30+ models · 13 providers · one API

Every model runs on one source of fire.

Fire is the inference engine underneath Modus Promethean — a single, model-agnostic API that routes chat, image, and speech generation across 13 providers, logs every call it will ever make, and never lets an agent touch a raw credential.

30+
Onboarded models
13
Providers behind one key
100%
Calls logged, no opt-out
0
Secrets an agent ever sees
Why fire

Built like infrastructure, not a wrapper.

Most "AI gateways" are a thin proxy in front of one provider's SDK. Fire is the pipeline every app in the Modus Promethean stack — Saga, FireScout, ImageLab, PornArt — actually runs production traffic through. What's sold here is exactly what's dogfooded internally.

Model-agnostic by design

One request shape for 30+ models across Anthropic, OpenAI, Google, Mistral, DeepSeek, and more. Swap species_name, not your integration.

Nothing gets un-logged

Every chat, image, and speech call writes to prompt_logs inside a finally block — it fires on success or failure, with no parameter to suppress it.

Multi-agent orchestration

Compose DAGs of model calls with parallel branches and real human-in-the-loop gates. Queued, resumable, billed per step — not a single opaque black box.

Vault-brokered, not exposed

Need to reach a third-party service? Fire injects the credential server-side and forwards the call — your agent's token is the badge, it never sees the key.

One api, every workload

Finance. Science. Code. Same endpoint.

Fire doesn't pick a lane. It routes each request to the model best suited for the job, and meters the same way regardless of what's on the other end of the wire.

Financial

Read the tape, not just the headline

Structured extraction, sentiment, and reasoning over filings, tickers, and market data — routed to reasoning-tier models when the analysis actually needs it.

POST /v1/chat
{ "species_name": "deepseek-reasoner" }
Scientific

Long-context synthesis, not a summary

Feed papers, datasets, and molecular data through long-context models built for reasoning across hundreds of pages, not chatting about them.

POST /v1/chat
{ "species_name": "gemini-2.5-pro" }
Coding

Codegen with an audit trail

Route to coding-tuned models for generation and review, with every prompt and diff logged — useful the day someone asks what the agent actually did.

POST /v1/chat
{ "species_name": "codestral-latest" }
Bootstrap in one request

No SDK to install. Just an API key and curl.

Get a key from the portal, then you're one request from a response — with the price you were actually charged returned inline, every time.

# chat with the default model
curl -X POST https://fire.prosaga.net/v1/chat \
  -H "Authorization: Bearer $FIRE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Hello"}]}'

# → {"content":"Hi! How can I help?","model":"Claude Sonnet 4.5",
# "meta":{"price":{"usd":0.00033375},"log_id":1661}}
Pricing

Two tiers. No hidden markup math.

Every call returns meta.price.usd — the actual amount charged, always, even when it's zero. Fire's own provider cost is never mixed into that number.

Published rate

One stable number per model

The default for new accounts. Text is billed off a daily-synced published price list; images are a flat per-image rate. What you see in the docs is what you pay — it doesn't move between calls.

  • Per-model published text pricing
  • Flat per-image rate ($0.06 standard / $0.22 premium)
  • Prepaid balance, top up via Stripe
Cost-plus

Transparent pass-through

For infra partners who want real provider cost plus a flat, disclosed markup instead of the retail list — computed fresh on every single call.

  • Provider cost × disclosed markup, every call
  • Redeemable tier codes for partner onboarding
  • Same logging and metering guarantees as retail
Accountability

Fire only sells what it's verified.

Onboarding, not just listing

A model isn't sellable until it passes a live checklist: a real call succeeds right now, usage is reported, cost is verified, a price is published. A weekly audit re-runs the same checklist — a model that dies upstream is pulled automatically, not left silently broken.

Governance-ready

Fire is a partial reference implementation of the AIGCSEP protocol (covenant.to) — a three-plane architecture separating governance, telemetry, and data, with emergency-stop hooks defined and authenticated ahead of the day they're needed.

Prepaid, fail-closed billing

A token with no resolvable billing tier is refused before any provider is ever called — a misconfigured account can't generate spend with nowhere to send the bill.

AIGCSEP covenant_level: 0
RFC 9697 reference impl
GET /v1/capabilities — no auth required
Ready when you are

Get a key. Make a call. See the price.

Free to sign up — you only pay when you top up. No card required to get your first key.