking · Input 0.6 / Output 3 USD credits / 1M
  • apiqd.com · aws Claude · claude-sonnet-4-6-thinking · Input 0.6 / Output 3 USD credits / 1M
  • apiqd.com · Claude2 · claude-sonnet-4-6-thinking · Input 0.6 / Output 3 USD credits / 1M
  • apiqd.com · claude default · claude-sonnet-4-6-thinking · Input 0.6 / Output 3 USD credits / 1M
  • apiqd.com · Claude3 kiro · claude-sonnet-4-6-thinking · Input 0.6 / Output 3 USD credits / 1M
View all 291 rows →
How this ranking works

All per-token prices: 96,427 prices from 839 sites (about 733 companies). 88,950 are ranked, from 826 sites (about 720 companies); 7,477 more are listed separately and not ranked. Prices collected up to 2026-10-10.

This model has 4572 recorded prices; 2393 can be compared directly (1993 ranked, 400 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 673, price not parsed yet 631, new price under review; showing the previous one 346, display unit not confirmed 235, billed per request or another unit 173, ratio looks unset 73, scope of the official doc price not confirmed 48

0 recent · 4 stale (older than 7 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 →

Switch model