Skip to main content
Core.Today
|
AnthropicMediumUltra

Claude Opus 4.7

Anthropic's latest flagship model with reliable knowledge cutoff to January 2026 and 128K max output tokens. Builds on Opus 4.6 with improved reasoning, coding, and instruction-following while staying compatible with the Anthropic Messages and OpenAI Chat Completions formats.

5 credits
per 1K tokens (avg)
Most capable Anthropic model
200K context window
128K max output tokens
Knowledge cutoff: January 2026
Vision and tool use
Streaming support

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

Model Specifications

Context Window
200K
tokens
Max Output
128K
tokens
Training Cutoff
2026-01
Compatible SDK
Anthropic, OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens10,000$10.00
Output Tokens50,000$50.00

* 1 credit โ‰ˆ $0.001 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-opus-4-7",
  "messages": [
    {
      "role": "system",
      "content": "You are a principal research analyst. Provide rigorous, source-aware analysis."
    },
    {
      "role": "user",
      "content": "Compare the safety and capability trade-offs of frontier closed-weight models versus open-weight alternatives for enterprise deployment in 2026, with mitigations."
    }
  ],
  "max_tokens": 8000
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects (OpenAI format)
max_tokensintegerNo4096Maximum tokens in response (up to 128000)
streambooleanNofalseEnable Server-Sent Events streaming

Examples

Long-form Analysis

Deep multi-step analysis with Claude Opus 4.7

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-opus-4-7",
  "messages": [
    {
      "role": "system",
      "content": "You are a principal research analyst. Provide rigorous, source-aware analysis."
    },
    {
      "role": "user",
      "content": "Compare the safety and capability trade-offs of frontier closed-weight models versus open-weight alternatives for enterprise deployment in 2026, with mitigations."
    }
  ],
  "max_tokens": 8000
}'

Production Code Generation

Generate production-ready code with full reasoning

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-opus-4-7",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Write clean, well-tested, production code."
    },
    {
      "role": "user",
      "content": "Implement a distributed rate limiter in Go using Redis Cluster with the leaky bucket algorithm. Include unit tests."
    }
  ],
  "max_tokens": 6000
}'

Tips & Best Practices

1Most capable Anthropic model โ€” pick this for the hardest reasoning tasks
2128K output enables long-form drafts in a single response
3`temperature` is deprecated for this model โ€” omit it from your request body (Anthropic returns 400 if sent)
4Streaming recommended for long responses
5Compatible with both Anthropic Messages and OpenAI SDK formats

Use Cases

Frontier research and analysis
Long-form writing up to 128K tokens
Advanced code generation and refactoring
Multi-step agentic workflows
Enterprise-grade reasoning tasks