Anthropic builds the Claude model family and provides access via an API and Claude CLI. In OpenClaw, Anthropic API keys and Claude CLI reuse are both supported. Existing legacy Anthropic token profiles are still honored at runtime if they are already configured.
Best for: standard API access and usage-based billing. Create your API key in the Anthropic Console.
openclaw onboard
# choose: Anthropic API key
# or non-interactive
openclaw onboard --anthropic-api-key "$ANTHROPIC_API_KEY"
{
env: { ANTHROPIC_API_KEY: "sk-ant-..." },
agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
}
adaptive thinking in OpenClaw when no explicit thinking level is set./think:<level>) or in model params:
agents.defaults.models["anthropic/<model>"].params.thinking.OpenClaw’s shared /fast toggle also supports direct public Anthropic traffic, including API-key and OAuth-authenticated requests sent to api.anthropic.com.
/fast on maps to service_tier: "auto"/fast off maps to service_tier: "standard_only"{
agents: {
defaults: {
models: {
"anthropic/claude-sonnet-4-6": {
params: { fastMode: true },
},
},
},
},
}
Important limits:
api.anthropic.com requests. If you route anthropic/* through a proxy or gateway, /fast leaves service_tier untouched.serviceTier or service_tier model params override the /fast default when both are set.usage.service_tier. On accounts without Priority Tier capacity, service_tier: "auto" may still resolve to standard.OpenClaw supports Anthropic’s prompt caching feature. This is API-only; legacy Anthropic token auth does not honor cache settings.
Use the cacheRetention parameter in your model config:
| Value | Cache Duration | Description |
|---|---|---|
none | No caching | Disable prompt caching |
short | 5 minutes | Default for API Key auth |
long | 1 hour | Extended cache |
{
agents: {
defaults: {
models: {
"anthropic/claude-opus-4-6": {
params: { cacheRetention: "long" },
},
},
},
},
}
When using Anthropic API Key authentication, OpenClaw automatically applies cacheRetention: "short" (5-minute cache) for all Anthropic models. You can override this by explicitly setting cacheRetention in your config.
Use model-level params as your baseline, then override specific agents via agents.list[].params.
{
agents: {
defaults: {
model: { primary: "anthropic/claude-opus-4-6" },
models: {
"anthropic/claude-opus-4-6": {
params: { cacheRetention: "long" }, // baseline for most agents
},
},
},
list: [
{ id: "research", default: true },
{ id: "alerts", params: { cacheRetention: "none" } }, // override for this agent only
],
},
}
Config merge order for cache-related params:
agents.defaults.models["provider/model"].paramsagents.list[].params (matching id, overrides by key)This lets one agent keep a long-lived cache while another agent on the same model disables caching to avoid write costs on bursty/low-reuse traffic.
amazon-bedrock/*anthropic.claude*) accept cacheRetention pass-through when configured.cacheRetention: "none" at runtime.cacheRetention: "short" for Claude-on-Bedrock model refs when no explicit value is set.Anthropic’s 1M context window is beta-gated. In OpenClaw, enable it per model
with params.context1m: true for supported Opus/Sonnet models.
{
agents: {
defaults: {
models: {
"anthropic/claude-opus-4-6": {
params: { context1m: true },
},
},
},
},
}
OpenClaw maps this to anthropic-beta: context-1m-2025-08-07 on Anthropic
requests.
This only activates when params.context1m is explicitly set to true for
that model.
Requirement: Anthropic must allow long-context usage on that credential.
Note: Anthropic currently rejects context-1m-* beta requests when using
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.
The bundled Anthropic claude-cli backend is supported in OpenClaw.
claude -p usage as
sanctioned for this integration unless Anthropic publishes a new policy.claude -p, and Anthropic staff told us OpenClaw-style Claude CLI usage is
allowed again. We are treating that guidance as settled unless Anthropic
publishes a new policy change.claude -p when available.401 errors / token suddenly invalid
No API key found for provider “anthropic”
openclaw models status.No credentials found for profile anthropic:default
openclaw models status to see which auth profile is active.No available auth profile (all in cooldown/unavailable)
openclaw models status --json for auth.unusableProfiles.More: /gateway/troubleshooting and /help/faq.