1. Getting started
2. Using the API (OpenAI & Anthropic formats)
3. Autorouter
4. Quality & scoring
5. Organisations & administration
6. Identity management sync (SCIM)
7. BYOK supplier keys
8. How-to: Claude Code with TaaS
9. How-to: OpenClaw with TaaS
10. Billing & budgets

Sign in to the TaaS dashboard, open API keys and create a key. The key is shown once — store it safely. Every key is scoped to your user and, where applicable, your organisation's budgets and model policies.

curl https://taas.cloudsigma.com/v1/chat/completions \
  -H "Authorization: Bearer $TAAS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "auto", "messages": [{"role": "user", "content": "Hello TaaS"}]}'

Use model: "auto" to let the autorouter pick the best model for each request, or any model id from the model catalogue.

TaaS exposes two fully parallel API formats against the same base URL, same keys, same models and same billing:

• OpenAI-compatible — POST /v1/chat/completions (plus embeddings, rerank, audio and more; see the API reference). Works with every OpenAI SDK by setting base_url.
• Anthropic-compatible — POST /v1/messages and POST /v1/messages/count_tokens. Works with the Anthropic SDKs by setting the base URL; the key is accepted via x-api-key or Authorization: Bearer.

# Anthropic format — any TaaS model, including "auto"
curl https://taas.cloudsigma.com/v1/messages \
  -H "x-api-key: $TAAS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model": "auto", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}]}'

Both formats support streaming (SSE), tools/function calling, images and system prompts. The gateway converts between formats automatically based on the underlying model — an Anthropic-format request can address an OpenAI-backed model and vice versa, with no conversion overhead for native models.

Set model: "auto" and TaaS classifies each request (task type, difficulty, context size, tool use) and routes it to the best candidate. Variants:

• auto — balanced best fit.
• auto:price_perf — price/performance: genuinely cheaper models win when quality stays within a guarded fit floor.
• auto:cost, auto:ttft, auto:tps — cost- or latency-first selection backed by live route telemetry.
• auto:orchestrator / auto:subagent — role hints for agentic pipelines: orchestrators weight reasoning higher, subagents weight task fit. Combinable, e.g. auto:price_perf:subagent.

Admins can enforce an algorithm at organisation, department, API-key or user level from the Autorouter page, which also shows routed traffic, selection shares and per-request routing detail.

Every model has a fit profile (coding, reasoning, creative, factual, vision, tool use, reliability) seeded from public benchmarks and refined by live telemetry and qualitative outcome scoring. The Quality page breaks results out by task subtype and, for coding agents, by task focus (implementation, debugging, refactoring, long-horizon) so you can see how models perform on your actual workload — the same signals feed back into autorouting.

Organisations group users under shared budgets, model policies and administration. Org owners manage members and roles, per-org model overrides, budgets, and organisation integrations (identity sync). Domain verification lets an organisation claim an email domain so new sign-ups join automatically. TaaS platform admins additionally manage suppliers, system keys and all organisations.

Link your corporate IdP so users are provisioned and deprovisioned en masse, with IdP groups mapped to TaaS roles. TaaS implements standard SCIM 2.0, supported natively by Microsoft Entra ID and Okta.

Workflow (Dashboard → Org Integrations):

1. Configure — pick your provider (Entra ID, Okta, or generic SCIM) and a default role for provisioned users; save.
2. Connect — generate a SCIM bearer token (shown once) and enter it, together with the SCIM base URL, in your IdP's provisioning settings.
3. Test & go live — start provisioning in the IdP, then press Test connection. The status badge moves from Not configured → Awaiting first sync → Active once the first sync lands.

Microsoft Entra ID: Enterprise applications → New application → Create your own → Provisioning → Automatic; Tenant URL = the SCIM base URL, Secret token = your SCIM token; assign users/groups; start provisioning.

Okta: Applications → Browse App Catalog → SCIM 2.0 (OAuth Bearer Token) app; SCIM connector base URL = the SCIM base URL, OAuth Bearer Token = your SCIM token; enable Provisioning to App (create/update/deactivate); assign people/groups.

Role mappings: map IdP group names to TaaS roles (member, org admin, org owner) on the same page; membership changes in the IdP flow through on the next sync.

Bring your own supplier API key so all of your organisation's traffic to that supplier uses your key instead of the shared TaaS key. Managed on API keys → BYOK (organisation owners; TaaS admins can manage any organisation via the org selector). Keys are write-only — only a masked hint is shown after saving. BYOK requests are pinned to the supplier's corporate lane with no failover to other lanes.

Optionally set a budget per key (weekly, monthly, quarterly, annually or lifetime). Leave it blank for no cap. When a budget is exhausted, traffic falls back to the shared TaaS key until the period resets.

Claude Code speaks the Anthropic Messages API, which TaaS serves natively at /v1/messages — pointing it at TaaS is two environment variables:

export ANTHROPIC_BASE_URL="https://taas.cloudsigma.com"
export ANTHROPIC_AUTH_TOKEN="sk-taas-..."      # your TaaS API key
export ANTHROPIC_MODEL="auto"                  # optional: or any TaaS model id
claude

Model choice: auto engages the TaaS autorouter per request; agentic runs work well with auto:orchestrator for the main loop. All usage is metered against your TaaS key and budgets as normal.

OpenClaw can use TaaS through either API format. The simplest setup registers TaaS as an OpenAI-compatible provider:

// openclaw config — models section
{
  "models": {
    "providers": {
      "taas": {
        "baseUrl": "https://taas.cloudsigma.com/v1",
        "apiKey": "sk-taas-...",
        "api": "openai-completions",
        "models": [{ "id": "auto", "name": "TaaS autorouter" }]
      }
    }
  }
}

Set the agent's model to taas/auto (or a specific model id). For Anthropic-format integration instead, use base URL https://taas.cloudsigma.com with an anthropic provider type — both routes hit the same models, budgets and billing.

Usage is metered per token at the prices on the model catalogue, including discounted cache reads where the upstream supports caching. Budgets can be set at organisation, department, API-key and user level over the standard periods — weekly, monthly, quarterly, annually or lifetime/one-off — and BYOK supplier keys accept the same per-key budgets. The dashboard shows live spend against each budget; renewal reports can be enabled per organisation.

See also: API reference. This guide is updated as features ship.