Skip to content
FluxCDNFluxCDN
esc

581 models from 80 makers

One API.Every model. Best route.

One OpenAI-compatible endpoint, one key and one Toman wallet for 581 models from 80 makers. The router sends each request the best way, and the next way if one fails.

Not writing code? Try Chat

How the router chooses

router/autoAn illustration, not live data.
  • Route ASelected
  • Route BStandby
  • Route CDegraded
581
models
80
model makers
2M
tokens, the largest context window
63
models published in the last 30 days
Models fromOpenAIQwenGoogleMistralAnthropicZ.aiNVIDIADeepSeek

Why teams put their traffic through us

What happens to a request

A request names a model, not a vendor. The router resolves that name to a ranked list of concrete endpoints, reserves credit against your wallet, and streams the first token back while the ledger settles behind it.

Read the routing docs →
  1. 01

    Authenticate and resolve

    Key hash lookup, org and project scope, allowed-model check.

  2. 02

    Filter endpoints

    Drop anything failing capability, region, policy, or breaker state.

  3. 03

    Score and rank

    Balanced, cheapest, fastest, or a pinned provider order you define.

  4. 04

    Reserve credit

    Maximum-cost hold on the wallet, released and trued up on completion.

  5. 05

    Stream, or fall back

    First token wins the attempt. A pre-token failure retries the next peer.

Every model, one price list

Frontier and open-weight models, priced per million tokens.

All 581 models →

Free plan prices, in Toman at today's rate. Plans and prices

Newest in the catalog

The models published most recently, straight from the catalog, which follows the market several times a day.

All new models →
  1. Thinking Machines: Inkling 2 MiniNov 21, 20261M context · 27,328 Toman/M input tokens
  2. RadixArk: DaisyRose 27BNov 21, 2026262K context · 54,656 Toman/M input tokens
  3. Perplexity: Embed V2 Context 0.6BNov 20, 202632K context · 0 Toman/M input tokens
  4. Perplexity: Embed V2 Context 9BNov 20, 202632K context · 0 Toman/M input tokens
  5. Qwen: Qwen3 TTS 1.7BNov 20, 20264K context · 0 Toman/M input tokens

Drop it into what you already wrote

Change the base URL and the key. Every official OpenAI client, LangChain, LlamaIndex, and the Vercel AI SDK work unmodified.

Use your key in Claude Code, Codex, Cursor and other tools →
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://ai.fluxcdn.cloud/api/v1",
    api_key=os.environ["FLUXCDN_API_KEY"],
)

resp = client.chat.completions.create(
    model="router/auto",
    messages=[{"role": "user", "content": "Hello"}],
)

print(resp.choices[0].message.content)

Enterprise

Controls your security review will actually ask about

Pin inference to a region, forbid providers that train on inputs, cap spend per project, and export an audit trail for every routing decision.

SAML and SCIM
Okta, Entra ID, and Google Workspace. Directory-synced roles, enforced sign-in, and automatic deprovisioning when someone leaves.
Regional routing
Pin a project to US-only or EU-only endpoints. Requests that cannot be served in-region fail rather than silently leaving it.
Retention policy
Zero-retention by default, with providers that train on inputs excluded at the org level. Enable logging per project when you need it.
Budgets and limits
RPM, TPM, concurrency, and daily or monthly spend ceilings per key, per project, and per organization.
Audit logs
Every key, member, policy, and routing-configuration change, with actor and timestamp, exportable to your SIEM.
Invoicing
Net-30 terms, purchase orders, committed-volume discounts, and a single monthly invoice covering every provider you route through.

Integrate once. Never migrate again.

50,000 Toman of trial credit on sign-up, 150,000 Toman more when you verify your mobile number.