OpenAI setup

Compare OpenAI authentication methods to choose based on model access, hosted plugins, usage tracking, and permissions.

Getting started

API key (OpenAI Platform)

Best for: direct API access and usage-based billing.

Get your API key

Create or copy an API key from the OpenAI Platform dashboard.

Run onboarding

openclaw onboard --auth-choice openai-api-key

Or pass the key directly:

openclaw onboard --openai-api-key "$OPENAI_API_KEY"

Verify the model is available

openclaw models list --provider openai

Route summary

Config example

{
  env: { vars: { OPENAI_API_KEY: "example-openai-key-not-real" } },
  agents: { defaults: { model: { primary: "openai/gpt-6-astra" } } },
}

The bare direct-API gpt-5.6 alias is also accepted and resolves to the Sol tier. If this API organization does not expose GPT-5.6, set the primary to openai/gpt-5.5 explicitly.

To try ChatGPT's current Instant model from the OpenAI API, set the model to openai/chat-latest:

{
  env: { vars: { OPENAI_API_KEY: "example-openai-key-not-real" } },
  agents: { defaults: { model: { primary: "openai/chat-latest" } } },
}

chat-latest is a moving alias. Fresh OpenAI API-key setup instead uses openai/gpt-6-astra. The bare direct-API openai/gpt-5.6 alias remains supported and resolves to Sol. Existing explicit primaries, including openai/gpt-5.5, remain unchanged. The chat-latest alias only accepts medium text verbosity; OpenClaw forces any other requested verbosity to medium for this model.

Codex subscription

Best for: using your ChatGPT/Codex subscription with native Codex app-server execution instead of a separate API key. Codex cloud requires ChatGPT sign-in.

Run Codex OAuth

openclaw onboard --auth-choice openai

Or run OAuth directly:

openclaw models auth login --provider openai

For headless or callback-hostile setups, add --device-code to sign in with a ChatGPT device-code flow instead of the localhost browser callback:

openclaw models auth login --provider openai --device-code

Use the canonical OpenAI model route

openclaw config set agents.defaults.model.primary openai/gpt-6-astra

No runtime config is required for this exact official HTTPS native route. It may select the Codex app-server runtime automatically, and OpenClaw installs or repairs the bundled Codex plugin when that runtime is chosen.

Verify Codex auth is available

openclaw models list --provider openai

After the gateway is running, send /codex status or /codex models in chat to verify the native app-server runtime.

Route summary

Config example

{
  plugins: { entries: { codex: { enabled: true } } },
  agents: {
    defaults: {
      model: { primary: "openai/gpt-6-astra" },
    },
  },
}

With an API-key backup, keep the selected model under openai/* and put the auth order under openai. OpenClaw tries the subscription first, then the API key, while staying on the Codex harness:

{
  plugins: { entries: { codex: { enabled: true } } },
  agents: {
    defaults: {
      model: { primary: "openai/gpt-6-astra" },
    },
  },
  auth: {
    order: {
      openai: [
        "openai:[email protected]",
        "openai:api-key-backup",
      ],
    },
  },
}

Check and recover Codex OAuth routing

openclaw models status
openclaw models auth list --provider openai
openclaw config get agents.defaults.model --json
openclaw config get models.providers.openai.agentRuntime --json

For a specific agent, add --agent <id>:

openclaw models status --agent <id>
openclaw models auth list --agent <id> --provider openai

If an older config still has legacy Codex GPT refs, or a stale OpenAI runtime session pin without explicit runtime config, repair it:

openclaw doctor --fix
openclaw config validate

If models auth list --provider openai shows no usable profile, sign in again:

openclaw models auth login --provider openai
openclaw models status --probe --probe-provider openai

Use --profile-id for multiple Codex OAuth logins in the same agent, then control them via auth ordering or /model ...@<profileId> -s:

openclaw models auth login --provider openai --profile-id openai:ritsuko
openclaw models auth login --provider openai --profile-id openai:lain

Run openclaw doctor --fix to migrate older legacy OpenAI Codex prefix profile ids and order entries before relying on profile ordering.

Status indicator

Chat /status shows which model runtime is active for the current session. The bundled Codex app-server harness appears as Runtime: OpenAI Codex when an eligible implicit route or explicit provider/model runtime policy selects it.

Doctor warning

If legacy Codex model refs or stale OpenAI runtime pins remain in config or session state, openclaw doctor --fix rewrites them to openai/* with the Codex runtime unless OpenClaw is explicitly configured.

Context window defaults and long-context opt-in

OpenClaw treats native model capacity and the active runtime budget as separate values:

• contextWindow declares the model's native window.
• contextTokens caps how much of that window OpenClaw uses for active input.

ChatGPT/Codex OAuth follows the live Codex account catalog. The current catalog commonly advertises a 272000 token active window for GPT-5.6. Direct API-key GPT-5.5 and GPT-5.6 models also default to 272000 contextTokens, even though the Platform API exposes a larger native window. This keeps the normal latency, quality, and cost profile consistent across auth modes. Override a direct model's active-input budget with models.providers.openai.models[].contextTokens on that exact model entry.

For direct API-key GPT-5.5 and GPT-5.6, OpenAI documents a 1050000 token provider window and 128000 maximum output tokens. Reserving the full output allowance gives the shared safe input budget used by both runtime recipes below:

1050000 total - 128000 maximum output = 922000 safe active input
automatic compaction threshold = 700000 active tokens

922000 is a derived operating budget, not a separate provider-published input limit. The two runtimes translate that budget differently: embedded OpenClaw sends Responses compaction controls, while native Codex owns its catalog window and automatic compaction. See the official model comparison and GPT-5.5 model page.

Embedded OpenClaw translation

This example pins the exact Sol model to the embedded OpenClaw runtime, enables OpenAI API Fast mode through the shared runtime control, and asks OpenAI Responses to compact at 700000 active tokens:

{
  models: {
    providers: {
      openai: {
        models: [
          {
            id: "gpt-5.6-sol",
            name: "GPT-5.6 Sol",
            contextWindow: 1050000,
            contextTokens: 922000,
            maxTokens: 128000,
          },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "openai/gpt-5.6-sol" },
      models: {
        "openai/gpt-5.6-sol": {
          agentRuntime: { id: "openclaw" },
          params: {
            fastMode: true,
            responsesServerCompaction: true,
            responsesCompactThreshold: 700000,
          },
        },
      },
    },
  },
}

OpenAI Responses automatic compaction emits an encrypted compaction output item. A stateless client carries the newest item into the next request and may drop every earlier input item. OpenClaw persists that item opaquely, fences reuse by route, session, and auth, replays it, prunes the replaced prefix, carries it through worker transcript commits, and removes it from display and diagnostics. Never print, log, or expose the encrypted content.

A process-owned isolated-Gateway run on OpenClaw 2026.8.1 verified this exact openai/gpt-5.6-sol configuration. Dense turns reached 295098, 586562, and 863664 prompt tokens. Turn three emitted and persisted a first-class server compaction item; the next request replayed that exact opaque item, pruned its prefix, and used 9602 prompt tokens. A deterministic long response produced 5480 output tokens, durable markers survived compaction and Gateway restart, restart latency was 12081 ms, every call reported serviceTier: priority, and the full suite took 220.03 seconds. These timings are observations, not service-level guarantees.

Native Codex translation

Keep the same OpenClaw model selection, but make Codex the explicit runtime and do not add Responses compaction params to this model entry:

{
  agents: {
    defaults: {
      model: { primary: "openai/gpt-5.6-sol" },
      models: {
        "openai/gpt-5.6-sol": {
          agentRuntime: { id: "codex" },
          params: { fastMode: true },
        },
      },
    },
  },
}

Codex must receive 922000 for both context_window and max_context_window, 700000 for auto_compact_token_limit, and matching app-server overrides with model_auto_compact_token_limit_scope=total. Codex then applies its 95% effective-window reserve, yielding 875900 active tokens. Configure an ordered OpenAI API-key profile and keep the default isolated agent-scoped Codex home. The complete catalog, app-server, auth, and restart recipe is in Codex harness long context.

These examples are two explicit runtime choices, not one auto-selecting configuration. The model-scoped agentRuntime and runtime-owned compaction settings must change together. OpenClaw can retain both choices only when their model refs or agent configurations are distinguishable; otherwise, switch the model runtime and its matching config as one atomic change. Then restart the Gateway and native Codex app-server, run /model default -s, and start a fresh chat. Existing native Codex threads retain the provider and model recorded when they were created.

Catalog recovery

OpenClaw uses upstream Codex catalog metadata for gpt-5.5 when it is present. If live Codex discovery omits the gpt-5.5 row while the account is authenticated, OpenClaw synthesizes that OAuth model row so cron, sub-agent, and configured default-model runs do not fail with Unknown model.

Use Sign in with ChatGPT (SIWC) for app-specific authorization to spend your Codex allowance on eligible Responses API requests. Check shared allowance usage in ChatGPT Settings → Usage. OpenClaw does not show SIWC quota or per-app usage, and does not set per-app limits; ChatGPT may offer app-specific controls for your account.

Your account and workspace must have SIWC registration and token sharing enabled by OpenAI.

SIWC does not support OpenAI-hosted plugins or connected apps yet. Those require a Codex credential with connector invocation scope, which device-code login does not grant. OpenClaw tools and locally configured plugins can still use their own credentials. See OpenAI authentication to compare the methods.

Run this on the computer running OpenClaw:

openclaw models auth login --provider openai --method siwc

Approve token sharing during sign-in to enable model calls. If you grant identity permissions only, OpenClaw saves the account but asks you to enable sharing or choose another credential before inference.

The browser returns to http://localhost:8080/auth/callback. If your browser runs on another computer, forward its port 8080 to OpenClaw's IPv4 loopback before starting sign-in. For an SSH host, keep this command running on your browser's computer:

ssh -N -L 8080:127.0.0.1:8080 user@gateway-host

Open the sign-in link on that computer.

To reconnect an existing account, sign in with the same ChatGPT user and workspace. To switch either, choose Connect a different ChatGPT account or workspace in the sign-in prompt.

Current limitations

• Developer function tools and web search are supported. OpenAI-hosted plugins, connected apps, hosted MCP tools, tool search, and hosted image generation are not supported yet.
• Text, images, and files can be inputs when the selected Responses model accepts them. This does not grant access to the Files upload API, audio or video input, or the transcription API.
• SIWC credentials do not authorize image generation, audio transcription, speech synthesis, or memory embeddings. Configure a separate compatible credential for those tools. Onboarding continues with the agent's emoji when no image-generation provider is available; an avatar is optional.
• Responses requests use HTTP streaming. WebSocket inference and SIWC quota reporting in OpenClaw are not available.
• With the Codex runtime, SIWC requires a managed local process and an isolated agent home. Automatic context summarization is supported; manual /compact, remote execution, and supervised sessions are unavailable with this credential.

OpenClaw discovers SIWC model choices from the selected account through GET https://api.openai.com/v1/models, using the same profile's access token as inference. Only models marked for display are offered, with their account-specific names and order. Switching profiles uses that profile's catalog. A successful empty list stays empty; a rejected credential does not fall back to static model access. If discovery is temporarily unavailable, OpenClaw retains static hints and marks discovery unavailable. Codex app-server's bundled or cached model list is not proof of current SIWC account access.

Model and allowance eligibility are enforced by OpenAI. SIWC does not import ChatGPT conversations or Codex history.