Claude Platform | Claude (original) (raw)
Build on the Claude Platform
Use our API to create new user experiences, products, and ways to work with the most advanced AI models on the market.
"Claude Fable 5 is the state of the art model on CursorBench. It's opened up a class of long-horizon problems that were out of reach for earlier models."
Michael Truell, CEO and Co-founder
“The decision to choose Claude was entirely data-driven. We tested multiple model providers side by side, and Claude consistently delivered the best results for case resolution rates and customer satisfaction scores.”
Timothy Addison, Engineering Org Chief of Staff
"Claude Fable 5 came out #1 on our evals, winning head-to-head against every model we tested. It was significantly stronger on the hardest tasks in the set — UI design and game coding."
Kay Zhu, Co-founder & CTO
“The partnership with Anthropic has been exceptional—their guidance and support have helped our engineering teams maximize the models.”
"Claude Fable 5 is the highest-scoring model on FrontierBench, Cognition's frontier coding eval. It excels at long-horizon reasoning and generalizes to unfamiliar tools out of the box."
“Claude Opus 4.8 sets a new bar for enterprise AI. In Genie, Databricks' AI agent for data and knowledge work, the new Opus model unlocks a step change in agentic reasoning, tackling deeper, multi-step questions faster than any prior Opus. Its multimodal strength also lets Genie reason directly over PDFs, diagrams, and other unstructured content at 61% cheaper token cost than Opus 4.7.”
Hanlin Tang, CTO - Neural Networks
"On ViBench, our end-to-end vibe-coding benchmark, Claude Fable 5 is the highest-performing model we've tested — nearly saturating our base use cases and building apps in less time with fewer tokens."
Michele Catasta, President & Head of AI
“On our long-running evals, Claude Opus 4.8’s analysis was consistently higher quality than prior Opus models. It finished faster and produced richer, more information dense outputs. Overall, a noticeably better signal to noise ratio. The biggest differentiator was Opus 4.8’s tendency to proactively flag issues with the inputs and outputs of an analysis, something other models routinely missed and left to the users to catch.”
Michael Ran, Sr. Investment Associate
"Claude Fable 5 is the strongest finance-first model we've tested, both on general finance and reasoning. It's a notable step up."
Damian Miraglia, Principal Engineer, Applied AI
“With Claude, we’re not just automating customer service—we’re elevating it to truly human quality. This lets support teams think more strategically about customer experience and what makes interactions genuinely valuable.”
"Claude Fable 5 is the new leader on AutomationBench, consistently higher than Opus 4.8 — and more autonomous. Where Opus stops to ask, Fable 5 keeps looking."
Build on your own
Launch your own generative AI solution with:
- Access to all Claude models
- Usage-based tiers
- Automatically increasing rate limits
- Simple pay-as-you-go pricing
- Self-serve deployment on workbench
- Prompting guides and developer docs
Get extra support
Need custom rate limits or hands-on help? Contact our sales team for:
- Anthropic-supported onboarding
- Custom rate limits
- Billing via monthly invoices
- Prompting support
- Deployment support
Right-sized for any task, our models offer the best combination of speed and performance.
Fable 5
Next generation intelligence for long-running agents
Claude Fable 5 is unavailable. Learn more
Opus 4.8
Ideal for complex agentic coding and enterprise work
Sonnet 4.6
Optimal balance of intelligence, cost, and speed
Haiku 4.5
Fastest, most cost-effective model
For workloads that need to run in the US, US-only inference is available at 1.1x pricing for input and output tokens. Learn more.
Get up to 2.5x faster speeds with fast mode for Opus 4.8 at 2x standard pricing. Learn more.
Prompt caching pricing reflects 5-minute TTL. Learn about extended prompt caching.
Claude Managed Agents
A suite of composable APIs for building and deploying agents at scale.
Prompt caching
Give Claude more background knowledge and example outputs to reduce costs and latency.
Web search and fetch
Augment Claude’s knowledge with current, real-world data from across the web.
Advanced tool use
Allow Claude to interact with hundreds of external tools and APIs so it can perform a wider range of tasks.
Batch processing
Process large volumes of requests asynchronously and save 50% on costs.
Memory
Let Claude store and consult information from a dedicated memory file.
Context editing
Automatically clear less relevant tool calls and results from the context window when approaching token limits.
MCP connector
Connect Claude to any remote MCP server without writing client code.
Code execution
Run Python code, create visualizations, and analyze data directly within API calls.
Citations
Get detailed references to the exact sentences and passages Claude uses to generate responses, leading to more verifiable, trustworthy outputs.
Files API
Upload documents once and reference them repeatedly across conversations.
Skills
Teach Claude your expertise, procedures, and best practices so it delivers consistent, expert-level results.
Structured outputs
Ensure Claude's responses conform to your JSON schema.
Explore Claude’s advanced features and capabilities.
Integrate Claude’s powerful AI capabilities into your apps and deliver production-grade solutions faster.
You are an AI assistant specialized in classifying customer support tickets. Your task is to analyze the content of a given ticket and assign it to the most appropriate category from a predefined list. You will also provide reasoning for your classification decision.
First, let's review the available categories:
<category_list>
{{CATEGORY_LIST}}
</category_list>
Now, here is the content of the support ticket you need to classify:
<ticket_content>
{{TICKET_CONTENT}}
</ticket_content>
Please follow these steps to complete the task:
– Carefully read and analyze the ticket content.
– Consider how the content relates to each of the available categories.
– Choose the most appropriate category for the ticket.
– Provide a detailed explanation of your reasoning process.
Use the following structure for your response:
<classification_analysis>
In this section, break down your thought process:
– Quote the most relevant parts of the ticket content.
– List each category and note how it relates to the ticket content.
– For each category, provide arguments for and against classifying the ticket into that category.
– Rank the top 3 most likely categories.
</classification_analysis>
Remember to be thorough in your analysis and clear in your explanation. Your goal is to provide an accurate classification with well-supported reasoning.
Built for developers
Build, test, and iterate on your deployment:
- Automatically generate or improve existing prompts
- Evaluate model responses against real-world scenarios
- Build faster with pre-built cookbooks and guides
Coding
Our models are constantly improving on coding, math, and reasoning. Claude can complete complex engineering tasks to solve problems that would typically take a full day of engineering work.
Agents
Claude offers superior instruction following, tool selection, error correction, and advanced reasoning for customer-facing agents and complex AI workflows.
Productivity
Claude can extract relevant information from business emails and documents, categorize and summarize survey responses, and wrangle reams of text with high speed and accuracy.
Customer support
Claude can handle ticket triage, on-demand complex inquiries using rich context awareness, and multi-step support workflows—all with a casual tone and conversational responses.
Start building
Get the developer newsletter
Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.
Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time.
Thank you! You’re subscribed.
Sorry, there was a problem with your submission, please try again later.