Skip to content

Meet DeepintShield at Bengaluru Tech Summit 2026, 17 to 19 November, BIEC Hall 1, booth H1A106. Book 20 minutes

Start For Free

Anthropic

Claude chat and Responses with thinking, prompt caching, files and batch.

Route Claude models through DeepintShield with your own Anthropic key, from OpenAI-compatible clients or the native Anthropic SDK.

What works

  • Chat Completions and the Responses API, both with streaming
  • Legacy text completions (/v1/complete, no streaming)
  • Files, batch and list models
  • Tools, images by URL or base64, prompt caching with cache_control, and reasoning (thinking)

Limits to know: No embeddings, speech, transcription or image generation, because the upstream Anthropic API does not offer them. A manual reasoning budget must be at least 1,024 tokens. The gateway marks static prompt prefixes for caching, with a 5-minute TTL by default or 1 hour.

How to connect

Add your Anthropic key in Model Hub → AI Providers, create a Virtual Key, then call anthropic/<model> through https://app.deepintshield.com/v1 with any OpenAI-compatible client, or keep native Messages code with the Anthropic SDK integration.

Read the Anthropic provider docs. Requests get the same Virtual Key budgets, guardrails and logs as every other provider on the AI gateway.

Read the integration docs

Start For Free