FlowManner
Chat
Sign InGet Started
Flowmanner
Menu
  • Chat
  • Agents
  • Pricing
  • Docs
  • About
Products
  • Workflows
  • Templates
  • Changelog
  • Missions
Resources
  • Blog
  • API Reference
More
  • Careers
  • Contact
  • Security
  • Start
    • Quickstart
    • Your First Mission
    • Your First Eval
  • How-to
    • Connect Your Own Keys (BYOK)
    • Switch Models Per Task
    • Publish a Template
    • Run Evaluations
    • Chat with Artifacts & Previews
    • Automate via the API
    • Webhooks & Triggers
  • Concepts
    • Glossary
    • Execution Model
    • Models & Routing
    • Sandboxes & Previews
    • Memory & Privacy
    • Trust Model
  • Reference
    • Reference · API
      • Authentication
      • Missions & Runs
      • Chat & Sandboxes
      • Blueprints, Graphs & Templates
      • Evaluations & Feedback
      • Marketplace & Community
      • Files & Exports
      • Integrations & Webhooks
      • Agents & Orchestration
      • Auth, Workspaces & Billing
      • Memory & Knowledge
      • Notifications
      • Platform Services
    • Errors
    • Models
    • Limits

Models & Routing

Platform key vs BYOK, tolerant key matching, wire-spelling rewrites, reasoning budgets.

Two key sources

  • Platform key — Flowmanner's own provider keys back your calls within plan limits.
  • BYOK — your stored provider keys are preferred for your missions; keys are encrypted at rest and relayed server-side (see Connect BYOK).

Tolerant matching, strict gateways

Routing matches a requested model id against each key's declared model list suffix-tolerantly (llm_router.py:858-870). When the match was suffix-only, Flowmanner sends the key's declared spelling on the wire, because strict gateways reject spellings they did not declare — e.g. a bare deepseek-v4-flash sent to a gateway declaring deepseek-chat/deepseek-v4-flash fails with 400 invalid model format. Expected format: modelType/model (llm_router.py:512-524, defect fixed 2026-08-24).

Your results and logs keep showing your original id; only the outbound payload spelling changes.

Reasoning-model quirk

Reasoning-style models spend part of the context window on internal reasoning before answering. When you cap output tokens, leave headroom or answers can come back truncated.

Last updated 2026-08-25 (git-derived)

  • Two key sources
  • Tolerant matching, strict gateways
  • Reasoning-model quirk