# Anthropic表示，允许再次使用OpenClaw风格的Claude CLI

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：jmsflknr
- 发布时间：2026-04-21 15:23
- AIHOT 链接：https://aihot.virxact.com/items/cmo8bczng04ptslmldq2d8krl
- 原文链接：https://docs.openclaw.ai/providers/anthropic

## AI 摘要

Anthropic已恢复允许开发者使用OpenClaw风格的命令行界面访问Claude模型。此前该公司曾限制此类第三方CLI工具，此次政策调整标志着官方态度的转变。OpenClaw是一个提供类官方Claude CLI体验的第三方开源项目，此次解禁后开发者可再次通过该方式调用API。该消息在Hacker News社区获得112个点赞关注。

## 正文

Anthropic builds the Claude model family. OpenClaw supports two auth routes:

API key — direct Anthropic API access with usage-based billing (anthropic/* models)

anthropic/*

Claude CLI — reuse an existing Claude Code login on the same host

Getting started

API key

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

Get your API key Create an API key in the Anthropic Console.

Get your API key

Create an API key in the Anthropic Console.

Run onboarding bashCopy codeopenclaw onboard# choose: Anthropic API keyOr pass the key directly: bashCopy codeopenclaw onboard --anthropic-api-key "$ANTHROPIC_API_KEY"

Run onboarding

openclaw onboard# choose: Anthropic API key

openclaw onboard# choose: Anthropic API key

Or pass the key directly:

openclaw onboard --anthropic-api-key "$ANTHROPIC_API_KEY"

openclaw onboard --anthropic-api-key "$ANTHROPIC_API_KEY"

Verify the model is available bashCopy codeopenclaw models list --provider anthropic

Verify the model is available

openclaw models list --provider anthropic

openclaw models list --provider anthropic

Config example

{ env: { ANTHROPIC_API_KEY: "example-anthropic-key-not-real" }, agents: { defaults: { model: { primary: "anthropic/claude-opus-4-8" } } },}

{ env: { ANTHROPIC_API_KEY: "example-anthropic-key-not-real" }, agents: { defaults: { model: { primary: "anthropic/claude-opus-4-8" } } },}

Claude CLI

Best for: reusing an existing Claude CLI login without a separate API key.

Ensure Claude CLI is installed and logged in Verify with: bashCopy codeclaude --version

Ensure Claude CLI is installed and logged in

Verify with:

claude --version

claude --version

Run onboarding bashCopy codeopenclaw onboard# choose: Claude CLIOpenClaw detects and reuses the existing Claude CLI credentials.

Run onboarding

openclaw onboard# choose: Claude CLI

openclaw onboard# choose: Claude CLI

OpenClaw detects and reuses the existing Claude CLI credentials.

Verify the model is available bashCopy codeopenclaw models list --provider anthropic

Verify the model is available

openclaw models list --provider anthropic

openclaw models list --provider anthropic

Config example

Prefer the canonical Anthropic model ref plus a CLI runtime override:

{ agents: { defaults: { model: { primary: "anthropic/claude-opus-4-8" }, models: { "anthropic/claude-opus-4-8": { agentRuntime: { id: "claude-cli" }, }, }, }, },}

{ agents: { defaults: { model: { primary: "anthropic/claude-opus-4-8" }, models: { "anthropic/claude-opus-4-8": { agentRuntime: { id: "claude-cli" }, }, }, }, },}

Legacy claude-cli/claude-opus-4-7 model refs still work for compatibility, but new config should keep provider/model selection as anthropic/* and put the execution backend in provider/model runtime policy.

claude-cli/claude-opus-4-7

anthropic/*

Billing and claude -p

claude -p

OpenClaw uses Claude Code's non-interactive claude -p path for Claude CLI runs. Anthropic currently treats that path as Agent SDK/programmatic usage:

claude -p

Until June 15, 2026, subscription-plan handling follows Anthropic's active Claude Code rules for the signed-in account.

Starting June 15, 2026, subscription-plan claude -p usage draws from the user's monthly Agent SDK credit first, then from usage credits at standard API rates if usage credits are enabled.

claude -p

Console/API-key logins use pay-as-you-go API billing and do not receive the subscription Agent SDK credit.

Anthropic can change Claude Code billing and rate-limit behavior without an OpenClaw release. Check claude auth status, /status, and Anthropic's linked docs when billing predictability matters.

claude auth status

/status

Thinking defaults (Claude Fable 5, 4.8, and 4.6)

anthropic/claude-fable-5 always uses adaptive thinking and defaults to high effort. Because Anthropic does not allow thinking to be disabled for this model, /think off and /think minimal use low effort. OpenClaw also omits custom temperature values for Fable 5 requests.

anthropic/claude-fable-5

high

/think off

/think minimal

low

Claude Opus 4.8 keeps thinking off by default in OpenClaw. When you explicitly enable adaptive thinking with /think high|xhigh|max, OpenClaw sends Anthropic's Opus 4.8 effort values; Claude 4.6 models default to adaptive.

/think high|xhigh|max

adaptive

Override per-message with /think: or in model params:

/think:

{ agents: { defaults: { models: { "anthropic/claude-opus-4-8": { params: { thinking: "high" }, }, }, }, },}

{ agents: { defaults: { models: { "anthropic/claude-opus-4-8": { params: { thinking: "high" }, }, }, }, },}

Prompt caching

OpenClaw supports Anthropic's prompt caching feature for API-key auth.

Value Cache duration Description "short" (default) 5 minutes Applied automatically for API-key auth "long" 1 hour Extended cache "none" No caching Disable prompt caching

"short"

"long"

"none"

{ agents: { defaults: { models: { "anthropic/claude-opus-4-6": { params: { cacheRetention: "long" }, }, }, }, },}

{ agents: { defaults: { models: { "anthropic/claude-opus-4-6": { params: { cacheRetention: "long" }, }, }, }, },}

Use model-level params as your baseline, then override specific agents via agents.list[].params:

agents.list[].params

{ agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" }, models: { "anthropic/claude-opus-4-6": { params: { cacheRetention: "long" }, }, }, }, list: [ { id: "research", default: true }, { id: "alerts", params: { cacheRetention: "none" } }, ], },}

{ agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" }, models: { "anthropic/claude-opus-4-6": { params: { cacheRetention: "long" }, }, }, }, list: [ { id: "research", default: true }, { id: "alerts", params: { cacheRetention: "none" } }, ], },}

Config merge order:

agents.defaults.models["provider/model"].params

agents.defaults.models["provider/model"].params

agents.list[].params (matching id, overrides by key)

agents.list[].params

id

This lets one agent keep a long-lived cache while another agent on the same model disables caching for bursty/low-reuse traffic.

Anthropic Claude models on Bedrock (amazon-bedrock/*anthropic.claude*) accept cacheRetention pass-through when configured.

amazon-bedrock/*anthropic.claude*

cacheRetention

Non-Anthropic Bedrock models are forced to cacheRetention: "none" at runtime.

cacheRetention: "none"

API-key smart defaults also seed cacheRetention: "short" for Claude-on-Bedrock refs when no explicit value is set.

cacheRetention: "short"

Advanced configuration

OpenClaw's shared /fast toggle supports direct Anthropic traffic (API-key and OAuth to api.anthropic.com).

/fast

api.anthropic.com

Command Maps to /fast on service_tier: "auto" /fast off service_tier: "standard_only"

/fast on

service_tier: "auto"

/fast off

service_tier: "standard_only"

{ agents: { defaults: { models: { "anthropic/claude-sonnet-4-6": { params: { fastMode: true }, }, }, }, },}

{ agents: { defaults: { models: { "anthropic/claude-sonnet-4-6": { params: { fastMode: true }, }, }, }, },}

The bundled Anthropic plugin registers image and PDF understanding. OpenClaw auto-resolves media capabilities from the configured Anthropic auth — no additional config is needed.

Property Value Default model claude-opus-4-8 Supported input Images, PDF documents

claude-opus-4-8

When an image or PDF is attached to a conversation, OpenClaw automatically routes it through the Anthropic media understanding provider.

Anthropic's 1M context window is available on GA-capable Claude 4.x models such as Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6. OpenClaw sizes those models at 1M automatically:

{ agents: { defaults: { models: { "anthropic/claude-opus-4-6": {}, }, }, },}

{ agents: { defaults: { models: { "anthropic/claude-opus-4-6": {}, }, }, },}

Older configs can keep params.context1m: true, but OpenClaw no longer sends the retired context-1m-2025-08-07 beta header. Older anthropicBeta config entries with that value are ignored during request header resolution and unsupported older Claude models stay on their normal context window.

params.context1m: true

context-1m-2025-08-07

anthropicBeta

params.context1m: true also applies to the Claude CLI backend (claude-cli/*) for eligible GA-capable Opus and Sonnet models, preserving the runtime context window for those CLI sessions to match the direct-API behavior.

params.context1m: true

claude-cli/*

anthropic/claude-opus-4-8 and its claude-cli variant have a 1M context window by default — no params.context1m: true needed.

anthropic/claude-opus-4-8

claude-cli

params.context1m: true

Troubleshooting

Anthropic token auth expires and can be revoked. For new setups, use an Anthropic API key instead.

Anthropic auth is per agent — new agents do not inherit the main agent's keys. Re-run onboarding for that agent (or configure an API key on the gateway host), then verify with openclaw models status.

openclaw models status

Run openclaw models status to see which auth profile is active. Re-run onboarding, or configure an API key for that profile path.

openclaw models status

Check openclaw models status --json for auth.unusableProfiles. Anthropic rate-limit cooldowns can be model-scoped, so a sibling Anthropic model may still be usable. Add another Anthropic profile or wait for cooldown.

openclaw models status --json

auth.unusableProfiles

Related

Choosing providers, model refs, and failover behavior.

Claude CLI backend setup and runtime details.

How prompt caching works across providers.

Auth details and credential reuse rules.