API PRICES

Anthropic · claude-sonnet-5

Tiered prices, cheapest first

Browse all models

Price ranges per million tokens

Official cash prices · Lowest 4 · median 4 · highest 4 · 1 quotes USD / per million tokens

Inference provider cash prices · Lowest 4 · median 4 · highest 4 · 1 quotes USD / per million tokens

Uses the standard tier (shortest context, base price). Full rules are in Details.

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
sites have comparable prices536910 sites list this model; approximately 1 operators on this board
Lowest input price0.64USD credits / 1M
Median of each provider’s lowest price0.64USD credits / 1M
#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Recent price
01code4ai.topAsk or discussCollected:
Collected this cycle
View 4 plans
Super-high intelligence - kiropro - unstable [machine translation]Group on site: 超高智商-kiropro-不稳定
Standard tier · standard
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
Operator pending verification
0.643.20.0641.28Full prices and sources
01code4ai.topAsk or discussCollected:
Collected this cycle
View 4 plans
High intelligence - kiropro - stable [machine translation]Group on site: 高智商-kiropro-稳定
Standard tier · standard
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
Operator pending verification
0.643.20.0641.28Full prices and sources
03code4ai.topAsk or discussCollected:
Collected this cycle
View 4 plans
ccmax
Standard tier · standard
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
Operator pending verification
1.969.80.1963.92Full prices and sources
03code4ai.topAsk or discussCollected:
Collected this cycle
View 4 plans
ccmax1
Standard tier · standard
Operator pending verification
1.969.80.1963.92Full prices and sources
Special groups · 27 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: 17 rows
  • top-up or membership gated: 6 rows
  • marked display-only or do-not-select: 4 rows
  • near-zero-ratio group: 2 rows
  • deprecated or disabled: 1 rows
  • airouter.mxyhi.com · 福利 · claude-sonnet-5 · Input 0.003 / Output 0.015 USD credits / 1M
  • ergouzi.life · 0.5折Claude · claude-sonnet-5 · Input 0.04 / Output 0.2 USD credits / 1M
  • bikip.pro · duc-testing · claude-sonnet-5 · Input 0.4 / Output 2 USD credits / 1M
  • api.vibelearning.top · claude-cursor · claude-sonnet-5 · Input 1.4 / Output 7 USD credits / 1M
  • api.99ai.uk · claude官稳特惠组-日卡专用 · claude-sonnet-5 · Input 1.56 / Output 7.8 USD credits / 1M
  • clearapi.dev · claude官稳特惠组-日卡专用 · claude-sonnet-5 · Input 1.56 / Output 7.8 USD credits / 1M
  • zzshu.cc · Claude 测试专属-1 · claude-sonnet-5 · Input 1.7 / Output 8.5 USD credits / 1M
  • api.99ai.uk · claude高兼容兜底-日卡专用 · claude-sonnet-5 · Input 2 / Output 10 USD credits / 1M
  • api.witflow.ai · CC蒸馏测试组(提前订量) · claude-sonnet-5 · Input 2 / Output 10 USD credits / 1M
  • clearapi.dev · claude高兼容兜底-日卡专用 · claude-sonnet-5 · Input 2 / Output 10 USD credits / 1M
View all 27 rows →
Related variants · 7 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-5-thinking (-thinking · thinking edition): 7 rows
  • airouter.mxyhi.com · claude_kiro · claude-sonnet-5-thinking · Input 0.16 / Output 0.8 USD credits / 1M
  • tz.xingwan.store · kiro-自建号池 · claude-sonnet-5-thinking · Input 0.9 / Output 4.5 USD credits / 1M
  • xingwan.store · kiro-自建号池 · claude-sonnet-5-thinking · Input 0.9 / Output 4.5 USD credits / 1M
  • tz.xingwan.store · kiro-自建号池-带缓存 · claude-sonnet-5-thinking · Input 1.5 / Output 7.5 USD credits / 1M
  • xingwan.store · kiro-自建号池-带缓存 · claude-sonnet-5-thinking · Input 1.5 / Output 7.5 USD credits / 1M
  • api123.icu · default · claude-sonnet-5-thinking · Input 10 / Output 50 USD credits / 1M
  • api123.top · default · claude-sonnet-5-thinking · Input 10 / Output 50 USD credits / 1M
View all 7 rows →
How this ranking works

All tiered prices: 30,485 prices from 636 sites (about 555 companies). 28,608 are ranked, from 629 sites (about 548 companies); 1,877 more are listed separately and not ranked. Prices collected up to 2026-10-17.

This model has 840 tiered prices; 748 can be compared directly (706 ranked, 42 listed separately). Not comparable yet: display unit not confirmed 67, rule billed per request · compared separately 25

4 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero values are separately unverified, without proof of free eligibility.

For tiered models (e.g. longer context costs more) we use the standard tier: shortest context, normal service tier, base price without promotions. Prices that change with time of day or request options are listed separately with the reason. See “Details” for the full rules.

Prices are converted to site credits using each site’s published ratio and display multiplier. What you actually pay depends on its top-up rate. 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.

Full methodology →

Sources not accepted this cycle and reasons

FAQ

Which API is cheapest for Anthropic · claude-sonnet-5?

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

What is the official price for Anthropic · claude-sonnet-5?

Input 2, output 10 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 2, output 10 USD per million tokens. Input 0% higher than official.

How do I use Anthropic · claude-sonnet-5 in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest Anthropic · claude-sonnet-5 API to Claude Code for me". Install Skill →