Loading...
    • Developer Guide
    • API Reference
    • MCP
    • Resources
    • Release Notes
    Search...
    ⌘K
    First steps
    Intro to ClaudeQuickstart
    Models & pricing
    Models overviewChoosing a modelWhat's new in Claude 4.6Migration guideModel deprecationsPricing
    Build with Claude
    Features overviewUsing the Messages APIHandling stop reasonsPrompting best practices
    Model capabilities
    Extended thinkingAdaptive thinkingEffortFast mode (beta: research preview)Structured outputsCitationsStreaming MessagesBatch processingPDF supportSearch resultsMultilingual supportEmbeddingsVision
    Tools
    OverviewHow tool use worksTutorial: Build a tool-using agentDefine toolsHandle tool callsParallel tool useTool Runner (SDK)Strict tool useTool use with prompt cachingServer toolsTroubleshootingTool referenceWeb search toolWeb fetch toolCode execution toolMemory toolBash toolComputer use toolText editor tool
    Tool infrastructure
    Manage tool contextTool combinationsTool searchProgrammatic tool callingFine-grained tool streaming
    Context management
    Context windowsCompactionContext editingPrompt cachingToken counting
    Files & assets
    Files API
    Agent Skills
    OverviewQuickstartBest practicesSkills for enterpriseClaude API skillUsing Skills with the API
    Agent SDK
    OverviewQuickstartHow the agent loop works
    MCP in the API
    MCP connectorRemote MCP servers
    Claude on 3rd-party platforms
    Amazon BedrockMicrosoft FoundryVertex AI
    Prompt engineering
    OverviewConsole prompting tools
    Test & evaluate
    Define success and build evaluationsUsing the Evaluation ToolReducing latency
    Strengthen guardrails
    Reduce hallucinationsIncrease output consistencyMitigate jailbreaksStreaming refusalsReduce prompt leak
    Administration and monitoring
    Admin API overviewData residencyWorkspacesUsage and Cost APIClaude Code Analytics APIAPI and data retention
    Console
    Log in
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...
    Loading...

    Solutions

    • AI agents
    • Code modernization
    • Coding
    • Customer support
    • Education
    • Financial services
    • Government
    • Life sciences

    Partners

    • Amazon Bedrock
    • Google Cloud's Vertex AI

    Learn

    • Blog
    • Catalog
    • Courses
    • Use cases
    • Connectors
    • Customer stories
    • Engineering at Anthropic
    • Events
    • Powered by Claude
    • Service partners
    • Startups program

    Company

    • Anthropic
    • Careers
    • Economic Futures
    • Research
    • News
    • Responsible Scaling Policy
    • Security and compliance
    • Transparency

    Learn

    • Blog
    • Catalog
    • Courses
    • Use cases
    • Connectors
    • Customer stories
    • Engineering at Anthropic
    • Events
    • Powered by Claude
    • Service partners
    • Startups program

    Help and security

    • Availability
    • Status
    • Support
    • Discord

    Terms and policies

    • Privacy policy
    • Responsible disclosure policy
    • Terms of service: Commercial
    • Terms of service: Consumer
    • Usage policy
    Documentation

    July 2024 Updates

    July 28, 2024

    Welcome to our inaugural Developer Newsletter. Every few weeks, we'll share product updates, resources, and news for Anthropic developers.

    Product updates

    Claude Sonnet 3.5

    Claude Sonnet 3.5, our latest release, outperforms competitor models and Claude Opus 3 across a variety of evaluations while maintaining the speed and cost of our previous mid-tier model. Try it in the Claude Console Workbench or explore our API docs.

    3-5-sonnet-curve.png

    View blog

    Extended outputs for Claude Sonnet 3.5

    We've doubled the max output token limit for Claude Sonnet 3.5 from 4096 to 8192 in the API. To extend outputs, add this header to your calls: "anthropic-beta": "max-tokens-3-5-sonnet-2024-07-15".

    Workbench enhancements

    New features in the Claude Console Workbench:

    1. Prompt generator: Describe your task (e.g. "Triage inbound customer support requests") and have Claude generate a high-quality prompt for you.
    2. Evaluate mode: Compare the outputs of two or more prompts side by side and rate Claude's outputs on a 5-point scale.

    prompt-generator.png

    Read our blog post

    Usage and cost dashboards

    Track API usage and billing by dollar amount, token count, and API keys in the new Usage and Cost tabs in the Developer Console.

    Release notes

    We've added comprehensive release notes to our docs, covering updates across our API, Claude Console, and Claude apps.

    release-notes.png

    Developer Resources

    Revamped Anthropic Docs

    Our overhauled docs now include a prompt optimization guide and Claude-powered search.

    New educational courses

    Two free, self-serve courses available now:

    1. Claude API fundamentals: Master the basics of our API and SDKs.
    2. Tool use with Claude: Learn to connect Claude with external client-side tools and generate structured JSON outputs.

    tools-course.png

    Expanding Claude Cookbook

    New guides on core Claude skills: citations, retrieval augmented generation, and classification.

    Was this page helpful?

    • Claude Sonnet 3.5
    • Extended outputs for Claude Sonnet 3.5
    • Workbench enhancements
    • Usage and cost dashboards
    • Release notes
    • Revamped Anthropic Docs
    • New educational courses
    • Expanding Claude Cookbook