Skip to content
➜NextOS

OpenAI
in NextOS.

Reasoning, tool calling, server-side web search with citations, a Python sandbox.

Use OpenAIGet an API key

01Supported models

Every model
this plugin lists.

  • gpt-5.6-sol

    GPT-5.6 Sol (most capable)

    272K contexttools

    Flagship for complex professional work. Budgeted at 272,000 to stay under the 1,050,000-window long-context surcharge.

  • gpt-5.6-terra

    GPT-5.6 Terra (balanced)

    272K contexttools

    Mid tier, the successor to the old "mini" slot. Same 272,000 budget as Sol.

  • gpt-5.6-luna

    GPT-5.6 Luna (fastest, cheapest)

    272K contexttools

    Cost-optimised for high volume; same window and surcharge shape as the rest of the 5.6 family.

  • gpt-6-astra

    GPT-6 Astra (frontier)

    272K contexttools

    Frontier model, and the priciest here. Takes reasoning effort 'low' and above - not 'none'.

  • gpt-5.1

    GPT-5.1 (previous flagship)

    400K contexttools

    Cheap and well understood, with the real 400,000 window budgeted in full. Takes reasoning effort 'none', 'low', 'medium' and 'high' only. A safe default model.

  • gpt-4o-mini

    GPT-4o mini (legacy, non-reasoning)

    128K contexttools

    No reasoning tokens at all - the fastest entry, kept for agents that already reference it.

02Bring your own key, or hosted

How you
pay for it.

OpenAI runs bring-your-own-key only: add your key in Settings > API keys, or send it per-request over the gateway.

  • Full tool calling - agents can use every app and MCP tool through this provider
  • No provider-hosted web search
  • No provider-hosted URL fetch

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-openai-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-5.6-sol","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 OpenAI.
Governed exactly like every other provider.

Set your defaultSee pricing