Anthropic

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

• API key - direct Anthropic API access with usage-based billing (anthropic/* models)
• Claude CLI - reuse an existing Claude Code login through the installed executable on the same host

Usage and cost tracking

OpenClaw detects the available Anthropic credential and selects the matching usage surface:

• OpenClaw-managed subscription/setup credentials show quota windows and optional extra-usage budget.
• Native Claude CLI logins stay under Claude's exclusive refresh control, so OpenClaw does not poll their quota endpoint.
• ANTHROPIC_ADMIN_KEY or ANTHROPIC_ADMIN_API_KEY shows 30 days of provider-reported organization cost and Messages API usage in Control UI Usage, including daily spend, token/cache totals, top models, and cost categories.
• An sk-ant-admin... credential stored in the Anthropic provider profile is detected as an Admin API key automatically.

Admin API cost history comes from Anthropic's Usage and Cost API. It is actual provider billing, separate from OpenClaw's session-derived estimated cost.

Getting started

openclaw onboard# choose: Anthropic API key

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

openclaw models list --provider anthropic

{  env: { vars: { ANTHROPIC_API_KEY: "example-anthropic-key-not-real" } },  agents: { defaults: { model: { primary: "anthropic/claude-opus-5" } } },}

claude --versionclaude auth status --text

claude auth login

claude update

openclaw onboard# choose: Claude CLI

openclaw models list --provider anthropic

openclaw models auth login --provider anthropic --method setup-token

{  agents: {    defaults: {      model: { primary: "anthropic/claude-opus-5" },      models: {        "anthropic/claude-opus-5": {          agentRuntime: { id: "claude-cli" },        },      },    },  },}

Use Claude Fable 5.1

After setting up either auth route above, select the canonical model ref:

openclaw models set anthropic/claude-fable-5-1

For Claude CLI authentication, keep that same ref and select the CLI runtime:

{  agents: {    defaults: {      model: { primary: "anthropic/claude-fable-5-1" },      models: {        "anthropic/claude-fable-5-1": {          agentRuntime: { id: "claude-cli" },        },      },    },  },}

The API and Claude CLI catalogs expose a 1,000,000-token context window and 128,000-token output limit. Fable 5.1 always uses adaptive thinking, defaults to high, and supports native low, medium, high, xhigh, and max effort. For API-key billing, input and output remain $10/$50 per million tokens; cache reads cost $0.25 per million tokens, one quarter of Fable 5's rate. See Anthropic's Fable 5.1 specifications.

The bare fable alias now selects anthropic/claude-fable-5-1. Explicit fable-5 and anthropic/claude-fable-5 selections still use Fable 5; OpenClaw does not rewrite them to Fable 5.1.

Tool calls and retained thinking

Fable 5.1 accepts automatic or disabled tool use, not forced tool calls. OpenClaw's Anthropic adapter converts a forced tool choice to auto when thinking is enabled. State in the prompt when a particular tool must run; see Anthropic's migration guide.

Fable 5.1 binds retained thinking to the preceding system prompt, tools, and conversation history. Changing that prefix can invalidate later thinking blocks. Claude Code manages this history for the CLI runtime. OpenClaw's embedded runtime uses append-only context only for prefix-binding models such as Fable 5.1: it persists hidden runtime-context carriers after their user turn, keeps earlier carriers and inline inbound metadata in place, and preserves consecutive user turns on the Messages API. This also applies to matching Claude models on Bedrock, Vertex, and Foundry, although Bedrock Converse still merges consecutive user turns. Carriers contain only the delimited context body; the instruction to use it privately lives once in the stable system prompt. Other Claude models keep transient carriers and normal user-turn merging. Transient carriers are the cheaper cache shape when thinking does not bind the prefix: old carriers consume no later context or repeated cache-read charges.

Direct Anthropic API-key requests with adaptive thinking send the thinking-binding-controls-2026-08-01 beta and thinking.block_binding.prefix_mismatch_behavior: "drop_block". Anthropic drops invalidated replayed thinking server-side, and OpenClaw logs a warning with the count and up to five affected paths. These controls are not sent for OAuth, proxies, Bedrock, Vertex, Foundry, or budget-based or disabled thinking. Client-side compaction removes stale thinking signatures; a provider-confirmed thinking rejection can still trigger one retry without prior thinking and persist the successful repair. Adaptive mode remains enabled, but a response may contain no thinking block. Integrations that build Messages API requests directly should follow Anthropic's preserved-thinking rules.

With contextPruning.mode: "cache-ttl", direct Anthropic API-key requests use server-side tool-result clearing. Anthropic's server-side clearing and compaction never invalidate Fable 5.1 thinking: the prefix check uses the history sent by the client, before those server edits. See Anthropic's context-editing contract. On other eligible routes, a client-side prune is a one-time prefix edit. OpenClaw retains that projection for later requests, so pruning does not flip back to the original bytes and invalidate newly created thinking. Earlier thinking affected by a client-side edit is handled by drop_block where the binding controls above apply, or by the existing rejection-and-repair path elsewhere.

Fable 5.1 thinking is also bound to the model that produced it. Switching a session from Fable 5.1 to any other model (Opus 5, Sonnet 5, Fable 5, or older) continues the visible conversation without Fable's earlier reasoning; Anthropic drops those blocks unbilled, and OpenClaw's embedded runtime omits them from the replay for the same result. The reverse move keeps reasoning: Fable 5.1 reads thinking produced by Opus 5, Sonnet 5, Opus 4.8, and Fable 5, so a session that moves onto Fable 5.1 replays that history intact. Switching away and back does not restore the pre-switch Fable reasoning: the switch changes the system prompt, which invalidates every earlier Fable block. On direct API-key routes Anthropic drops those blocks server-side and OpenClaw logs the drop; elsewhere, organizations that enforce the prefix check reject the request once and the embedded runtime retries without prior thinking. Changing the thinking level with /think has the same effect. Pick the model and thinking level when you start the session when reasoning continuity matters.

Claude sessions across computers

The bundled Anthropic plugin adds a Claude Code group to the normal sessions sidebar. Rows open in the normal Chat pane. It discovers non-archived Claude Code sessions on the Gateway and on connected node hosts:

• Claude CLI sessions come from valid project-index records. For unindexed transcripts, a bounded metadata fallback recognizes concurrent non-sidechain interactive (cli) and headless Agent SDK CLI (sdk-cli) sessions under ~/.claude/projects/.
• Claude Desktop sessions use the Desktop title, activity time, and archive state when its metadata points to the same Claude Code session ID.
• A CLI-only session has no archive flag, so it remains visible while its transcript is present.

Claude Code /rename titles take precedence over automatic titles and the first prompt. /color imports the matching session color; cleared or unrecognized colors stay unset. Discovery reads a bounded transcript prefix and tail, so recent metadata appended to large transcripts is included without reading the entire history. Metadata outside those windows may be unavailable. Desktop rows retain their Desktop title and remain colorless.

No additional OpenClaw config is required for discovery. The Anthropic plugin is bundled and enabled by default; a native macOS node advertises the read-only Claude session commands when the local ~/.claude/projects/ directory exists. Approve the node pairing upgrade when those commands first appear.

The sidebar groups rows by their Gateway or paired-node host and shows each host's newest bounded page as soon as that computer answers. It reconciles again after host-connectivity changes, when the page regains focus, and at most every 30 seconds while visible, so Claude sessions created outside OpenClaw appear without a reload. A changed catalog gets a faster follow-up pass. Use Load more sessions below a catalog group to append the next page for every host that has more history; appended rows stay visible and are re-fetched to the same depth across refreshes. Catalog clients use sessions.catalog.list; opening a row uses sessions.catalog.read.

Those refreshes are cheap on the Gateway: the plugin watches ~/.claude/projects/ and the Desktop session store for changes instead of re-reading them on every poll, so an unchanged tree costs no disk access and a change re-reads only the affected project directory. It re-reads the whole tree at most every five minutes as a backstop, and falls back to per-request scanning if the platform cannot provide a file watcher. Desktop metadata also refreshes every 60 seconds to pick up custom-group changes outside the watched session store. Gateway enumeration keeps each caller isolated; the plugin reuses its watched filesystem snapshot across those enumerations.

Catalog visibility follows the authenticated Gateway profile. Admin connections see every discovered Claude row, and solo or shared-secret Gateways remain unfiltered. On a multi-user Gateway, a non-admin sees only rows already adopted by their durable profile; unattributed host-discovered Claude CLI and Desktop rows stay hidden. This is a privacy control within one trusted Gateway domain; see Multi-user mode.

Terminal takeover resolves claude from the owning host user's login-shell PATH before the service/daemon PATH. This keeps app-launched sessions aligned with the Claude CLI the operator gets in a normal terminal.

Selecting a row reads the newest transcript page first. Load older transcript items follows an opaque byte cursor and reads another bounded section from the JSONL file instead of loading the entire history. Normal user, assistant, reasoning, tool-call, and tool-result content is preserved. An individual item larger than the node/Gateway safety ceiling is clearly marked as truncated.

For a Gateway-local claude-cli row, typing in the normal composer calls sessions.catalog.continue. OpenClaw re-resolves the local catalog record, creates or reuses a model-locked native session, imports at most 200 visible items or 512 KiB, and seeds the Claude CLI binding. The first turn resumes with --fork-session; Claude assigns the fork a new session ID, so later turns use the fork and the source session stays untouched.

The new OpenClaw session starts with the catalog title and color. Continuing an already adopted session preserves any title or color changes made in OpenClaw.

A headless node host can also make its Claude CLI rows continuable by enabling the node-local setting below and restarting the node host:

{  nodeHost: {    agentRuns: {      claude: { enabled: true },    },  },}

The node advertises agent.cli.claude.run.v1 only when the setting is enabled and its local claude executable resolves. OpenClaw re-resolves the catalog record on that node, imports the same bounded history, and binds the adopted session to the node and catalog-reported working directory. Each turn runs the node's real claude -p process using that node's Claude files and login. The node's exec approval policy still applies; the Gateway cannot force the opt-in.

Node continuation v1 is one-shot only. It omits Gateway loopback MCP config and Gateway skills plugin arguments, does not reseed from a Gateway transcript, and rejects attachments and images. Claude Desktop rows remain view-only. Native macOS app nodes also remain view-only until the app advertises the run command.

See Nodes: Claude sessions and transcripts for the node command and security boundary.

Live model discovery

With an Anthropic API key configured, OpenClaw refreshes the Claude catalog from Anthropic's models endpoint, so newly published snapshots of supported model families appear without an OpenClaw release. Models the shipped catalog already describes always keep their published metadata and pricing.

A newly discovered model is only offered when Anthropic's advertised capabilities match the request shaping OpenClaw would apply to it. A brand-new model generation therefore stays hidden until OpenClaw adds support for it, rather than appearing in the picker and failing every request. Discovery is advisory: without an API key, or if the endpoint is unreachable, the shipped catalog is used unchanged.

Thinking defaults (Claude Opus 5, Sonnet 5, Mythos 5, Fable 5, 4.8, and 4.6)

Bare family aliases are rolling: opus tracks the current supported Claude Opus generation and today resolves to anthropic/claude-opus-5, the same way sonnet tracks the current Sonnet. Upgrading OpenClaw can therefore move a config that says opus onto a newer model generation. Pin a version to opt out — versioned aliases such as opus-4.8 keep resolving to their own model, and configs that already name claude-opus-4-8 are never rewritten.

anthropic/claude-opus-5 uses adaptive thinking at high effort by default. Use /think off to disable thinking, or /think xhigh|max for the model's higher native effort levels. OpenClaw omits manual thinking budgets, custom sampling parameters, assistant prefills, and Priority Tier for Opus 5 because Anthropic does not support those request features on this model. The catalog publishes its 1,000,000-token context window, 128,000-token output limit, image input, and $5/$25 input/output pricing.

anthropic/claude-sonnet-5 uses the same adaptive-thinking defaults and request restrictions. The catalog uses Anthropic's standard $2/$10 input/output pricing per million tokens. Anthropic canceled the previously scheduled September 2026 increase; see current model pricing.

anthropic/claude-fable-5-1 and anthropic/claude-fable-5 always use adaptive thinking and default to high effort. Anthropic does not allow thinking to be disabled for these models, so /think off and /think minimal map to low effort instead. OpenClaw also omits caller-selected sampling parameters for both Fable versions.

anthropic/claude-mythos-5 is a limited-access model with the same always-on adaptive-thinking contract. OpenClaw defaults to high, maps /think off and /think minimal to low, and omits caller-selected sampling parameters. The catalog publishes its 1,000,000-token context window, 128,000-token output limit, image input, and $10/$50 input/output pricing.

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 (Opus 4.6 and Sonnet 4.6) default to adaptive.

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

{  agents: {    defaults: {      models: {        "anthropic/claude-opus-5": {          params: { thinking: "high" },        },      },    },  },}

Safety refusal fallback (Claude Opus 5 and Fable 5)

Why this exists

Opus 5 and Fable classifiers return stop_reason: "refusal" on requests in restricted domains. Without a fallback, the turn ends with an error even when Anthropic has a recommended model for that refusal category.

How it works

1. For every direct API-key request to anthropic/claude-opus-5, anthropic/claude-fable-5-1, or anthropic/claude-fable-5, OpenClaw sends the server-side-fallback-2026-07-01 beta header plus fallbacks: "default". Anthropic selects the recommended model for the reported refusal category.
2. Only a safety-classifier decline triggers the fallback. Rate limits, overloads, and server errors behave exactly as before and go through OpenClaw's normal model failover.
3. The rescue happens inside the same call. A decline before any output is invisible apart from latency; the whole answer comes from the serving model. On a mid-stream decline the partial text is kept as the prefix the fallback model continues from, while the declined model's reasoning and tool calls are discarded per Anthropic's replay rules (they must not be echoed back or executed).
4. If the recommended model declines as well, the turn surfaces the refusal as an error. OpenClaw does not retry a final refusal or advance to another configured model.

The fallback happens at the Anthropic API level, so the serving model does not need to be in your configured OpenClaw fallback chain.

Observability and billing

• A fallback-served turn records a provider_fallback diagnostic on the assistant message naming fromModel and toModel, and the message's responseModel reports the model that answered.
• Anthropic bills the fallback attempt at the serving model's rates. OpenClaw prices known Opus 4.8 fallback-served turns at Opus 4.8 rates.
• A mid-stream decline additionally bills the already-streamed primary-model partial on Anthropic's side; that portion is reported in the API's per-attempt usage but not folded into OpenClaw's per-turn estimate.

Scope

Applies to anthropic/claude-opus-5, anthropic/claude-fable-5-1, and anthropic/claude-fable-5 with API-key auth against api.anthropic.com. OAuth (including Claude CLI subscription reuse), proxy base URLs, Bedrock, Vertex, and Foundry requests are unchanged and still surface refusals as errors there.

See Anthropic's refusals and fallback guide for the underlying behavior.

Prompt caching

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

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

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

Advanced configuration

{  agents: {    defaults: {      models: {        "anthropic/claude-opus-5": {          params: { fastMode: true },        },      },    },  },}

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

{  agents: {    defaults: {      models: {        "anthropic/claude-sonnet-4-6": {          params: {            anthropicServerCompaction: true,            anthropicCompactThreshold: 120000,          },        },      },    },  },}

{  agents: {    defaults: {      models: {        "anthropic/claude-opus-5": {},        "anthropic/claude-sonnet-5": {},        "anthropic/claude-mythos-5": {},        "anthropic/claude-opus-4-8": {},      },    },  },}

Troubleshooting

claude auth status --textclaude auth loginopenclaw gateway restart

Related