API PRICES

Anthropic · claude-opus-4-8

Provider prices, cheapest first

Browse all models

Anthropic · claude-opus-4-8 official price: input 5, output 25 USD per million tokens (Anthropic, observed 2026-10-16). Cheapest inference provider: DeepInfra, input 5.00, output 25.00 USD per million tokens. Cheapest relay: api.mixrai.com "default" 10 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 572 sites have comparable prices; 923 sites list this model.Relay blended price uses 75% input and 25% output.

Official price

ProviderInputOutputCache readCache writeUnitObservedConditions and source
Anthropic5250.506.25USD / 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
DeepInfra5.0025.00——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: api.mixrai.com

Searching…

Browse all providers
Clear filters

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

sites have comparable prices572923 sites list this model; approximately 1 operators
Lowest input price5USD credits / 1M
Median of each provider’s lowest price5USD 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
01api.mixrai.comAsk or discussCollected:
View 1 plans
default
默认分组
525—10Full prices and sources
Special groups · 57 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: 28 rows
  • near-zero-ratio group: 15 rows
  • marked display-only or do-not-select: 10 rows
  • internal or channel key: 8 rows
  • top-up or membership gated: 7 rows
  • airouter.mxyhi.com · 福利 · claude-opus-4-8 · Input 0.005 / Output 0.025 USD credits / 1M
  • nty-hk.zhouyang168.top · cc8 · claude-opus-4-8 · Input 0.05 / Output 0.25 USD credits / 1M
  • yfy.zhouyang168.top · cc8 · claude-opus-4-8 · Input 0.05 / Output 0.25 USD credits / 1M
  • ainzy.net · kiro-claude · claude-opus-4-8 · Input 0.1 / Output 0.5 USD credits / 1M
  • newtonrouter.com · Claude Kiro · claude-opus-4-8 · Input 0.11 / Output 0.55 USD credits / 1M
  • bmodels.top · default · claude-opus-4-8 · Input 0.128 / Output 0.64 USD credits / 1M
  • bmodels.top · claude95%高缓存 · claude-opus-4-8 · Input 0.132 / Output 0.66 USD credits / 1M
  • 77code.cn · 福利claude · claude-opus-4-8 · Input 0.2 / Output 1 USD credits / 1M
  • 77code.fun · 福利claude · claude-opus-4-8 · Input 0.2 / Output 1 USD credits / 1M
  • code.77code.fun · 福利claude · claude-opus-4-8 · Input 0.2 / Output 1 USD credits / 1M
View all 57 rows →
Related variants · 215 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-opus-4-8-thinking (-thinking · thinking edition): 168 rows
  • claude-opus-4-8-max (-max · max edition): 17 rows
  • claude-opus-4-8[1m] ([1m] · context or size tier (e.g. 128k, 1M, 4K)): 7 rows
  • claude-opus-4-8-high-thinking (-high-thinking · thinking edition): 5 rows
  • claude-opus-4-8-low-thinking (-low-thinking · thinking edition): 5 rows
  • claude-opus-4-8-max-thinking (-max-thinking · max edition, thinking edition): 5 rows
  • claude-opus-4-8-xhigh-thinking (-xhigh-thinking · thinking edition): 5 rows
  • claude-opus-4-8-medium-thinking (-medium-thinking · thinking edition): 2 rows
  • [低价ccmax]claude-opus-4-8 ([低价ccmax] · max edition): 1 rows
  • oojj.top · aws0-ex · claude-opus-4-8-thinking · Input 0.25 / Output 1.25 USD credits / 1M
  • 00ccc.cn · 0.06-kiro · claude-opus-4-8-max · Input 0.3 / Output 1.5 USD credits / 1M
  • api.mxwell.ai · Claude-kiro · claude-opus-4-8-thinking · Input 0.6 / Output 3 USD credits / 1M
  • mxwell.ai · Claude-kiro · claude-opus-4-8-thinking · Input 0.6 / Output 3 USD credits / 1M
  • oojj.top · awsq-a-ex · claude-opus-4-8-thinking · Input 0.6 / Output 3 USD credits / 1M
  • api.wapq.cn · default · claude-opus-4-8-thinking · Input 1 / Output 1 USD credits / 1M
  • apiqd.com · Claude2 · claude-opus-4-8-thinking · Input 1 / Output 5 USD credits / 1M
  • pro.auroai.icu · Kiro 满血高缓 · claude-opus-4-8-thinking · Input 1 / Output 5 USD credits / 1M
  • ssnaicloud.com · CC krio · claude-opus-4-8-max · Input 1.25 / Output 6.25 USD credits / 1M
  • ssnaiyun.com · CC krio · claude-opus-4-8-max · Input 1.25 / Output 6.25 USD credits / 1M
View all 215 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 4616 recorded prices; 2335 can be compared directly (2018 ranked, 317 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 791, price not parsed yet 605, new price under review; showing the previous one 353, display unit not confirmed 222, billed per request or another unit 212, ratio looks unset 50, scope of the official doc price not confirmed 48

1 recent · 0 stale (older than 7 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