OpenClawDocs
On this page

On this page

View as MarkdownView this page as plain textOpen in ChatGPTAsk questions about this pageOpen in ClaudeAsk questions about this page

Providers

Requesty

Requesty routes requests to hundreds of models behind a single OpenAI-compatible endpoint and API key, with per-request pricing and prompt caching.

Property Value
Provider requesty
Distribution Bundled with OpenClaw
Auth REQUESTY_API_KEY
API OpenAI-compatible
Base URL https://router.requesty.ai/v1/
Model catalog Auto-discovered via /v1/models/managed

Requesty ships with OpenClaw as a bundled provider plugin. No separate plugin installation is required; it updates together with OpenClaw.

Setup

  • Create an API key

    Go to app.requesty.ai, sign in or create an account, then generate an API key.

  • Run onboarding

    bash
    openclaw onboard --auth-choice requesty-api-key

    Or set the environment variable directly:

    bash
    export REQUESTY_API_KEY="<your-requesty-api-key>" # pragma: allowlist secret

  • Verify the model is available

    bash
    openclaw models list --provider requesty

    • Onboarding preserves your model entries and leaves generated catalog rows to discovery. With models.mode: "replace", it also writes the built-in catalog because that mode skips discovery.

    Non-interactive example

    bash
    openclaw onboard --non-interactive --accept-risk --skip-health \  --mode local \  --auth-choice requesty-api-key \  --requesty-api-key "$REQUESTY_API_KEY"

    Default model and catalog

    The default model is requesty/claude-sonnet-5-5.

    Once a key is configured, OpenClaw queries GET https://router.requesty.ai/v1/models/managed with that key and publishes the managed policies your key can route to, with Requesty's live prices, context window, output limit, vision, and reasoning flags. Managed policies are addressed by bare name (claude-sonnet-5-5, gpt-6-luna, gemini-3.8-flash), and Requesty picks the hosting provider. When discovery is unavailable, the static catalog keeps those three defaults addressable.

    Run /models requesty or openclaw models list --provider requesty to see the list for your key.

    Config example

    json5
    {  env: { vars: { REQUESTY_API_KEY: "<your-requesty-api-key>" } }, // pragma: allowlist secret  agents: {    defaults: {      model: { primary: "requesty/claude-sonnet-5-5" },    },  },}

    Behavior notes

    Managed policies and provider-specific ids

    Discovery lists Requesty's managed policies, which route a bare model name to the best available hosting provider under your organization's routing and compliance settings. To pin a specific host instead (vertex/claude-sonnet-4-6, bedrock/claude-sonnet-4-6), add that id under models.providers.requesty.models in your config; OpenClaw publishes authored rows alongside the discovered policies.

    Transport, reasoning, and tools

    Requests use the OpenAI-compatible chat completions path with a Bearer token built from your API key. Streaming, tool calls, and vision input work for models whose catalog flags advertise them. /think levels are sent as the standard reasoning_effort field for models that report supports_reasoning.

    Gemini-backed refs stay on the proxy-Gemini replay path: OpenClaw sanitizes Gemini thought signatures there but does not enable native Gemini replay validation.

    Prompt caching

    OpenClaw does not send Anthropic cache_control markers or enable Requesty's auto_cache. Any caching is controlled by Requesty and the upstream provider. Discovered prices include cache read and cache write rates for usage accounting; they do not enable caching.

    App attribution

    Requests to router.requesty.ai carry HTTP-Referer: https://openclaw.ai and X-Title: OpenClaw so Requesty's dashboard can attribute usage to OpenClaw. Custom headers you set elsewhere are preserved; these two are provider-owned.

    Troubleshooting
    • Discovery only runs once REQUESTY_API_KEY is configured; the list reflects what that key is approved to use.
    • If discovery fails, OpenClaw reports an unavailable catalog refresh and keeps the static rows; a rejected key is reported as an authentication failure rather than an empty catalog.
    • If a policy you expect is missing, check the key's approved models and routing policies in the Requesty dashboard.
    • When Gateway runs as a daemon, ensure REQUESTY_API_KEY is available to that process (for example in ~/.openclaw/.env or via env.shellEnv).
    Model selection

    Choosing providers, model refs, and failover behavior.
    Configuration reference

    Full OpenClaw configuration reference.
    Requesty

    Requesty dashboard, API keys, and usage analytics.
    Was this useful?