FAQ: models and auth

Set with:

agents.defaults.model.primary

Models are provider/model refs (example: openai/gpt-5.5, anthropic/claude-sonnet-4-6). Always set provider/model explicitly. If you omit the provider, OpenClaw tries an alias match first, then a unique configured-provider match for that model id, then falls back to the configured default provider (deprecated compatibility path). If that provider no longer has the configured default model, OpenClaw falls back to the first configured provider/model instead of a stale default.

Use the strongest latest-generation model your provider stack offers, especially for tool-enabled or untrusted-input agents — weaker or over-quantized models are more vulnerable to prompt injection and unsafe behavior (see Security). Route cheaper models to routine/low-stakes chat by agent role.

Route models per agent and use sub-agents to parallelize long tasks (each sub-agent consumes its own tokens). See Models, Sub-agents, MiniMax, and Local models.

Change only the model fields — avoid full config replaces.

• /model in chat (per-session, see Slash commands)
• openclaw models set ... (updates just model config)
• openclaw configure --section model (interactive)
• edit agents.defaults.model in ~/.openclaw/openclaw.json directly

For RPC edits, inspect with config.schema.lookup first (normalized path, shallow schema docs, child summaries), then prefer config.patch over config.apply with a partial object. If you did overwrite config, restore from backup or run openclaw doctor to repair.

Docs: Models, Configure, Config, Doctor.

Yes — Ollama is the easiest path. Quick setup:

1. Install Ollama from https://ollama.com/download
2. Pull a local model, e.g. ollama pull gemma4
3. For cloud models too, run ollama signin
4. Run openclaw onboard, choose Ollama, then Local or Cloud + Local

Cloud + Local gives you cloud models plus your local Ollama models; cloud models such as kimi-k2.5:cloud need no local pull. To switch manually: openclaw models list, then openclaw models set ollama/<model>.

Smaller/heavily quantized models are more vulnerable to prompt injection. Use large models for any bot with tool access; if you use small models anyway, enable sandboxing and strict tool allowlists.

Docs: Ollama, Local models, Model providers, Security, Sandboxing.

Send /model <name> as a standalone message. See Slash commands for the full command list, including the numbered picker (/model, /model list, /model 3), /model default to clear a session override, and /model status for endpoint/API-mode detail.

Force a specific auth profile per session with @profile:

/model opus@anthropic:default/model opus@anthropic:work

To unpin a profile set with @profile, re-run /model without the suffix (e.g. /model anthropic/claude-opus-4-6), or pick the default from /model. Use /model status to confirm the active auth profile.

/model provider/model selects that exact provider route. For example, qianfan/deepseek-v4-flash and deepseek/deepseek-v4-flash are different refs even though the model id matches — OpenClaw does not silently switch providers on a bare id match.

A user-selected /model ref is strict for fallback: if that provider/model becomes unavailable, the reply fails visibly instead of falling back to agents.defaults.model.fallbacks. Configured fallback chains still apply to configured defaults, cron job primaries, and auto-selected fallback state. When a non-session-override run is allowed to use fallback, OpenClaw tries the requested provider/model first, then configured fallbacks, then the configured primary — so duplicate bare model ids never jump straight back to the default provider.

See Models and Model failover.

Yes — model choice and runtime choice are separate:

• Native Codex coding agent: set agents.defaults.model.primary to openai/gpt-5.5. Sign in with openclaw models auth login --provider openai for ChatGPT/Codex subscription auth.
• Direct OpenAI API tasks outside the agent loop: configure OPENAI_API_KEY for images, embeddings, speech, realtime, and other non-agent OpenAI API surfaces.
• OpenAI agent API-key auth: /model openai/gpt-5.5 with an ordered openai API-key profile.
• Sub-agents: route coding tasks to a Codex-focused agent with its own openai/gpt-5.5 model.

See Models and Slash commands.

• Per session: send /fast on while using openai/gpt-5.5.
• Per model default: set agents.defaults.models["openai/gpt-5.5"].params.fastMode to true.
• Automatic cutoff: /fast auto or params.fastMode: "auto" runs new model calls fast until the cutoff, then runs later retry, fallback, tool-result, or continuation calls without fast mode. Cutoff defaults to 60 seconds; override with params.fastAutoOnSeconds on the model.

{  agents: {    defaults: {      models: {        "openai/gpt-5.5": {          params: {            fastMode: "auto",            fastAutoOnSeconds: 30,          },        },      },    },  },}

Fast mode maps to service_tier = "priority" on native OpenAI Responses requests; existing service_tier values are preserved and fast mode does not rewrite reasoning or text.verbosity. Session /fast overrides beat config defaults.

See Thinking and fast mode and the Fast mode section under Advanced configuration on the OpenAI provider page.

If agents.defaults.models is set, it becomes the allowlist for /model and session overrides. Picking a model outside that list returns this instead of a normal reply:

Model "provider/model" is not allowed. Use /models to list providers, or /models <provider> to list models.Add it with: openclaw config set agents.defaults.models '{"provider/model":{}}' --strict-json --merge

Fix: add the exact model to agents.defaults.models, add a provider wildcard such as "provider/*": {} for dynamic catalogs, remove the allowlist, or pick a model from /model list. If the command also included --runtime codex, update the allowlist first, then retry the same /model provider/model --runtime codex command.

If you're on an older OpenClaw release, upgrade first (or run from source main) and restart the gateway — MiniMax-M3 may not be in your installed release's catalog yet. Otherwise the MiniMax provider is not configured (no provider entry or auth profile found), so the model can't resolve. See the Troubleshooting section on the MiniMax provider page for the full fix checklist, provider/model id table, and config-block example.

Yes. Use MiniMax as the default and switch models per session — fallbacks are for errors, not "hard tasks", so use /model or a separate agent.

Option A: switch per session

{  env: { MINIMAX_API_KEY: "sk-...", OPENAI_API_KEY: "sk-..." },  agents: {    defaults: {      model: { primary: "minimax/MiniMax-M3" },      models: {        "minimax/MiniMax-M3": { alias: "minimax" },        "openai/gpt-5.5": { alias: "gpt" },      },    },  },}

Then /model gpt.

Option B: separate agents — Agent A defaults to MiniMax, Agent B defaults to OpenAI; route by agent or use /agent to switch.

Docs: Models, Multi-Agent Routing, MiniMax, OpenAI.

Yes — built-in shorthands, applied only when the target model exists in agents.defaults.models:

Your own alias with the same name overrides the built-in one.

Aliases live at agents.defaults.models.<modelId>.alias:

{  agents: {    defaults: {      model: { primary: "anthropic/claude-opus-4-6" },      models: {        "anthropic/claude-opus-4-6": { alias: "opus" },        "anthropic/claude-sonnet-4-6": { alias: "sonnet" },      },    },  },}

Then /model sonnet (or /<alias> when supported) resolves to that model id.

OpenRouter (pay-per-token; many models):

{  agents: {    defaults: {      model: { primary: "openrouter/anthropic/claude-sonnet-4-6" },      models: { "openrouter/anthropic/claude-sonnet-4-6": {} },    },  },  env: { OPENROUTER_API_KEY: "sk-or-..." },}

Z.AI (GLM models):

{  agents: {    defaults: {      model: { primary: "zai/glm-5.1" },      models: { "zai/glm-5.1": {} },    },  },  env: { ZAI_API_KEY: "..." },}

Missing provider key for a referenced provider/model raises a runtime auth error (e.g. No API key found for provider "zai").

No API key found for provider after adding a new agent

A new agent has an empty auth store — auth is per-agent, stored at:

~/.openclaw/agents/<agentId>/agent/auth-profiles.json

Fix: run openclaw agents add <id> and configure auth in the wizard, or copy only portable static api_key/token profiles from the main agent's store. For OAuth, sign in from the new agent when it needs its own account. See Multi-Agent Routing for the full agentDir reuse and credential-sharing rules — never reuse agentDir across agents.

Two stages:

1. Auth profile rotation within the same provider.
2. Model fallback to the next model in agents.defaults.model.fallbacks.

Cooldowns apply to failing profiles (exponential backoff), so OpenClaw keeps responding when a provider is rate-limited or temporarily failing.

The rate-limit bucket covers more than plain 429: Too many concurrent requests, ThrottlingException, concurrency limit reached, workers_ai ... quota limit exceeded, resource exhausted, and periodic usage-window limits (weekly/monthly limit reached) all count as failover-worthy rate limits.

Billing responses aren't always 402, and some 402s stay in the transient/rate-limit bucket rather than the billing lane. Explicit billing text on 401/403 can still route to billing; provider-specific text matchers (e.g. OpenRouter Key limit exceeded) stay scoped to their own provider. A 402 that reads like a retryable usage-window or org/workspace spend limit (daily limit reached, resets tomorrow, organization spending limit exceeded) is treated as rate_limit, not a long billing disable.

Context-overflow errors stay off the fallback path entirely — signatures like request_too_large, input exceeds the maximum number of tokens, input token count exceeds the maximum number of input tokens, input is too long for the model, or ollama error: context length exceeded go to compaction/retry instead of advancing model fallback.

Generic server-error text is narrower than "anything with unknown/error in it". Provider-scoped transient shapes that do count as failover signals: Anthropic bare An unknown error occurred, OpenRouter bare Provider returned error, stop-reason errors like Unhandled stop reason: error, JSON api_error payloads with transient server text (internal server error, unknown error, 520, upstream error, backend error), and provider-busy errors like ModelNotReadyException when the provider context matches. Generic internal fallback text like LLM request failed with an unknown error. stays conservative and does not trigger fallback by itself.

The auth profile id anthropic:default has no credentials in the expected auth store.

Fix checklist:

• Confirm where profiles live — current: ~/.openclaw/agents/<agentId>/agent/auth-profiles.json; legacy: ~/.openclaw/agent/* (migrated by openclaw doctor).
• Confirm the Gateway loads your env var. ANTHROPIC_API_KEY set only in your shell won't reach a Gateway run via systemd/launchd — put it in ~/.openclaw/.env or enable env.shellEnv.
• Confirm you're editing the right agent — multi-agent setups have multiple auth-profiles.json files.
• Run openclaw models status to see configured models and provider auth state.

For "No credentials found for profile anthropic" (no email suffix):

The run is pinned to an Anthropic profile the Gateway can't find.

• Use Claude CLI: run openclaw models auth login --provider anthropic --method cli --set-default on the gateway host.

• Prefer an API key instead: put ANTHROPIC_API_KEY in ~/.openclaw/.env on the gateway host, then clear any pinned order that forces the missing profile:

  openclaw models auth order clear --provider anthropic

• Remote mode: auth profiles live on the gateway machine, not your laptop — confirm you're running commands there.

If your model config includes Google Gemini as a fallback (or you switched to a Gemini shorthand), OpenClaw tries it during fallback. No Google credentials configured gives No API key found for provider "google". Fix: add Google auth, or remove Google models from agents.defaults.model.fallbacks/aliases.

LLM request rejected: thinking signature required (Google Antigravity)

Cause: session history has thinking blocks without signatures (often from an aborted/partial stream); Google Antigravity requires signatures on thinking blocks. OpenClaw strips unsigned thinking blocks for Google Antigravity Claude; if it still appears, start a new session or set /thinking off for that agent.

A named credential record (OAuth or API key) tied to a provider, stored at:

~/.openclaw/agents/<agentId>/agent/auth-profiles.json

Inspect saved profiles without dumping secrets: openclaw models auth list (optionally --provider <id> or --json). See Models CLI.

Provider-prefixed: anthropic:default (common when no email identity exists), anthropic:<email> for OAuth identities, or a custom id you choose (e.g. anthropic:work).

Yes. auth.order.<provider> config sets rotation order per provider (metadata only — no secrets stored).

OpenClaw may skip a profile in a short cooldown (rate limits, timeouts, auth failures) or a longer disabled state (billing/insufficient credits). Inspect with openclaw models status --json and check auth.unusableProfiles. Tune with auth.cooldowns.billingBackoffHours*. Rate-limit cooldowns can be model-scoped — a profile cooling down for one model can still serve a sibling model on the same provider; billing/disabled windows block the whole profile.

Set a per-agent order override (stored in that agent's auth-state.json):

# Defaults to the configured default agent (omit --agent)openclaw models auth order get --provider anthropic # Lock rotation to a single profileopenclaw models auth order set --provider anthropic anthropic:default # Or set an explicit order (fallback within provider)openclaw models auth order set --provider anthropic anthropic:work anthropic:default # Clear override (fall back to config auth.order / round-robin)openclaw models auth order clear --provider anthropic # Target a specific agentopenclaw models auth order set --provider anthropic --agent main anthropic:default

Verify what will actually be tried: openclaw models status --probe. A stored profile omitted from an explicit order reports excluded_by_auth_order instead of being tried silently.

• OAuth / CLI login often uses subscription access where the provider supports it. For Anthropic, OpenClaw's Claude CLI backend uses Claude Code claude -p, which Anthropic currently treats as Agent SDK/programmatic usage drawing from subscription usage limits — see Anthropic for the current billing-pause status and source links.
• API keys use pay-per-token billing.

The wizard supports Anthropic Claude CLI, OpenAI Codex OAuth, and API keys.