docs(anthropic): remove setup-token setup docs

This commit is contained in:
Peter Steinberger 2026-04-04 15:46:13 +09:00
parent 1b4bb5be19
commit 0ab160cda9
No known key found for this signature in database
20 changed files with 108 additions and 306 deletions

View File

@ -29,6 +29,7 @@ Docs: https://docs.openclaw.ai
- Docs/memory: add a dedicated Dreaming concept page, expand Memory overview with the Dreaming model, and link Dreaming from further reading to document the experimental opt-in consolidation workflow. Thanks @vignesh07.
- Agents/cache prefixes: route compaction, OpenAI WebSocket HTTP fallback, and later-turn embedded session reuse through the same cache-safe prompt shaping path so Anthropic-family and OpenAI-family requests keep stable prompt bytes across follow-up turns and fallback transport changes. (#60691) Thanks @vincentkoc.
- Agents/Claude CLI: expose OpenClaw tools to background Claude CLI runs through a loopback MCP bridge that reuses gateway tool policy, honors session/account/channel scoping, and only advertises the bridge when the local runtime is actually live. (#35676) Thanks @mylukin.
- Providers/Anthropic: remove setup-token from new onboarding and auth-command setup paths, keep existing configured legacy token profiles runnable, and steer new Anthropic setup to Claude CLI or API keys.
### Fixes

View File

@ -426,7 +426,7 @@ Options:
- `--mode <local|remote>`
- `--flow <quickstart|advanced|manual>` (manual is an alias for advanced)
- `--auth-choice <choice>` where `<choice>` is one of:
`setup-token`, `token`, `chutes`, `deepseek-api-key`, `openai-codex`, `openai-api-key`,
`chutes`, `deepseek-api-key`, `openai-codex`, `openai-api-key`,
`openrouter-api-key`, `kilocode-api-key`, `litellm-api-key`, `ai-gateway-api-key`,
`cloudflare-ai-gateway-api-key`, `moonshot-api-key`, `moonshot-api-key-cn`,
`kimi-code-api-key`, `synthetic-api-key`, `venice-api-key`, `together-api-key`,
@ -437,10 +437,6 @@ Options:
`mistral-api-key`, `volcengine-api-key`, `byteplus-api-key`, `qianfan-api-key`,
`modelstudio-standard-api-key-cn`, `modelstudio-standard-api-key`,
`modelstudio-api-key-cn`, `modelstudio-api-key`, `custom-api-key`, `skip`
- `--token-provider <id>` (non-interactive; used with `--auth-choice token`)
- `--token <token>` (non-interactive; used with `--auth-choice token`)
- `--token-profile-id <id>` (non-interactive; default: `<provider>:manual`)
- `--token-expires-in <duration>` (non-interactive; e.g. `365d`, `12h`)
- `--secret-input-mode <plaintext|ref>` (default `plaintext`; use `ref` to store provider default env refs instead of plaintext keys)
- `--anthropic-api-key <key>`
- `--openai-api-key <key>`
@ -986,17 +982,9 @@ Tip: these config write RPCs preflight active SecretRef resolution for refs in t
See [/concepts/models](/concepts/models) for fallback behavior and scanning strategy.
Anthropic setup-token (supported):
```bash
claude setup-token
openclaw models auth setup-token --provider anthropic
openclaw models status
```
Billing note: Anthropic changed third-party harness billing on **April 4, 2026
at 12:00 PM PT / 8:00 PM BST**. Anthropic says Claude subscription limits no
longer cover OpenClaw, and setup-token usage in OpenClaw now requires **Extra
longer cover OpenClaw, and Claude CLI usage in OpenClaw now requires **Extra
Usage** billed separately from the subscription. For production, prefer an
Anthropic API key or another supported subscription-style provider such as
OpenAI Codex, Alibaba Cloud Model Studio Coding Plan, MiniMax Coding Plan, or
@ -1010,6 +998,9 @@ openclaw models auth login --provider anthropic --method cli --set-default
Onboarding shortcut: `openclaw onboard --auth-choice anthropic-cli`
Existing legacy Anthropic token profiles still run if already configured, but
OpenClaw no longer offers Anthropic setup-token as a new auth path.
Legacy alias note: `claude-cli` is the deprecated onboarding auth-choice alias.
Use `anthropic-cli` for onboarding, or use `models auth login` directly.
@ -1107,7 +1098,7 @@ Options:
- `add`: interactive auth helper
- `login`: `--provider <name>`, `--method <method>`, `--set-default`
- `login-github-copilot`: GitHub Copilot OAuth login flow
- `setup-token`: `--provider <name>` (default `anthropic`), `--yes`
- `setup-token`: `--provider <name>`, `--yes`
- `paste-token`: `--provider <name>`, `--profile-id <id>`, `--expires-in <duration>`
### `models auth order get|set|clear`

View File

@ -67,7 +67,7 @@ openclaw models fallbacks list
```bash
openclaw models auth add
openclaw models auth login --provider <id>
openclaw models auth setup-token
openclaw models auth setup-token --provider <id>
openclaw models auth paste-token
```
@ -85,6 +85,6 @@ Notes:
- `login --provider anthropic --method cli --set-default` reuses a local Claude
CLI login and rewrites the main Anthropic default-model path to `claude-cli/...`.
- `setup-token` prompts for a setup-token value (generate it with `claude setup-token` on any machine).
- `paste-token` accepts a token string generated elsewhere or from automation.
- Anthropic billing note: Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover OpenClaw, and setup-token usage in OpenClaw now requires **Extra Usage** billed separately from the subscription.
- Anthropic billing note: Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover OpenClaw, and Claude CLI traffic in OpenClaw now requires **Extra Usage** billed separately from the subscription.
- Existing legacy Anthropic token profiles still run if already configured, but OpenClaw no longer offers Anthropic setup-token as a new auth path.

View File

@ -174,13 +174,13 @@ OpenClaw ships with the piai catalog. These providers require **no**
### Anthropic
- Provider: `anthropic`
- Auth: `ANTHROPIC_API_KEY` or `claude setup-token`
- Auth: `ANTHROPIC_API_KEY`
- Optional rotation: `ANTHROPIC_API_KEYS`, `ANTHROPIC_API_KEY_1`, `ANTHROPIC_API_KEY_2`, plus `OPENCLAW_LIVE_ANTHROPIC_KEY` (single override)
- Example model: `anthropic/claude-opus-4-6`
- CLI: `openclaw onboard --auth-choice token` (paste setup-token) or `openclaw models auth paste-token --provider anthropic`
- CLI: `openclaw onboard --auth-choice apiKey` or `openclaw onboard --auth-choice anthropic-cli`
- Direct public Anthropic requests support the shared `/fast` toggle and `params.fastMode`, including API-key and OAuth-authenticated traffic sent to `api.anthropic.com`; OpenClaw maps that to Anthropic `service_tier` (`auto` vs `standard_only`)
- Billing note: Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover OpenClaw, and subscription-auth traffic now requires **Extra Usage** billed separately from the subscription.
- Recommendation: Anthropic API key auth is the safer, recommended path over subscription setup-token auth.
- Billing note: Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover OpenClaw, and Claude CLI traffic now requires **Extra Usage** billed separately from the subscription.
- Existing legacy Anthropic token profiles still run if already configured, but new setup is no longer offered through onboarding or auth commands.
```json5
{

View File

@ -44,7 +44,7 @@ openclaw onboard
```
It can set up model + auth for common providers, including **OpenAI Code (Codex)
subscription** (OAuth) and **Anthropic** (API key or `claude setup-token`).
subscription** (OAuth) and **Anthropic** (API key or Claude CLI).
## Config keys (overview)
@ -163,12 +163,14 @@ JSON includes `auth.oauth` (warn window + profiles) and `auth.providers`
(effective auth per provider).
Use `--check` for automation (exit `1` when missing/expired, `2` when expiring).
Auth choice is provider/account dependent. For always-on gateway hosts, API keys are usually the most predictable; subscription token flows are also supported.
Auth choice is provider/account dependent. For always-on gateway hosts, API
keys are usually the most predictable; Claude CLI reuse and existing legacy
Anthropic token profiles are also supported.
Example (Anthropic setup-token):
Example (Claude CLI):
```bash
claude setup-token
claude auth login
openclaw models status
```

View File

@ -3,7 +3,7 @@ summary: "OAuth in OpenClaw: token exchange, storage, and multi-account patterns
read_when:
- You want to understand OpenClaw OAuth end-to-end
- You hit token invalidation / logout issues
- You want setup-token, Claude CLI, or OAuth auth flows
- You want Claude CLI or OAuth auth flows
- You want multiple accounts or profile routing
title: "OAuth"
---
@ -11,15 +11,15 @@ title: "OAuth"
# OAuth
OpenClaw supports “subscription auth” via OAuth for providers that offer it
(notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic subscriptions, you
can either use the **setup-token** flow or reuse a local **Claude CLI** login
on the gateway host, but Anthropic changed third-party harness billing on
(notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic subscriptions, new
setup should use the local **Claude CLI** login path on the gateway host, but
Anthropic changed third-party harness billing on
**April 4, 2026 at 12:00 PM PT / 8:00 PM BST**: Anthropic says Claude
subscription limits no longer cover OpenClaw and Anthropic now requires **Extra
Usage** for that traffic. OpenAI Codex OAuth is explicitly supported for use in
external tools like OpenClaw. This page explains:
For Anthropic in production, API key auth is the safer recommended path over subscription setup-token auth.
For Anthropic in production, API key auth is the safer recommended path.
- how the OAuth **token exchange** works (PKCE)
- where tokens are **stored** (and why)
@ -64,14 +64,15 @@ All of the above also respect `$OPENCLAW_STATE_DIR` (state dir override). Full r
For static secret refs and runtime snapshot activation behavior, see [Secrets Management](/gateway/secrets).
## Anthropic setup-token (subscription auth)
## Anthropic legacy token compatibility
<Warning>
Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM
PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover
OpenClaw or other third-party harnesses. Anthropic setup-token support remains
technically usable in OpenClaw, but Anthropic now requires **Extra Usage**
(pay-as-you-go billed separately from the subscription) for that traffic.
OpenClaw or other third-party harnesses. Existing Anthropic token profiles
remain technically usable in OpenClaw, but Anthropic now requires **Extra
Usage** (pay-as-you-go billed separately from the subscription) for that
traffic.
If you want other subscription-style options in OpenClaw, see [OpenAI
Codex](/providers/openai), [Alibaba Cloud Model Studio Coding
@ -79,23 +80,9 @@ Plan](/providers/qwen_modelstudio), [MiniMax Coding Plan](/providers/minimax),
and [Z.AI / GLM Coding Plan](/providers/glm).
</Warning>
Run `claude setup-token` on any machine, then paste it into OpenClaw:
```bash
openclaw models auth setup-token --provider anthropic
```
If you generated the token elsewhere, paste it manually:
```bash
openclaw models auth paste-token --provider anthropic
```
Verify:
```bash
openclaw models status
```
OpenClaw no longer offers Anthropic setup-token onboarding or auth commands for
new setup. Existing legacy Anthropic token profiles are still honored at
runtime if they are already configured.
## Anthropic Claude CLI migration
@ -136,16 +123,10 @@ openclaw models status
OpenClaws interactive login flows are implemented in `@mariozechner/pi-ai` and wired into the wizards/commands.
### Anthropic setup-token / Claude CLI
### Anthropic Claude CLI
Flow shape:
Setup-token path:
1. run `claude setup-token`
2. paste the token into OpenClaw
3. store as a token auth profile (no refresh)
Claude CLI path:
1. sign in with `claude auth login` on the gateway host
@ -157,11 +138,6 @@ Interactive assistant path:
- `openclaw onboard` / `openclaw configure` → auth choice `anthropic-cli`
Manual setup-token path:
- `openclaw models auth setup-token --provider anthropic`
- `openclaw models auth paste-token --provider anthropic`
### OpenAI Codex (ChatGPT OAuth)
OpenAI Codex OAuth is explicitly supported for use outside the Codex CLI, including OpenClaw workflows.

View File

@ -39,10 +39,10 @@ cache-write size, directly lowering cost.
OpenClaw auto-enables pruning for Anthropic profiles:
| Profile type | Pruning enabled | Heartbeat |
| -------------------- | --------------- | --------- |
| OAuth or setup-token | Yes | 1 hour |
| API key | Yes | 30 min |
| Profile type | Pruning enabled | Heartbeat |
| ------------------------------- | --------------- | --------- |
| Claude CLI or legacy token auth | Yes | 1 hour |
| API key | Yes | 30 min |
If you set explicit values, OpenClaw does not override them.

View File

@ -1,5 +1,5 @@
---
summary: "Model authentication: OAuth, API keys, and setup-token"
summary: "Model authentication: OAuth, API keys, and Claude CLI reuse"
read_when:
- Debugging model auth or OAuth expiry
- Documenting authentication or credential storage
@ -9,7 +9,7 @@ title: "Authentication"
# Authentication (Model Providers)
<Note>
This page covers **model provider** authentication (API keys, OAuth, setup tokens). For **gateway connection** authentication (token, password, trusted-proxy), see [Configuration](/gateway/configuration) and [Trusted Proxy Auth](/gateway/trusted-proxy-auth).
This page covers **model provider** authentication (API keys, OAuth, Claude CLI reuse). For **gateway connection** authentication (token, password, trusted-proxy), see [Configuration](/gateway/configuration) and [Trusted Proxy Auth](/gateway/trusted-proxy-auth).
</Note>
OpenClaw supports OAuth and API keys for model providers. For always-on gateway
@ -26,8 +26,8 @@ For credential eligibility/reason-code rules used by `models status --probe`, se
If youre running a long-lived gateway, start with an API key for your chosen
provider.
For Anthropic specifically, API key auth is the safe path and is recommended
over subscription setup-token auth.
For Anthropic specifically, API key auth is the safe path. Claude CLI reuse is
the other supported subscription-style setup path.
1. Create an API key in your provider console.
2. Put it on the **gateway host** (the machine running `openclaw gateway`).
@ -59,53 +59,18 @@ API keys for daemon use: `openclaw onboard`.
See [Help](/help) for details on env inheritance (`env.shellEnv`,
`~/.openclaw/.env`, systemd/launchd).
## Anthropic: setup-token (subscription auth)
## Anthropic: legacy token compatibility
If youre using a Claude subscription, the setup-token flow is supported. Run
it on the **gateway host**:
Existing Anthropic token profiles are still honored at runtime if they are
already configured, but OpenClaw no longer offers Anthropic setup-token auth
for new setup via onboarding or `models auth` commands.
```bash
claude setup-token
```
Then paste it into OpenClaw:
```bash
openclaw models auth setup-token --provider anthropic
```
If the token was created on another machine, paste it manually:
```bash
openclaw models auth paste-token --provider anthropic
```
If you see an Anthropic error like:
```
This credential is only authorized for use with Claude Code and cannot be used for other API requests.
```
…use an Anthropic API key instead.
<Warning>
Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM
PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover
OpenClaw or other third-party harnesses. Setup-token auth still works in
OpenClaw, but Anthropic now requires **Extra Usage** (pay-as-you-go billed
separately from the subscription) for that traffic.
If you want the clearest path for always-on or team gateways, prefer an
Anthropic API key. OpenClaw also supports other subscription-style options,
including [OpenAI Codex](/providers/openai), [Alibaba Cloud Model Studio Coding
Plan](/providers/qwen_modelstudio), [MiniMax Coding Plan](/providers/minimax),
and [Z.AI / GLM Coding Plan](/providers/glm).
</Warning>
For new setup, use an Anthropic API key or migrate to Claude CLI on the gateway
host.
Manual token entry (any provider; writes `auth-profiles.json` + updates config):
```bash
openclaw models auth paste-token --provider anthropic
openclaw models auth paste-token --provider openrouter
```
@ -124,14 +89,12 @@ openclaw models status --check
Optional ops scripts (systemd/Termux) are documented here:
[Auth monitoring scripts](/help/scripts#auth-monitoring-scripts)
> `claude setup-token` requires an interactive TTY.
## Anthropic: Claude CLI migration
If Claude CLI is already installed and signed in on the gateway host, you can
switch an existing Anthropic setup over to the CLI backend instead of pasting a
setup-token. This is a supported OpenClaw migration path for reusing a local
Claude CLI login on that host.
switch an existing Anthropic setup over to the CLI backend. This is a
supported OpenClaw migration path for reusing a local Claude CLI login on that
host.
Prerequisites:
@ -159,8 +122,7 @@ openclaw onboard --auth-choice anthropic-cli
```
Interactive `openclaw onboard` and `openclaw configure` prefer Claude CLI for
Anthropic and do not show setup-token in the assistant picker. Setup-token
remains supported through the manual commands above.
Anthropic and no longer offer setup-token as a new setup path.
## Checking model auth status
@ -210,8 +172,8 @@ Use `--agent <id>` to target a specific agent; omit it to use the configured def
### "No credentials found"
If the Anthropic token profile is missing, run `claude setup-token` on the
**gateway host**, then re-check:
If the Anthropic profile is missing, migrate that setup to Claude CLI or an API
key on the **gateway host**, then re-check:
```bash
openclaw models status
@ -219,10 +181,10 @@ openclaw models status
### Token expiring/expired
Run `openclaw models status` to confirm which profile is expiring. If the profile
is missing, rerun `claude setup-token` and paste the token again.
Run `openclaw models status` to confirm which profile is expiring. If a legacy
Anthropic token profile is missing or expired, migrate that setup to Claude CLI
or an API key.
## Requirements
- Anthropic subscription account (for `claude setup-token`)
- Claude Code CLI installed (`claude` command available)

View File

@ -536,62 +536,19 @@ If more than one person can DM your bot (multiple entries in `allowFrom`, pairin
For Discord/Slack/Google Chat/Microsoft Teams/Mattermost/IRC, sender authorization is ID-first by default.
Only enable direct mutable name/email/nick matching with each channel's `dangerouslyAllowNameMatching: true` if you explicitly accept that risk.
### OAuth with API key failover
### Anthropic API key + MiniMax fallback
```json5
{
auth: {
profiles: {
"anthropic:subscription": {
provider: "anthropic",
mode: "oauth",
email: "me@example.com",
},
"anthropic:api": {
provider: "anthropic",
mode: "api_key",
},
},
order: {
anthropic: ["anthropic:subscription", "anthropic:api"],
},
},
agent: {
workspace: "~/.openclaw/workspace",
model: {
primary: "anthropic/claude-sonnet-4-6",
fallbacks: ["anthropic/claude-opus-4-6"],
},
},
}
```
### Anthropic setup-token + API key, MiniMax fallback
<Warning>
Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM
PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover
OpenClaw, and Anthropic setup-token traffic now requires **Extra Usage** billed
separately from the subscription. Prefer an Anthropic API key if you want the
clearest billing path.
</Warning>
```json5
{
auth: {
profiles: {
"anthropic:subscription": {
provider: "anthropic",
mode: "oauth",
email: "user@example.com",
},
"anthropic:api": {
provider: "anthropic",
mode: "api_key",
},
},
order: {
anthropic: ["anthropic:subscription", "anthropic:api"],
anthropic: ["anthropic:api"],
},
},
models: {

View File

@ -290,7 +290,7 @@ Doctor checks:
Doctor inspects OAuth profiles in the auth store, warns when tokens are
expiring/expired, and can refresh them when safe. If the Anthropic Claude Code
profile is stale, it suggests running `claude setup-token` (or pasting a setup-token).
profile is stale, it suggests migrating to Claude CLI or an Anthropic API key.
Refresh prompts only appear when running interactively (TTY); `--non-interactive`
skips refresh attempts.

View File

@ -20,7 +20,7 @@ Troubleshooting: [Scheduled Tasks](/automation/cron-jobs#troubleshooting)
## Quick start (beginner)
1. Leave heartbeats enabled (default is `30m`, or `1h` for Anthropic OAuth/setup-token) or set your own cadence.
1. Leave heartbeats enabled (default is `30m`, or `1h` for Anthropic Claude CLI or legacy token auth) or set your own cadence.
2. Create a tiny `HEARTBEAT.md` checklist in the agent workspace (optional but recommended).
3. Decide where heartbeat messages should go (`target: "none"` is the default; set `target: "last"` to route to the last contact).
4. Optional: enable heartbeat reasoning delivery for transparency.
@ -50,7 +50,7 @@ Example config:
## Defaults
- Interval: `30m` (or `1h` when Anthropic OAuth/setup-token is the detected auth mode). Set `agents.defaults.heartbeat.every` or per-agent `agents.list[].heartbeat.every`; use `0m` to disable.
- Interval: `30m` (or `1h` when Anthropic Claude CLI or legacy token auth is the detected auth mode). Set `agents.defaults.heartbeat.every` or per-agent `agents.list[].heartbeat.every`; use `0m` to disable.
- Prompt body (configurable via `agents.defaults.heartbeat.prompt`):
`Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.`
- The heartbeat prompt is sent **verbatim** as the user message. The system

View File

@ -543,7 +543,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
<Accordion title="What does onboarding actually do?">
`openclaw onboard` is the recommended setup path. In **local mode** it walks you through:
- **Model/auth setup** (provider OAuth/setup-token flows and API keys supported, plus local model options such as LM Studio)
- **Model/auth setup** (provider OAuth, Claude CLI reuse, and API keys supported, plus local model options such as LM Studio)
- **Workspace** location + bootstrap files
- **Gateway settings** (bind/port/auth/tailscale)
- **Providers** (WhatsApp, Telegram, Discord, Mattermost (plugin), Signal, iMessage)
@ -577,46 +577,26 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
</Accordion>
<Accordion title="Can I use Claude Max subscription without an API key?">
Yes. You can either use a **setup-token** or reuse a local **Claude CLI**
login on the gateway host.
Yes, via a local **Claude CLI** login on the gateway host.
Claude Pro/Max subscriptions **do not include an API key**, so this is the
technical path for subscription accounts. But Anthropic changed third-party
harness billing on **April 4, 2026 at 12:00 PM PT / 8:00 PM BST**:
Anthropic says OpenClaw now requires **Extra Usage** billed separately from
the subscription for this path. If you want the clearest and safest
supported path for production, use an Anthropic API key.
</Accordion>
<Accordion title="How does Anthropic setup-token auth work?">
`claude setup-token` generates a **token string** via the Claude Code CLI (it is not available in the web console). You can run it on **any machine**. Interactive onboarding/configure no longer shows setup-token as an assistant choice; use `openclaw models auth setup-token --provider anthropic` or paste an existing token with `openclaw models auth paste-token --provider anthropic`. The token is stored as an auth profile for the **anthropic** provider and used like an API key (no auto-refresh). More detail: [OAuth](/concepts/oauth).
</Accordion>
<Accordion title="Where do I find an Anthropic setup-token?">
It is **not** in the Anthropic Console. The setup-token is generated by the **Claude Code CLI** on **any machine**:
```bash
claude setup-token
```
Copy the token it prints, then either run `openclaw models auth setup-token --provider anthropic` on the gateway host or paste it there with `openclaw models auth paste-token --provider anthropic`. See [Anthropic](/providers/anthropic).
Claude Pro/Max subscriptions **do not include an API key**, so Claude CLI
reuse is the supported subscription-style path in OpenClaw. Anthropic
changed third-party harness billing on **April 4, 2026 at 12:00 PM PT /
8:00 PM BST**: Anthropic says OpenClaw now requires **Extra Usage** billed
separately from the subscription for this path. If you want the clearest
and safest supported path for production, use an Anthropic API key.
</Accordion>
<Accordion title="Do you support Claude subscription auth (Claude Pro or Max)?">
Yes. You can either:
Yes. Reuse a local **Claude CLI** login on the gateway host with `openclaw models auth login --provider anthropic --method cli --set-default`.
- reuse a local **Claude CLI** login on the gateway host with `openclaw models auth login --provider anthropic --method cli --set-default`
- use a **setup-token** manually with `openclaw models auth setup-token --provider anthropic`
Claude CLI is the preferred interactive Anthropic path. Setup-token is still supported for manual config. See [Anthropic](/providers/anthropic) and [OAuth](/concepts/oauth).
Existing legacy Anthropic token profiles still run if they are already configured, but OpenClaw no longer offers Anthropic setup-token as a new setup path. See [Anthropic](/providers/anthropic) and [OAuth](/concepts/oauth).
Important: Anthropic changed third-party harness billing on **April 4, 2026
at 12:00 PM PT / 8:00 PM BST**. Anthropic says Claude subscription limits no
longer cover OpenClaw, and Anthropic now requires **Extra Usage** billed
separately from the subscription for setup-token or Claude CLI traffic
through OpenClaw.
separately from the subscription for Claude CLI traffic through OpenClaw.
For production or multi-user workloads, Anthropic API key auth is the
safer, recommended choice. If you want other subscription-style hosted
@ -629,15 +609,15 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
<a id="why-am-i-seeing-http-429-ratelimiterror-from-anthropic"></a>
<Accordion title="Why am I seeing HTTP 429 rate_limit_error from Anthropic?">
That means your **Anthropic quota/rate limit** is exhausted for the current window. If you
use a **Claude subscription** (setup-token), wait for the window to
reset or upgrade your plan. If you use an **Anthropic API key**, check the Anthropic Console
use **Claude CLI**, wait for the window to reset or upgrade your plan. If you
use an **Anthropic API key**, check the Anthropic Console
for usage/billing and raise limits as needed.
If the message is specifically:
`Extra usage is required for long context requests`, the request is trying to use
Anthropic's 1M context beta (`context1m: true`). That only works when your
credential is eligible for long-context billing (API key billing or subscription
with Extra Usage enabled).
credential is eligible for long-context billing (API key billing or Claude
CLI with Extra Usage enabled).
Tip: set a **fallback model** so OpenClaw can keep replying while a provider is rate-limited.
See [Models](/cli/models), [OAuth](/concepts/oauth), and
@ -2381,9 +2361,8 @@ for usage/billing and raise limits as needed.
This means the run is pinned to an Anthropic auth profile, but the Gateway
can't find it in its auth store.
- **Use a setup-token**
- Run `claude setup-token`, then paste it with `openclaw models auth setup-token --provider anthropic`.
- If the token was created on another machine, use `openclaw models auth paste-token --provider anthropic`.
- **Use Claude CLI**
- Run `openclaw models auth login --provider anthropic --method cli --set-default` on the gateway host.
- **If you want to use an API key instead**
- Put `ANTHROPIC_API_KEY` in `~/.openclaw/.env` on the **gateway host**.
- Clear any pinned order that forces a missing profile:
@ -2470,7 +2449,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
- **OAuth** often leverages subscription access (where applicable).
- **API keys** use pay-per-token billing.
The wizard explicitly supports Anthropic setup-token and OpenAI Codex OAuth and can store API keys for you.
The wizard explicitly supports Anthropic Claude CLI, OpenAI Codex OAuth, and API keys.
</Accordion>
</AccordionGroup>

View File

@ -244,26 +244,6 @@ openclaw models list
openclaw models list --json
```
## Live: Anthropic setup-token smoke
- Test: `src/agents/anthropic.setup-token.live.test.ts`
- Goal: verify Claude Code CLI setup-token (or a pasted setup-token profile) can complete an Anthropic prompt.
- Enable:
- `pnpm test:live` (or `OPENCLAW_LIVE_TEST=1` if invoking Vitest directly)
- `OPENCLAW_LIVE_SETUP_TOKEN=1`
- Token sources (pick one):
- Profile: `OPENCLAW_LIVE_SETUP_TOKEN_PROFILE=anthropic:setup-token-test`
- Raw token: `OPENCLAW_LIVE_SETUP_TOKEN_VALUE=sk-ant-oat01-...`
- Model override (optional):
- `OPENCLAW_LIVE_SETUP_TOKEN_MODEL=anthropic/claude-opus-4-6`
Setup example:
```bash
openclaw models auth paste-token --provider anthropic --profile-id anthropic:setup-token-test
OPENCLAW_LIVE_SETUP_TOKEN=1 OPENCLAW_LIVE_SETUP_TOKEN_PROFILE=anthropic:setup-token-test pnpm test:live src/agents/anthropic.setup-token.live.test.ts
```
## Live: CLI backend smoke (Claude Code CLI or other local CLIs)
- Test: `src/gateway/gateway-cli-backend.live.test.ts`

View File

@ -1,8 +1,7 @@
---
summary: "Use Anthropic Claude via API keys, setup-token, or Claude CLI in OpenClaw"
summary: "Use Anthropic Claude via API keys or Claude CLI in OpenClaw"
read_when:
- You want to use Anthropic models in OpenClaw
- You want setup-token instead of API keys
- You want to reuse Claude CLI subscription auth on the gateway host
title: "Anthropic"
---
@ -10,13 +9,15 @@ title: "Anthropic"
# Anthropic (Claude)
Anthropic builds the **Claude** model family and provides access via an API.
In OpenClaw you can authenticate with an API key or a **setup-token**.
In OpenClaw, new Anthropic setup should use an API key or the local Claude CLI
backend. Existing legacy Anthropic token profiles are still honored at runtime
if they are already configured.
<Warning>
Anthropic changed third-party harness billing on **April 4, 2026 at 12:00 PM
PT / 8:00 PM BST**. Anthropic says Claude subscription limits no longer cover
OpenClaw or other third-party harnesses. You can still use Anthropic
subscription auth in OpenClaw, but Anthropic now requires **Extra Usage**
OpenClaw or other third-party harnesses. Existing legacy Anthropic token auth
can still run in OpenClaw, but Anthropic now requires **Extra Usage**
(pay-as-you-go, billed separately from the subscription) for that traffic.
If you want a clearer billing path, use an Anthropic API key instead. OpenClaw
@ -89,7 +90,7 @@ Important limits:
## Prompt caching (Anthropic API)
OpenClaw supports Anthropic's prompt caching feature. This is **API-only**; subscription auth does not honor cache settings.
OpenClaw supports Anthropic's prompt caching feature. This is **API-only**; legacy Anthropic token auth does not honor cache settings.
### Configuration
@ -181,15 +182,15 @@ This only activates when `params.context1m` is explicitly set to `true` for
that model.
Requirement: Anthropic must allow long-context usage on that credential
(typically API key billing, or a subscription account with Extra Usage
(typically API key billing, or Claude CLI / legacy token auth with Extra Usage
enabled). Otherwise Anthropic returns:
`HTTP 429: rate_limit_error: Extra usage is required for long context requests`.
Note: Anthropic currently rejects `context-1m-*` beta requests when using
subscription setup-tokens (`sk-ant-oat-*`). If you configure `context1m: true`
with subscription auth, OpenClaw logs a warning and falls back to the standard
context window by skipping the context1m beta header while keeping the required
OAuth betas.
legacy Anthropic token auth (`sk-ant-oat-*`). If you configure
`context1m: true` with that legacy auth mode, OpenClaw logs a warning and
falls back to the standard context window by skipping the context1m beta
header while keeping the required OAuth betas.
## Option B: Claude CLI as the message provider
@ -272,7 +273,7 @@ If the `claude` binary is not on the gateway host PATH:
### Migrate from Anthropic auth to Claude CLI
If you currently use `anthropic/...` with a setup-token or API key and want to
If you currently use `anthropic/...` with a legacy token profile or API key and want to
switch the same gateway host to Claude CLI, OpenClaw supports that as a normal
provider-auth migration path.
@ -294,9 +295,7 @@ openclaw onboard --auth-choice anthropic-cli
```
Interactive `openclaw onboard` and `openclaw configure` now prefer **Anthropic
Claude CLI** first and **Anthropic API key** second. The setup-token flow
remains supported through manual auth commands, but is not shown in the
assistant picker.
Claude CLI** first and **Anthropic API key** second.
What this does:
@ -332,67 +331,31 @@ you need to.
More details: [/gateway/cli-backends](/gateway/cli-backends)
## Option C: Claude setup-token (manual)
**Best for:** using your Claude subscription with Anthropic **Extra Usage**
enabled, or while transitioning to API-key billing.
### Where to get a setup-token
Setup-tokens are created by the **Claude Code CLI**, not the Anthropic Console. You can run this on **any machine**:
```bash
claude setup-token
```
Then either run it on the gateway host:
```bash
openclaw models auth setup-token --provider anthropic
```
Or if you generated the token on a different machine, paste it:
```bash
openclaw models auth paste-token --provider anthropic
```
### Config snippet (setup-token)
```json5
{
agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
}
```
## Notes
- Generate the setup-token with `claude setup-token` and paste it, or run `openclaw models auth setup-token` on the gateway host.
- Anthropic says that starting **April 4, 2026 at 12:00 PM PT / 8:00 PM BST**,
OpenClaw usage with Claude subscription auth requires **Extra Usage**
OpenClaw usage with Claude CLI or legacy Anthropic token auth requires **Extra Usage**
(pay-as-you-go billed separately from the subscription).
- If you see “OAuth token refresh failed …” on a Claude subscription, re-auth with a setup-token. See [/gateway/troubleshooting](/gateway/troubleshooting).
- Existing legacy Anthropic token profiles are still honored at runtime, but OpenClaw no longer offers setup-token onboarding or auth commands for new setups.
- Auth details + reuse rules are in [/concepts/oauth](/concepts/oauth).
## Troubleshooting
**401 errors / token suddenly invalid**
- Claude subscription auth can expire or be revoked. Re-run `claude setup-token`
and paste it into the **gateway host**.
- If the Claude CLI login lives on a different machine, use
`openclaw models auth paste-token --provider anthropic` on the gateway host.
- Legacy Anthropic token auth can expire or be revoked.
- For new setup, migrate to an Anthropic API key or the local Claude CLI path on the gateway host.
**No API key found for provider "anthropic"**
- Auth is **per agent**. New agents dont inherit the main agents keys.
- Re-run onboarding for that agent, or paste a setup-token / API key on the
gateway host, then verify with `openclaw models status`.
- Re-run onboarding for that agent, or configure an API key on the gateway
host, then verify with `openclaw models status`.
**No credentials found for profile `anthropic:default`**
- Run `openclaw models status` to see which auth profile is active.
- Re-run onboarding, or paste a setup-token / API key for that profile.
- Re-run onboarding, or configure an API key or Claude CLI for that profile path.
**No available auth profile (all in cooldown/unavailable)**

View File

@ -150,5 +150,5 @@ launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.claude-max-api.plist
## See Also
- [Anthropic provider](/providers/anthropic) - Native OpenClaw integration with Claude setup-token or API keys
- [Anthropic provider](/providers/anthropic) - Native OpenClaw integration with Claude CLI or API keys
- [OpenAI provider](/providers/openai) - For OpenAI/Codex subscriptions

View File

@ -22,7 +22,7 @@ OpenClaw features that can generate provider usage or paid API calls.
**Per-message cost footer**
- `/usage full` appends a usage footer to every reply, including **estimated cost** (API-key only).
- `/usage tokens` shows tokens only; OAuth/setup-token/CLI subscription flows hide dollar cost.
- `/usage tokens` shows tokens only; subscription-style OAuth, legacy token, and CLI flows hide dollar cost.
Anthropic note: starting **April 4, 2026 at 12:00 PM PT / 8:00 PM BST**,
Anthropic says OpenClaw no longer uses included Claude subscription limits.

View File

@ -32,7 +32,7 @@ For a high-level overview, see [Onboarding (CLI)](/start/wizard).
<Step title="Model/Auth">
- **Anthropic API key**: uses `ANTHROPIC_API_KEY` if present or prompts for a key, then saves it for daemon use.
- **Anthropic Claude CLI**: preferred Anthropic assistant choice in onboarding/configure. On macOS onboarding checks Keychain item "Claude Code-credentials" (choose "Always Allow" so launchd starts don't block); on Linux/Windows it reuses `~/.claude/.credentials.json` if present and switches model selection to `claude-cli/...`.
- **Anthropic setup-token**: still supported as a manual auth flow with `openclaw models auth setup-token --provider anthropic` or `openclaw models auth paste-token --provider anthropic`, but no longer shown in the interactive assistant picker.
- **Anthropic legacy token profiles**: still honored at runtime if already configured, but onboarding/configure no longer offers Anthropic setup-token as a new setup path.
- **OpenAI Code (Codex) subscription (Codex CLI)**: if `~/.codex/auth.json` exists, onboarding can reuse it. Reused Codex CLI credentials stay managed by Codex CLI; OpenClaw re-reads that source on expiry instead of rotating the copied refresh token itself.
- **OpenAI Code (Codex) subscription (OAuth)**: browser flow; paste the `code#state`.
- Sets `agents.defaults.model` to `openai-codex/gpt-5.4` when model is unset or `openai/*`.

View File

@ -195,10 +195,9 @@ openclaw onboard --non-interactive \
</Accordion>
</AccordionGroup>
Anthropic setup-token remains supported for manual flows, but interactive
onboarding/configure no longer offers it as an assistant choice. Use
`openclaw models auth setup-token --provider anthropic` or
`openclaw models auth paste-token --provider anthropic` when you need it.
Anthropic setup-token is no longer offered as a new onboarding/configure path.
Existing legacy Anthropic token profiles still run if they are already
configured.
## Add another agent

View File

@ -138,14 +138,6 @@ What you set:
On macOS, choose "Always Allow" so launchd starts do not block.
</Accordion>
<Accordion title="Anthropic setup-token (manual)">
Supported for manual config, not shown as an interactive assistant choice.
- Generate on any machine: `claude setup-token`
- Run on the gateway host: `openclaw models auth setup-token --provider anthropic`
- Or paste an existing token: `openclaw models auth paste-token --provider anthropic`
</Accordion>
<Accordion title="OpenAI Code subscription (Codex CLI reuse)">
If `~/.codex/auth.json` exists, the wizard can reuse it.

View File

@ -72,7 +72,7 @@ Onboarding starts with **QuickStart** (defaults) vs **Advanced** (full control).
For non-interactive runs, `--secret-input-mode ref` stores env-backed refs in auth profiles instead of plaintext API key values.
In non-interactive `ref` mode, the provider env var must be set; passing inline key flags without that env var fails fast.
In interactive runs, choosing secret reference mode lets you point at either an environment variable or a configured provider ref (`file` or `exec`), with a fast preflight validation before saving.
For Anthropic, interactive onboarding/configure prefers **Anthropic Claude CLI** first, then **Anthropic API key**. The **setup-token** flow remains supported through manual auth commands.
For Anthropic, interactive onboarding/configure prefers **Anthropic Claude CLI** first, then **Anthropic API key**. Existing legacy Anthropic token profiles still run if already configured, but new setup is no longer offered through onboarding or auth commands.
2. **Workspace** — Location for agent files (default `~/.openclaw/workspace`). Seeds bootstrap files.
3. **Gateway** — Port, bind address, auth mode, Tailscale exposure.
In interactive token mode, choose default plaintext token storage or opt into SecretRef.