MoleAPI logo
MoleAPI
AI model gateway
Models/Anthropic

Anthropic

Anthropic models, pricing, and protocols

23 currently available models with pricing synced from the MoleAPI console.

23 models

Compare
A
claude-fable-5-70%

Claude model by Anthropic for general chat, writing, coding assistance, and tool-assisted workflows.

View model
defaultx1
base
Input$10 / 1M tokens
Output$50 / 1M tokens
Cache read$1 / 1M tokens
Cache write$12.5 / 1M tokens
Cache write (1 hour)$20 / 1M tokens
discountx0.8
base
Input$8 / 1M tokens
Output$40 / 1M tokens
Cache read$0.8 / 1M tokens
Cache write$10 / 1M tokens
Cache write (1 hour)$16 / 1M tokens
relayx0.3
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
Cache write$3.75 / 1M tokens
Cache write (1 hour)$6 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-fable-5-1-70%

claude-fable-5-1 · Model for reasoning, coding and multi-step agent tasks.

View model
defaultx1
base
Input$10 / 1M tokens
Output$50 / 1M tokens
Cache read$0.25 / 1M tokens
Cache write$12.5 / 1M tokens
Cache write (1 hour)$20 / 1M tokens
discountx0.8
base
Input$8 / 1M tokens
Output$40 / 1M tokens
Cache read$0.2 / 1M tokens
Cache write$10 / 1M tokens
Cache write (1 hour)$16 / 1M tokens
relayx0.3
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.075 / 1M tokens
Cache write$3.75 / 1M tokens
Cache write (1 hour)$6 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-haiku-5-5-70%

claude-haiku-5-5 is a Anthropic model available through MoleAPI with anthropic, openai access. It fits OpenAI compatible, Anthropic compatible, Prompt cache workflows, with pricing synced from the MoleAPI console.

View model
defaultx1
standard
Length ≤ 100K
Input$0.1 / 1M tokens
Output$0.5 / 1M tokens
Cache read$0.01 / 1M tokens
Cache write$0.125 / 1M tokens
Cache write (1 hour)$0.2 / 1M tokens
long_context
Input$0.5 / 1M tokens
Output$2.5 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$0.625 / 1M tokens
Cache write (1 hour)$1 / 1M tokens
discountx0.8
standard
Length ≤ 100K
Input$0.08 / 1M tokens
Output$0.4 / 1M tokens
Cache read$0.008 / 1M tokens
Cache write$0.1 / 1M tokens
Cache write (1 hour)$0.16 / 1M tokens
long_context
Input$0.4 / 1M tokens
Output$2 / 1M tokens
Cache read$0.4 / 1M tokens
Cache write$0.5 / 1M tokens
Cache write (1 hour)$0.8 / 1M tokens
relayx0.3
standard
Length ≤ 100K
Input$0.03 / 1M tokens
Output$0.15 / 1M tokens
Cache read$0.003 / 1M tokens
Cache write$0.0375 / 1M tokens
Cache write (1 hour)$0.06 / 1M tokens
long_context
Input$0.15 / 1M tokens
Output$0.75 / 1M tokens
Cache read$0.15 / 1M tokens
Cache write$0.1875 / 1M tokens
Cache write (1 hour)$0.3 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-5-70%Official profile verified

Claude Opus 5 is Anthropic's July 2026 high-capability model for complex agentic coding, code review, enterprise knowledge work, and tasks that require sustained autonomous execution.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
discountx0.8
base
Input$4 / 1M tokens
Output$20 / 1M tokens
Cache read$0.4 / 1M tokens
Cache write$5 / 1M tokens
Cache write (1 hour)$8 / 1M tokens
relayx0.3
base
Input$1.5 / 1M tokens
Output$7.5 / 1M tokens
Cache read$0.15 / 1M tokens
Cache write$1.875 / 1M tokens
Cache write (1 hour)$3 / 1M tokens
AA index 60anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-5-5-70%

claude-opus-5-5 is a Anthropic model available through MoleAPI with anthropic, openai access. It fits OpenAI compatible, Anthropic compatible, Prompt cache workflows, with pricing synced from the MoleAPI console.

View model
defaultx1
base
Input$4 / 1M tokens
Output$20 / 1M tokens
Cache read$0.2 / 1M tokens
Cache write$5 / 1M tokens
Cache write (1 hour)$8 / 1M tokens
discountx0.8
base
Input$3.2 / 1M tokens
Output$16 / 1M tokens
Cache read$0.16 / 1M tokens
Cache write$4 / 1M tokens
Cache write (1 hour)$6.4 / 1M tokens
relayx0.3
base
Input$1.2 / 1M tokens
Output$6 / 1M tokens
Cache read$0.06 / 1M tokens
Cache write$1.5 / 1M tokens
Cache write (1 hour)$2.4 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-sonnet-5-70%Official profile verified

Claude Sonnet 5 is Anthropic's balanced flagship for coding, agents, and enterprise workflows. It targets a strong speed-intelligence mix and enables adaptive thinking by default.

View model
defaultx1
base
Input$2 / 1M tokens
Output$10 / 1M tokens
Cache read$0.2 / 1M tokens
Cache write$2.5 / 1M tokens
Cache write (1 hour)$4 / 1M tokens
discountx0.8
base
Input$1.6 / 1M tokens
Output$8 / 1M tokens
Cache read$0.16 / 1M tokens
Cache write$2 / 1M tokens
Cache write (1 hour)$3.2 / 1M tokens
relayx0.3
base
Input$0.6 / 1M tokens
Output$3 / 1M tokens
Cache read$0.06 / 1M tokens
Cache write$0.75 / 1M tokens
Cache write (1 hour)$1.2 / 1M tokens
AA index 53anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-sonnet-5-5-70%

claude-sonnet-5-5 is a Anthropic model available through MoleAPI with anthropic, openai access. It fits OpenAI compatible, Anthropic compatible, Prompt cache workflows, with pricing synced from the MoleAPI console.

View model
defaultx1
base
Input$2 / 1M tokens
Output$10 / 1M tokens
Cache read$0.2 / 1M tokens
Cache write$2.5 / 1M tokens
Cache write (1 hour)$4 / 1M tokens
discountx0.8
base
Input$1.6 / 1M tokens
Output$8 / 1M tokens
Cache read$0.16 / 1M tokens
Cache write$2 / 1M tokens
Cache write (1 hour)$3.2 / 1M tokens
relayx0.3
base
Input$0.6 / 1M tokens
Output$3 / 1M tokens
Cache read$0.06 / 1M tokens
Cache write$0.75 / 1M tokens
Cache write (1 hour)$1.2 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-4.6Official profile verified

Claude Opus 4.6 is Anthropic's high-end reasoning and multimodal model for complex scientific, engineering, legal, and accuracy-first professional work.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
A
claude-sonnet-4.6Official profile verified

Claude Sonnet 4.6 is Anthropic's balanced model for everyday coding, analysis, and content work, combining near-Opus capability with controlled cost and a 1M context window.

View model
defaultx1
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
Cache write$3.75 / 1M tokens
Cache write (1 hour)$6 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
A
claude-haiku-4-5-70%Official profile verified

Claude Haiku 4.5 is Anthropic's compact model for low latency and scaled use, suited to real-time interaction, classification, extraction, and routine automation.

View model
defaultx1
base
Input$1 / 1M tokens
Output$5 / 1M tokens
Cache read$0.1 / 1M tokens
Cache write$1.25 / 1M tokens
Cache write (1 hour)$2 / 1M tokens
discountx0.8
base
Input$0.8 / 1M tokens
Output$4 / 1M tokens
Cache read$0.08 / 1M tokens
Cache write$1 / 1M tokens
Cache write (1 hour)$1.6 / 1M tokens
relayx0.3
base
Input$0.3 / 1M tokens
Output$1.5 / 1M tokens
Cache read$0.03 / 1M tokens
Cache write$0.375 / 1M tokens
Cache write (1 hour)$0.6 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-haiku-4-5-20251001-70%Official profile verified

Claude Haiku 4.5 is Anthropic's compact model for low latency and scaled use, suited to real-time interaction, classification, extraction, and routine automation.

View model
defaultx1
base
Input$1 / 1M tokens
Output$5 / 1M tokens
Cache read$0.1 / 1M tokens
Cache write$1.25 / 1M tokens
Cache write (1 hour)$2 / 1M tokens
discountx0.8
base
Input$0.8 / 1M tokens
Output$4 / 1M tokens
Cache read$0.08 / 1M tokens
Cache write$1 / 1M tokens
Cache write (1 hour)$1.6 / 1M tokens
relayx0.3
base
Input$0.3 / 1M tokens
Output$1.5 / 1M tokens
Cache read$0.03 / 1M tokens
Cache write$0.375 / 1M tokens
Cache write (1 hour)$0.6 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-haiku-4.5Official profile verified

Claude Haiku 4.5 is Anthropic's compact model for low latency and scaled use, suited to real-time interaction, classification, extraction, and routine automation.

View model
defaultx1
base
Input$1 / 1M tokens
Output$5 / 1M tokens
Cache read$0.1 / 1M tokens
Cache write$1.25 / 1M tokens
Cache write (1 hour)$2 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
A
claude-opus-4-5-70%Official profile verified

Claude Opus 4.5 is the high-capability flagship of the Claude 4.5 generation for difficult reasoning, coding, and visual understanding.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
discountx0.8
base
Input$4 / 1M tokens
Output$20 / 1M tokens
Cache read$0.4 / 1M tokens
Cache write$5 / 1M tokens
Cache write (1 hour)$8 / 1M tokens
relayx0.3
base
Input$1.5 / 1M tokens
Output$7.5 / 1M tokens
Cache read$0.15 / 1M tokens
Cache write$1.875 / 1M tokens
Cache write (1 hour)$3 / 1M tokens
openaianthropicOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-4-5-20251101-70%Official profile verified

Claude Opus 4.5 is the high-capability flagship of the Claude 4.5 generation for difficult reasoning, coding, and visual understanding.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
relayx0.3
base
Input$1.5 / 1M tokens
Output$7.5 / 1M tokens
Cache read$0.15 / 1M tokens
Cache write$1.875 / 1M tokens
Cache write (1 hour)$3 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-4-6-70%Official profile verified

Claude Opus 4.6 is Anthropic's high-end reasoning and multimodal model for complex scientific, engineering, legal, and accuracy-first professional work.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
discountx0.8
base
Input$4 / 1M tokens
Output$20 / 1M tokens
Cache read$0.4 / 1M tokens
Cache write$5 / 1M tokens
Cache write (1 hour)$8 / 1M tokens
relayx0.3
base
Input$1.5 / 1M tokens
Output$7.5 / 1M tokens
Cache read$0.15 / 1M tokens
Cache write$1.875 / 1M tokens
Cache write (1 hour)$3 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-4-7-70%Official profile verified

Claude Opus 4.7 is Anthropic's high-capability model for complex software engineering, multi-step agents, and high-resolution visual documents, with 1M context and task budgets.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
discountx0.8
base
Input$4 / 1M tokens
Output$20 / 1M tokens
Cache read$0.4 / 1M tokens
Cache write$5 / 1M tokens
Cache write (1 hour)$8 / 1M tokens
relayx0.3
base
Input$1.5 / 1M tokens
Output$7.5 / 1M tokens
Cache read$0.15 / 1M tokens
Cache write$1.875 / 1M tokens
Cache write (1 hour)$3 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-4-8-70%Official profile verified

Claude Opus 4.8 is Anthropic's model for complex agentic coding and enterprise work, with adaptive thinking enabled.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
discountx0.8
base
Input$4 / 1M tokens
Output$20 / 1M tokens
Cache read$0.4 / 1M tokens
Cache write$5 / 1M tokens
Cache write (1 hour)$8 / 1M tokens
relayx0.3
base
Input$1.5 / 1M tokens
Output$7.5 / 1M tokens
Cache read$0.15 / 1M tokens
Cache write$1.875 / 1M tokens
Cache write (1 hour)$3 / 1M tokens
AA index 56anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-opus-4.5Official profile verified

Claude Opus 4.5 is the high-capability flagship of the Claude 4.5 generation for difficult reasoning, coding, and visual understanding.

View model
defaultx1
base
Input$5 / 1M tokens
Output$25 / 1M tokens
Cache read$0.5 / 1M tokens
Cache write$6.25 / 1M tokens
Cache write (1 hour)$10 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
A
claude-sonnet-4-5-70%Official profile verified

Claude Sonnet 4.5 is the balanced Claude 4.5 model for enterprise retrieval, coding, data analysis, and scaled agent work.

View model
defaultx1
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
Cache write$3.75 / 1M tokens
Cache write (1 hour)$6 / 1M tokens
discountx0.8
base
Input$2.4 / 1M tokens
Output$12 / 1M tokens
Cache read$0.24 / 1M tokens
Cache write$3 / 1M tokens
Cache write (1 hour)$4.8 / 1M tokens
relayx0.3
base
Input$0.9 / 1M tokens
Output$4.5 / 1M tokens
Cache read$0.09 / 1M tokens
Cache write$1.125 / 1M tokens
Cache write (1 hour)$1.8 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-sonnet-4-5-20250929-70%Official profile verified

Claude Sonnet 4.5 is the balanced Claude 4.5 model for enterprise retrieval, coding, data analysis, and scaled agent work.

View model
defaultx1
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
Cache write$3.75 / 1M tokens
Cache write (1 hour)$6 / 1M tokens
relayx0.3
base
Input$0.9 / 1M tokens
Output$4.5 / 1M tokens
Cache read$0.09 / 1M tokens
Cache write$1.125 / 1M tokens
Cache write (1 hour)$1.8 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-sonnet-4-6-70%Official profile verified

Claude Sonnet 4.6 is Anthropic's balanced model for everyday coding, analysis, and content work, combining near-Opus capability with controlled cost and a 1M context window.

View model
defaultx1
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
Cache write$3.75 / 1M tokens
Cache write (1 hour)$6 / 1M tokens
discountx0.8
base
Input$2.4 / 1M tokens
Output$12 / 1M tokens
Cache read$0.24 / 1M tokens
Cache write$3 / 1M tokens
Cache write (1 hour)$4.8 / 1M tokens
relayx0.3
base
Input$0.9 / 1M tokens
Output$4.5 / 1M tokens
Cache read$0.09 / 1M tokens
Cache write$1.125 / 1M tokens
Cache write (1 hour)$1.8 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare
A
claude-sonnet-4.5Official profile verified

Claude Sonnet 4.5 is the balanced Claude 4.5 model for enterprise retrieval, coding, data analysis, and scaled agent work.

View model
defaultx1
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
Cache write$3.75 / 1M tokens
Cache write (1 hour)$6 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
A
claude-3-5-sonnet-20241022-70%

Claude model by Anthropic for general chat, writing, coding assistance, and tool-assisted workflows.

View model
relayx0.3
base
Input$0.9 / 1M tokens
Output$4.5 / 1M tokens
Cache read$0.09 / 1M tokens
Cache write$1.125 / 1M tokens
Cache write (1 hour)$1.8 / 1M tokens
anthropicopenaiOpenAI compatibleAnthropic compatiblePrompt cacheCompare