Skip to content

Anthropic
in NextOS.

Extended thinking, effort control, and Anthropic-hosted web search, web fetch and memory.

01Supported models

Every model
this plugin lists.

  • claude-opus-5

    Claude Opus 5 (most capable)

    1M contexttools

    1M context, 128k output, adaptive thinking on by default.

  • claude-sonnet-5

    Claude Sonnet 5 (balanced)

    1M contexttools

    1M context, 128k output, adaptive thinking on by default.

  • claude-haiku-4-5

    Claude Haiku 4.5 (fastest)

    200K contexttools

    200k context. No adaptive thinking or effort - set a thinking budget instead.

  • claude-opus-4-8

    Claude Opus 4.8

    1M contexttools

    1M context, 128k output. Thinking is off by default at the API; this plugin turns it on for every model that takes it.

  • claude-fable-5-1

    Claude Fable 5.1 (deepest reasoning, priciest)

    1M contexttools

    1M context, 128k output. Thinking is always on; runs the preserved-thinking history check.

02Bring your own key, or hosted

How you
pay for it.

The only provider the hosted allowance runs today (Pro and above) - every other provider is bring-your-own-key.

  • Full tool calling - agents can use every app and MCP tool through this provider
  • Provider-hosted web search available as a per-agent option
  • Provider-hosted URL fetch available as a per-agent option

03Governance

The same controls
as every provider.

  • Restrict which providers and models a team may use at all - an allowed list on the org policy, enforced on every gateway call
  • Set a default model the whole workspace inherits, with per-agent pins for the job that needs a different one
  • Per-org and per-key budgets and rate limits, checked before a call reaches the provider
  • Guardrails (PII redaction, prompt-injection screening) applied to every request and response, regardless of provider
  • A full audit trail of governance and budget events, in the team's activity log

04Over the gateway

One endpoint,
OpenAI-compatible.

gateway — next.os
curl https://jonkum.in/api/v1/chat/completions \
  -H "Authorization: Bearer ngk_..." \
  -H "X-Provider-Key: your-anthropic-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-opus-5","messages":[{"role":"user","content":"..."}]}'

Omit X-Provider-Key to run on the account's hosted allowance instead, where the plan supports it. See the gateway page for the full API.

05Every other provider

one plane · every provider · your key or ours

Run agents on Anthropic.
Governed exactly like every other provider.