
By Anthropic
Anthropic — The official Python library for the anthropic API. Listed under Large language models in the Model / Foundation layer. 4 of 10 comparison attributes are recorded, each with the page it was read from.
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
2 OF 4 SIGNALS HELD · MISSING LICENCE, REPOSITORY
What it runs on, and what runs on it
46 cited edgesComputed from the stack graph, both directions. Every cited edge links the page it was read from; a vendor-added one links the vendor’s own source — this is the reason to be here rather than on the vendor’s own site.
RUNS ON / INTEGRATES WITH
- nothing recorded
USED BY
- agentic_securityintegrates with sourceJSON
- agnointegrates with source
- Apache Airflowintegrates with sourceJSON
- Arize Phoenixintegrates with source
- camelintegrates with sourceJSON
- crewaiintegrates with source
- dataarc-syndata-toolkitintegrates with sourceJSON
- deepevalintegrates with sourceJSON
- eccintegrates with sourceJSON
- failproofaiintegrates with sourceJSON
- fast-agentintegrates with sourceJSON
- garakintegrates with sourceJSON
- gpt_academicintegrates with sourceJSON
- gptmeintegrates with sourceJSON
- Griptapeintegrates with source
- Guardrails AIintegrates with source
- headroomintegrates with sourceJSON
- HoneyHiveintegrates with source
- judgevalintegrates with sourceJSON
- khojintegrates with sourceJSON
- lightragintegrates with sourceJSON
- litellmintegrates with sourceJSON
- loushangintegrates with sourceJSON
- miroflowintegrates with sourceJSON
- oh-my-claudecodeintegrates with sourceJSON
- open-coworkintegrates with sourceJSON
- pageindexintegrates with sourceJSON
- paritok-4b-v1integrates with sourceJSON
- pentestgptintegrates with sourceJSON
- Promptfoointegrates with sourceJSON
- Pydantic AIintegrates with sourceJSON
- python-sdkintegrates with sourceJSON
- ragflowintegrates with sourceJSON
- Semantic Kernelintegrates with source
- serenaintegrates with sourceJSON
- skill_seekersintegrates with sourceJSON
- synthadocintegrates with sourceJSON
- vllmintegrates with sourceJSON
- waku-agentintegrates with sourceJSON
- Weights & Biases Weaveintegrates with source
- Arize Phoenixrequires source
- garakrequires source
- Lettarequires source
- Promptfoorequires source
- SGLangrequires source
- vllmrequires source
Agentic surface
24 integrationsMCP servers and agent skills that name Anthropic as their official vendor, or that mention wrapping it. Unverified means a mention in the tool’s own description, not a citation.
- academy-guideAgent skillwraps
- awesome-agent-skills-mcpMCP serverwraps
- brand-guidelinesAgent skillwraps
- brand-guidelinesAgent skillwraps
- claude-apiAgent skillwraps
- computer-control-mcpMCP serverwraps
- engramMCP serverwraps
- inoyu-mcp-unomi-serverMCP serverwraps
- jira-pilotMCP serverwraps
- llm-securityAgent skillwraps
- mcp-coingecko-serverMCP serverwraps
- mcp-jenkinsMCP serverwraps
- mcp-server-claude-chatMCP serverwraps
- mcp-server-semgrepMCP serverwraps
- MCP2LambdaMCP serverwraps
- mcpFirebirdMCP serverwraps
- migrateAgent skillwraps
- mobile-device-mcpMCP serverwraps
- pbs-mcp-serverMCP serverwraps
- prismix-status-mcpMCP serverwraps
- slop-evalMCP serverwraps
- sperax-crypto-mcpMCP serverwraps
- TruthRouteMCP serverwraps
- unified-ai-systemMCP serverwraps
Open-source signals
A HOLLOW RING IS UNMEASURED, NOT ZERO · WE DO NOT SUBSTITUTE A PARENT COMPANY’S REPOSITORY FOR A PRODUCT THAT HAS NONE
Price
READINGS OVER 21 DAYS OLD ARE HIDDEN RATHER THAN SHOWN STALE, SO THIS TABLE CAN EMPTY OUT BETWEEN READS · MOVED COMPARES THE CHEAPEST READING WE TOOK ON EACH DAY, WHICH ON A MARKETPLACE IS A DIFFERENT HOST FROM THE ONE PRICED BESIDE IT — BOTH ENDS ARE SHOWN SO NOTHING HAS TO BE INFERRED · A MOVE IS A CHANGE IN OUR READING, WHICH IS NOT ALWAYS A CHANGE IN THE MARKET: A CORRECTED EXTRACTOR MOVES THE SERIES WITHOUT THE PRICE MOVING
Configurations
Anthropic publishes no machine-readable catalogue of its instance types, so no configurations are recorded. The prices above were read from its pricing page; a configuration read the same way would be a guess about how many GPUs a price covers, which is the mistake this section exists to avoid.
CONFIGURATIONS ARE TAKEN ONLY FROM A VENDOR’S OWN CATALOGUE API · IF YOU WORK HERE AND PUBLISH ONE, TELL US AND IT WILL BE READ
What its categories ask
4 answered · 6 unanswered10 questions declared by Large language models. Most rows across the directory read like these.
“All current models support text and image input, text output, multilingual capabilities, vision, and tool use.”2026-10-06
“Guarantee schema conformance with two approaches: JSON outputs for structured data responses, and strict tool use for validated tool inputs.”2026-09-29
A ROW WITH NO ANSWER IS NOT A ROW WITH A “NO” · A VENDOR MAY ANSWER A BLANK ONE, MARKED VENDOR CLAIMED WITH ITS SOURCE · A DOCUMENTED VALUE IS DISPUTED, NOT OVERWRITTEN, AND STAYS VISIBLE WHILE WE RE-READ THE SOURCE
Practitioner reviews
Nobody has written one yet.
A review here is structured, not a star: hardware, scale band, what broke in production, and whether you would choose it again.
NO PERCENTAGE IS SHOWN UNDER FIVE REVIEWS · NO STAR RATINGS, EVER
Also in this category
40 products in Large language models. Comparison defaults to within the category — pairing this with a GPU cloud would produce a page that means nothing.
USED BY = LISTED PRODUCTS DEPENDING ON IT, IN THIS DIRECTORY
Frequently asked
How much does Anthropic charge for anthropic/claude-haiku-5.5?
Does Anthropic offer structured output?
How current are Anthropic's prices here?
What does a blank mean on the Anthropic page?
Where do the Anthropic figures come from?
Can Anthropic change what this page says?
Something here is wrong — how do I fix it?
Is this listing run by Anthropic?
Cite this page
A model that quotes us should quote us correctly. The reading and its date sit inside the citation rather than beside it, because a quotation carrying only a URL goes wrong the week the URL changes.
infratoapp, “Anthropic — Large language models”, read 22 October 2026. Price $10.00/token-1m-in as published at platform.claude.com. https://www.infratoapp.com/products/anthropic
What Anthropic can and cannot change here
Claiming Anthropic lets its admins and editors change the tagline, description, logo, docs link and deployment model of every product that org owns — live, labelled as theirs, and logged. Answers to blank questions and dependencies go live too, marked as the owner’s and sourced; a documented answer cannot be overwritten. Everything else on this page is a stated fact with a dispute route: price, licence and OSS figures. Those columns are ungranted at the database level, so they are not a feature we withheld — they are a write that cannot happen. Name, category, website, pricing page and package names can be changed by the owner only through our review. A dispute never deletes a value; it marks it and publishes the correction.