API PRICES

Anthropic · claude-fable-5

Provider prices, cheapest first

Browse all models

Anthropic · claude-fable-5 official price: input 10, output 50 USD per million tokens (Anthropic, observed 2026-10-17). Cheapest inference provider: DeepInfra, input 10.00, output 50.00 USD per million tokens. Cheapest relay: apiqd.com, group "Claude2" 4 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 523 sites have comparable prices; 865 sites list this model.Relay blended price uses 75% input and 25% output.

Price ranges per million tokens

Official cash prices · Lowest 20 · median 20 · highest 20 · 1 quotes USD / per million tokens

Inference provider cash prices · Lowest 20 · median 20 · highest 20 · 2 quotes USD / per million tokens

USD_CREDIT · Lowest 4 · median 4 · highest 16 · 5 quotes USD / per million tokens, site credit

Official price

ProviderInputOutputCache readCache writeUnitObservedConditions and source
Anthropic1050112.50USD / 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
DeepInfra10.0050.00——USD / 1M tokens
Official source
Input 0% · Output 0%
OpenRouter · Aggregator1050112.5USD / 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: apiqd.com

Searching…

Browse all providers
Clear filters

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

Price range: lowest 4 · median 4 · highest 16 (5 quotes, USD credits per million total tokens)

sites have comparable prices523865 sites list this model; approximately 1 operators
Lowest input price2USD credits / 1M
Median of each provider’s lowest price2USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Recent price
01apiqd.comAsk or discussCollected:
Collected this cycle
View 5 plans
Claude2
Very high cache, saves more money [machine translation]Original: 缓存超高更省钱
Operator pending verification
2100.24Median price ÷ this price: 1×Full prices and sources
01apiqd.comAsk or discussCollected:
Collected this cycle
View 5 plans
Claude3 kiro
Supports 1m context, extra-long cache 1h [machine translation]Original: 支持1m上下文,超长缓存1h
Operator pending verification
2100.24Median price ÷ this price: 1×Full prices and sources
01apiqd.comAsk or discussCollected:
Collected this cycle
View 5 plans
aws Claude
aws, cache optimization + 1m context!!! [machine translation]Original: aws,缓存优化+1m上下文!!!
Operator pending verification
2100.24Median price ÷ this price: 1×Full prices and sources
04apiqd.comAsk or discussCollected:
Collected this cycle
View 5 plans
Claude4Operator pending verification2.512.50.255Median price ÷ this price: 0.8×Full prices and sources
05apiqd.comAsk or discussCollected:
Collected this cycle
View 5 plans
Claude MAX
Official max, fable-5 supported [machine translation]Original: 官方max,fable-5支持
Operator pending verification
8400.816Median price ÷ this price: 0.25×Full prices and sources
Special groups · 16 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.

  • near-zero-ratio group: 9 rows
  • top-up or membership gated: 3 rows
  • ratio looks like a placeholder: 2 rows
  • Free declaration, listed separately: 1 rows
  • test or debug group: 1 rows
  • zero-ratio group: 1 rows
  • 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 · claude-fable-5 · Input 0 / Output 0 USD credits / 1M
  • bmodels.top · default · claude-fable-5 · Input 0.256 / Output 1.6 USD credits / 1M
  • bmodels.top · claude95% high cache [machine translation]Group on site: claude95%高缓存 · claude-fable-5 · Input 0.264 / Output 1.65 USD credits / 1M
  • 77code.cn · Perk claude [machine translation]Group on site: 福利claude · claude-fable-5 · Input 0.4 / Output 2 USD credits / 1M
  • 77code.fun · Perk claude [machine translation]Group on site: 福利claude · claude-fable-5 · Input 0.4 / Output 2 USD credits / 1M
  • code.77code.fun · Perk claude [machine translation]Group on site: 福利claude · claude-fable-5 · Input 0.4 / Output 2 USD credits / 1M
  • doce.77code.fun · Perk claude [machine translation]Group on site: 福利claude · claude-fable-5 · Input 0.4 / Output 2 USD credits / 1M
  • llmhub.ltd · Claude-Kiro-Pro · claude-fable-5 · Input 0.4 / Output 2 USD credits / 1M
  • realmrouter.cn · Claude-kiro special price [machine translation]Group on site: Claude-kiro特惠 · claude-fable-5 · Input 0.45 / Output 2.25 USD credits / 1M
  • test-api.apiqik.online · claudecode-max · claude-fable-5-thinking · Input 3 / Output 15 USD credits / 1M
View all 16 rows →
Related variants · 77 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-fable-5-thinking (-thinking · thinking edition): 66 rows
  • claude-fable-5[1m] ([1m] · context or size tier (e.g. 128k, 1M, 4K)): 3 rows
  • [低价ccmax]claude-fable-5 ([低价ccmax] · max edition): 1 rows
  • claude-fable-5-high-thinking (-high-thinking · thinking edition): 1 rows
  • claude-fable-5-low-thinking (-low-thinking · thinking edition): 1 rows
  • claude-fable-5-max (-max · max edition): 1 rows
  • claude-fable-5-max-thinking (-max-thinking · max edition, thinking edition): 1 rows
  • claude-fable-5-medium-thinking (-medium-thinking · thinking edition): 1 rows
  • claude-fable-5-xhigh-thinking (-xhigh-thinking · thinking edition): 1 rows
  • claude-fable-5[1m]-thinking ([1m] -thinking · context or size tier (e.g. 128k, 1M, 4K), thinking edition): 1 rows
  • pro.auroai.icu · Kiro full-strength high cache [machine translation]Group on site: Kiro 满血高缓 · claude-fable-5-thinking · Input 2 / Output 10 USD credits / 1M
  • api.bddevlab.online · default · claude-fable-5[1m] · Input 6.7136 / Output 32.2816 USD credits / 1M
  • ai.comfly.org · cc · claude-fable-5-thinking · Input 8 / Output 40 USD credits / 1M
  • ai.t8star.org · cc · claude-fable-5-thinking · Input 8 / Output 40 USD credits / 1M
  • api.bltcy.ai · cc · claude-fable-5-thinking · Input 8 / Output 40 USD credits / 1M
  • api.bltcy.top · cc · claude-fable-5-thinking · Input 8 / Output 40 USD credits / 1M
  • kg-api.cloud · cc · claude-fable-5-thinking · Input 8 / Output 40 USD credits / 1M
  • one-api.bltcy.top · cc · claude-fable-5-thinking · Input 8 / Output 40 USD credits / 1M
  • ai.comfly.org · default · claude-fable-5-thinking · Input 10 / Output 50 USD credits / 1M
  • ai.t8star.org · default · claude-fable-5-thinking · Input 10 / Output 50 USD credits / 1M
View all 77 rows →
How this ranking works

All per-token prices: 97,455 prices from 871 sites (about 765 companies). 89,631 are ranked, from 861 sites (about 755 companies); 7,824 more are listed separately and not ranked. Prices collected up to 2026-10-17.

This model has 3177 recorded prices; 1494 can be compared directly (1392 ranked, 102 listed separately). Not comparable yet: price not parsed yet 682, tiered by rules (see Tiered prices) 615, display unit not confirmed 90, scope of the official doc price not confirmed 49, billed per request or another unit 47, ratio looks unset 31, new price under review; showing the previous one 2

5 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-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

Sources not accepted this cycle and reasons

FAQ

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

apiqd.com, group "Claude2", 4 USD credit per million total tokens, observed 2026-10-16. 523 sites have comparable prices.

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

Input 10, output 50 USD per million tokens, checked 2026-10-17. Lowest inference provider: DeepInfra, input 10, output 50 USD per million tokens. Input 0% higher than official.

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

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