Data & providers

#The principle

The customer chooses, the platform discloses. Claude is the reference model every preset is built and evaluated on, but an agent can select a different provider/model — including OpenAI, Google, European, open-weights, and Chinese-made models — and every run shows exactly which provider processed which step, where that provider hosts inference, and what it cost.

#The model catalogue

GET /v1/models lists every selectable model, already filtered by the calling workspace's data-region policy:

bash

curl "https://api.agentflowbind.com/v1/models" -H "Authorization: Bearer afb_live_xxxxxxxxxxxx"

json

{
  "models": [
    {
      "id": "claude-sonnet-5",
      "displayName": "Claude Sonnet 5",
      "maker": "Anthropic",
      "host": "Anthropic",
      "hostRegion": "us",
      "tier": "A",
      "dataPolicy": { "retentionDays": 30, "trainingUse": false, "dpaAvailable": true }
    }
  ],
  "allowedDataRegions": "eu_us"
}

Each catalogue entry carries: maker (who made the underlying model), host (who actually operates the API you call), hostRegion (us / eu / cn / sg / global — where inference physically runs), and a dataPolicy (retentionDays, trainingUse, dpaAvailable). The console's model picker and the Your data FAQ render the same fields under friendlier labels ("Model by", "Hosted by", "Region", "Retention", "Training use", "Contract"). The same underlying open-weights model (e.g. Qwen) can appear more than once with a different host/hostRegion/dataPolicy depending on who's serving it — a maker's own cloud vs. an EU/US host are never conflated into one entry.

#Workspace data policy

A workspace sets Allowed data regions (allowedDataRegions, one of eu, eu_us, or any — eu_us is the default for EU customers). This filters GET /v1/models's results, blocks a per-run options.model override that falls outside the policy, and can only be changed by the workspace owner.

#Per-run disclosure

Every step in GET /v1/runs/:id/steps records the provider, model, and hostRegion actually used for that step — not just what the agent's config allows, but what it did:

json

{ "phase": "act", "tool": "extract_fields", "provider": "anthropic", "model": "claude-sonnet-5", "hostRegion": "us", "cost": 6 }

#Tiers

Tier	Capability	Examples
A	Full agent loop — tools, schemas, vision	Claude, GPT, Gemini
B	Structured output, limited tool calling — extraction/classification steps only	Mistral, DeepSeek, Qwen, Kimi, GLM, MiniMax
C	Open-weights, cheapest, bulk/EU-only steps	Llama/Qwen/Mistral/Gemma via Groq, Together, Fireworks, Scaleway, Nebius, or a self-hosted vLLM

Diagnose and Assess stay on a Tier A model by default; a profile can route bulk Act-phase work to a cheaper Tier B/C model. A model's per-phase cost (tokens × provider price × a margin factor that's lower for cheaper tiers) is included in a run's estimate and its final costCredits breakdown.

#Full FAQ

The complete, always-current "Where does my data go?" FAQ — providers used, sub-processors, retention, deletion, and whether Chinese-made models route through China (only if you pick the maker's own cloud; the same open-weights models are also available from EU/US hosts, labelled as such) — lives on Your data, generated from the same catalogue this page describes rather than hand-maintained separately.