#API の記事
5 記事
-
Claude
What Is Claude Sonnet 4.6 | Specs, Capabilities, and Differences from Opus
A breakdown of Claude Sonnet 4.6's official specs and features. Model ID is claude-sonnet-4-6, context window is 1M tokens, with support for both Extended Thinking and Adaptive Thinking. Covers comparisons with Opus 4.8 and Haiku 4.5, 300K output via Batch API, and how to use it on AWS Bedrock and Vertex AI — all from primary sources.
-
Claude
Vertex AI Claude Pricing | Opus/Sonnet Rates & Bedrock Comparison
A breakdown of Claude pricing via Vertex AI, model by model. Covers the same rate structure as the Anthropic direct API, the 10% premium for regional endpoints, and discounts available through Batch API and Prompt Caching.
-
Claude
How to Use Claude Web Search | claude.ai Settings, API Pricing, and Citations
A comprehensive guide to Anthropic's web search feature for both claude.ai and the API. Covers how to toggle it from the slider, supported models, the $10/1,000 searches pay-as-you-go pricing, domain filters, citation display, and the dynamic filtering available in Opus 4.7 — all based on official documentation.
-
Claude
Can Claude Run Locally? Differences from Local LLMs and Alternatives
Claude cannot be run as a local LLM — here's why, and what to do instead. We cover purpose-specific alternatives for protecting sensitive data, offline use, and cost reduction, including open-weight models and the API's Zero Data Retention option.
-
Claude
Bedrock Claude Pricing | Per-Token Rates and Cost Reduction for Opus, Sonnet, and Haiku
A breakdown of Claude pricing on Amazon Bedrock by model — Opus 4.x, Sonnet 4.6, and Haiku 4.5 — covering per-token rates, the difference between global and regional endpoints, Prompt Caching, 50% Batch API discounts, a comparison with Claude Platform on AWS pricing, and four practical cost-reduction strategies.