Tools · SPBoucher
Menu

Claude Platform

In-depth entry

by Anthropic · Platform · also known as Claude Developer Platform, Anthropic API, Claude API, Claude Console, Anthropic Console

Anthropic's developer platform for the Claude models: Messages API, tool use, structured outputs, prompt caching, batch processing and Managed Agents, plus cloud availability

ProprietaryUsage-basedEnterpriseCloud
Visit official site Compare

Link verified Nov 2, 2026

Overview

The Claude Platform is Anthropic's hosted API and console for building with the Claude model family. It was previously documented at docs.anthropic.com and docs.claude.com; both now redirect to platform.claude.com, where the console (API keys, workspaces, usage analytics, playground) and the documentation live together. The platform is cloud-only and usage-billed, and the same models are also sold through Amazon Bedrock, Google Cloud and Microsoft Foundry for teams that prefer to buy through an existing cloud account.

The core surface is the Messages API: the caller supplies the conversation, and Claude returns text, tool calls or structured JSON. Around it sit extended thinking, vision input, tool use with server-side tools (web search, code execution), structured outputs, prompt caching to reduce the cost of repeated context, streaming, batch processing for asynchronous workloads, the Files API and usage and cost analytics endpoints. A second surface, Managed Agents (beta), runs long-lived agents in stateful sessions with persistent event history, tool permission policies and orchestration handled by Anthropic rather than the caller. Official client libraries cover Python, TypeScript, Go, Java, Ruby, PHP and C#, and a command-line client (ant) is documented alongside them. Claude Code and the Agent SDK build on this platform but are documented separately.

Typical users are application teams adding assistant, extraction or agent features, and research groups running large batch jobs. Limits are the usual ones for a proprietary hosted API: there is no self-hosted option, model versions are retired on a published schedule, rate limits are tiered by spend, and data handling follows Anthropic's commercial terms rather than the consumer privacy policy.

Editorial note on uncertainty. Anthropic's own pages call the product "Claude Platform"; "Claude Developer Platform" is kept as an alias because it was used in earlier documentation and in this encyclopedia's slug.

Capabilities

  • Messages API with streaming, vision input and extended thinking
  • Tool use including server-side web search and code execution tools
  • Structured outputs validated against a JSON schema
  • Prompt caching and batch processing for cost control
  • Managed Agents (beta) with stateful sessions and permission policies
  • Workspaces, API keys and usage/cost analytics in the console
  • Client SDKs for Python, TypeScript, Go, Java, Ruby, PHP and C#, plus a CLI
  • Availability through Amazon Bedrock, Google Cloud and Microsoft Foundry

Typical workflows

  1. Prototype a prompt in the console playground, then call it from an SDK
  2. Build an agent loop with tool use and structured outputs
  3. Run nightly document-extraction jobs through the Batch API with cached system prompts
  4. Deploy a long-running agent with Managed Agents instead of hosting the loop yourself

Strengths

  • One documentation and console site after the 2025–2026 consolidation
  • Same models purchasable through three major clouds
  • Prompt caching and batch tiers make large workloads cheaper to operate
  • Broad official SDK coverage

Limitations

  • Cloud-only; no on-premises deployment
  • Model deprecation schedule requires periodic migration
  • Rate limits scale with spend tier and may constrain new accounts
  • Managed Agents is in beta and subject to change

Prerequisites

  • Anthropic console account with billing or a cloud marketplace subscription
  • An HTTP client or one of the official SDKs

Who it is for

  • Application developers integrating Claude
  • Agent and automation builders
  • Researchers running large batch analyses

Alternatives & comparison

The OpenAI API and Gemini API are the direct counterparts; all three expose chat-style endpoints with tool calling, structured outputs, caching and batch modes, but with different schemas, so a gateway such as LiteLLM or OpenRouter is often used to abstract them. Anthropic's Managed Agents parallels OpenAI's managed Agents API. Unlike Mistral AI, Anthropic does not publish open-weight models, so self-hosting is not an option.

  • Cohere

    Enterprise-focused model provider with Command generation, Embed and Rerank retrieval models, Aya multilingual research models, the North agent platform and private or dedicated deployment options

    ProprietaryFreemium
  • Foundation Models (Apple)

    Apple's Swift framework giving apps access to the on-device Apple Intelligence language model with guided generation, tool calling and sessions, on OS 26 and later

    ProprietaryFree
  • Gemini API

    Google's developer API for the Gemini model family, keyed from Google AI Studio, with function calling, Search grounding, Live API, image and video generation and a free tier

    ProprietaryFreemium
  • Mistral AI

    French model provider offering open-weight and proprietary models through the Studio API, OCR and speech models, the Vibe agent for productivity and coding, and self-deployment options

    MixedFreemium
  • OpenAI API

    OpenAI's hosted developer platform: Responses and Chat Completions APIs, Realtime voice, embeddings, images, audio, fine-tuning, evals and managed agents

    ProprietaryUsage-based
  • OpenRouter

    Unified API gateway to hundreds of models from many providers with automatic fallbacks, credit-based pass-through billing, BYOK, free models and data-policy routing

    ProprietaryFreemium
Compare Claude Platform with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

Confidence
High
Reviewed
Nov 1, 2026
Links
Verified · Nov 2, 2026

Spotted an error?

Broken link, outdated license, wrong category, or a tool that no longer exists? Tell us; reports are reviewed by the editor.

LiteLLM

BerriAI · Prompting, evaluation & observability

In-depth entry

Open-source Python SDK and self-hosted AI gateway that calls 100+ LLM providers in the OpenAI format, with routing, fallbacks, virtual keys, budgets, spend tracking and logging callbacks

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

Hugging Face Hub

Hugging Face · Training & fine-tuning

In-depth entry

Hosting platform for open models, datasets and Spaces demo apps built on git repositories and Xet storage, with Inference Providers, Endpoints, Jobs and an open-source Python client and CLI

MixedFreemiumPaidLocalNov 2, 2026

Together AI

Together AI · Model providers & APIs

Cloud platform for open-source models: serverless and dedicated inference, fine-tuning, GPU clusters, batch jobs and code sandboxes behind an OpenAI-compatible API

ProprietaryUsage-basedEnterpriseNov 2, 2026

Cohere

Cohere Inc. · Model providers & APIs

Enterprise-focused model provider with Command generation, Embed and Rerank retrieval models, Aya multilingual research models, the North agent platform and private or dedicated deployment options

ProprietaryFreemiumUsage-basedSelf-hostedNov 2, 2026

GroqCloud

Groq, Inc. · Model providers & APIs

Low-latency hosted inference API for open-weight models on Groq's LPU hardware, OpenAI-compatible, with speech-to-text, text-to-speech, tool use and batch tiers

ProprietaryUsage-basedEnterpriseNov 2, 2026