One API key.
Every model you ship with.

5 verified models behind one endpoint that speaks both the Anthropic and OpenAI dialects. Metered per token at 85% off vendor list price. No seats, no daily caps, no sales call.

Get your API key Read the docs

10 free requests to start. No card required.

Public status page
Multi-provider failover
Anthropic + OpenAI dialects
Crypto checkout

bash

$ curl -N https://fuelofai.com/v1/chat/completions \
  -H "Authorization: Bearer $FUELOFAI_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"claude-fable-5","stream":true,
       "messages":[{"role":"user","content":"Ship it."}]}'

data: {"choices":[{"delta":{"content":"Shipping"}}]}
data: {"choices":[{"delta":{"content":" it"}}]}
data: {"choices":[{"delta":{"content":" now."}}]}
data: [DONE]

x-fuelofai-model:        claude-fable-5
x-fuelofai-tokens-in:    12
x-fuelofai-tokens-out:   9
x-fuelofai-latency-ms:   612
x-fuelofai-request-id:   req_8f2a41c0

$ curl -N https://fuelofai.com/v1/chat/completions \
  -H "Authorization: Bearer $FUELOFAI_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"claude-fable-5","stream":true,
       "messages":[{"role":"user","content":"Ship it."}]}'

data: {"choices":[{"delta":{"content":"Shipping"}}]}
data: {"choices":[{"delta":{"content":" it"}}]}
data: {"choices":[{"delta":{"content":" now."}}]}
data: [DONE]

x-fuelofai-model:        claude-fable-5
x-fuelofai-tokens-in:    12
x-fuelofai-tokens-out:   9
x-fuelofai-latency-ms:   612
x-fuelofai-request-id:   req_8f2a41c0

The request is real and copyable. The response body shown is an illustrative example.

Try it first

Run a real request before you sign up

This streams through the same routing and failover machinery as a paid call. Anonymous, rate limited by IP, and it costs you nothing.

Live playground

Anonymous · 3 runs/hour · 256 output tokens max

Prompts here are capped and shared anonymously against a demo channel. Sign up for unlimited →

Drop-in

Works with the tools already on your machine

Change a base URL and a key. Nothing else in your setup changes — open any tool below for the exact snippet.

Claude Code

Anthropic dialect. Set two env vars in ~/.claude/settings.json.

json

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://fuelofai.com",
    "ANTHROPIC_AUTH_TOKEN": "foai_live_..."
  }
}

Cursor

Settings → Models → OpenAI API Key → "Override OpenAI Base URL". Add the model slug as a custom model.

text

Base URL:  https://fuelofai.com/v1
API key:   foai_live_...
Model:     claude-fable-5

Codex CLI

Add a provider block to ~/.codex/config.toml.

toml

model_provider = "fuelofai"
model = "claude-fable-5"

[model_providers.fuelofai]
name = "FuelOfAI"
base_url = "https://fuelofai.com/v1"
env_key = "FUELOFAI_API_KEY"

Cline

Provider: "OpenAI Compatible".

text

Base URL:  https://fuelofai.com/v1
API key:   foai_live_...
Model ID:  claude-fable-5

Aider

Two environment variables, then run aider as usual.

bash

export OPENAI_API_BASE=https://fuelofai.com/v1
export OPENAI_API_KEY=foai_live_...
aider --model openai/claude-fable-5

Continue

Add a model entry to your Continue config.

yaml

models:
  - name: FuelOfAI
    provider: openai
    model: claude-fable-5
    apiBase: https://fuelofai.com/v1
    apiKey: foai_live_...

Windsurf

Settings → Cascade → add a custom OpenAI-compatible provider.

text

Base URL:  https://fuelofai.com/v1
API key:   foai_live_...
Model:     claude-fable-5

OpenCode

Custom provider in opencode.json.

json

{
  "provider": {
    "fuelofai": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://fuelofai.com/v1",
        "apiKey": "foai_live_..."
      },
      "models": { "claude-fable-5": { "name": "claude-fable-5" } }
    }
  }
}

Roo Code

API Provider: "OpenAI Compatible".

text

Base URL:  https://fuelofai.com/v1
API key:   foai_live_...
Model ID:  claude-fable-5

Kilo Code

API Provider: "OpenAI Compatible".

text

Base URL:  https://fuelofai.com/v1
API key:   foai_live_...
Model ID:  claude-fable-5

Live catalogue

Models and prices, straight from our pricing table

Only models verified on a live upstream channel are listed. Prices are in credits per million tokens, where one credit is one US dollar of vendor list-price usage.

Public models with context window and per-million-token price in credits, capabilities
Model	Context	Input / 1M	Output / 1M	Capabilities
claude-fable-5Claude Fable 5	1,000K	5.00 cr	25.00 cr	Streaming · Tools
claude-opus-5Claude Opus 5	1,000K	5.10 cr	25.10 cr	Streaming · Tools
claude-opus-4.6Claude Opus 4.6	1,000K	5.00 cr	25.00 cr	Streaming · Tools · Vision · Prompt cache
claude-opus-4.8Claude Opus 4.8	200K	5.00 cr	25.00 cr	Streaming · Tools · Vision · Prompt cache
gpt-5.6-solGPT-5.6 Sol	200K	5.00 cr	25.00 cr	Streaming · Tools · Vision

Full model details, context windows and capabilities →

Why us

Claims we can back, and nothing else

No uptime percentage we have not measured, no zero-retention promise we do not keep. Here is the honest comparison.

Feature comparison between FuelOfAI, a typical reseller, and a direct vendor account
Capability	FuelOfAI	Typical reseller	Direct vendor
Published per-token price for every modelMost resellers publish a monthly seat price and no token rate.	Yes	No	Yes
Public per-channel status page	Yes	No	Yes
Automatic failover across multiple upstream channelsA direct vendor account has exactly one place to fail.	Yes	No	No
No daily request caps	Yes	No	Yes
Streaming (SSE) on every model	Yes	Varies	Yes
Both API dialects on one key (Anthropic + OpenAI)	Yes	Varies	No
Per-request cost and request id in response headers	Yes	No	Varies

Pricing

Prepaid credits, metered per token

Pay as you go only — no seats and no monthly commitment. Credits are denominated at vendor list price and bought at a discount, so the price table above stays directly comparable to the vendor's own rates.

Starter
$15
1 credit = $1
100.00 credits
- 85% off vendor list price on every token you spend
- Credits never expire (unlike token packs)
- All published models, both API dialects
Buy Starter
Builder
Most popular
$45
1 credit = $1
320.00 credits
- 86% off vendor list price on every token you spend
- Credits never expire (unlike token packs)
- All published models, both API dialects
- Includes a 6.7% volume bonus
Buy Builder
Pro
$150
1 credit = $1
1,100.00 credits
- 86% off vendor list price on every token you spend
- Credits never expire (unlike token packs)
- All published models, both API dialects
- Includes a 10% volume bonus
Buy Pro
Scale
$750
1 credit = $1
5,750.00 credits
- 87% off vendor list price on every token you spend
- Credits never expire (unlike token packs)
- All published models, both API dialects
- Includes a 15% volume bonus
Buy Scale

How a credit works

One credit spends like one US dollar of vendor list-price usage. $45 buys 320 credits, so you pay about 14% of list price for the tokens you actually use. Usage is metered per token at the published per-model rate and rounded up to the nearest micro-credit. Full pricing detail →

Three steps

From signup to first token in about a minute

Create a key
Sign up, hit "Create key", copy it once. Keys are hashed at rest — we cannot show it again.
text
```
foai_live_xxxxxxxxxxxxxxxxxxxxxxxx
```

Point your base URL here

Anthropic-shaped tools use the root URL. OpenAI-shaped tools use /v1.

bash

export ANTHROPIC_BASE_URL=https://fuelofai.com
export ANTHROPIC_AUTH_TOKEN=foai_live_...

# or, for OpenAI-compatible tools
export OPENAI_API_BASE=https://fuelofai.com/v1
export OPENAI_API_KEY=foai_live_...

Ship

Same request bodies, same streaming format. Nothing else in your code changes.

bash

curl -N https://fuelofai.com/v1/messages \
  -H "x-api-key: $FUELOFAI_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"claude-fable-5","max_tokens":256,"stream":true,
       "messages":[{"role":"user","content":"Say hi"}]}'

Full docs →

FAQ

The questions that decide it

Token pack or credits — which do I want?

A token pack if you know you are about to do a lot of work in the next day or three: it is far cheaper per token, and the short validity window is exactly what pays for that. Credits if your usage is unpredictable or occasional — they cost a little more per token but sit on your balance indefinitely. Plenty of customers keep a credit balance as a floor and buy a pack when a sprint starts. When both are present we always spend the soonest-expiring pack first, so nothing is lost by accident.

How does billing work, and how is it rounded?

Pay as you go, metered per token at the published per-model rate. Cost is computed at full precision and then rounded up to the nearest 0.000001 credit — one micro-credit. Streaming requests place a temporary hold for the maximum possible cost and settle to the real amount when the stream ends; a cancelled stream is billed only for the tokens actually delivered.

Do input and output tokens cost the same inside a pack?

Yes. A pack is a flat bucket — input, output and reasoning tokens all draw from the same number, with no 5× multiplier on output. That is where most of a vendor bill normally goes, which is a large part of why a pack works out cheaper than metered credits.

What exactly is a credit?

One credit equals one US dollar of vendor list-price usage. You buy credits at 85% off list, so $45 buys 320credits. That keeps the price table directly comparable to the vendor's own published rates — the discount lives in what you pay for credits, not in a rewritten price sheet.

When does a pack expire, and what happens to what is left?

The clock starts when your payment confirms, not at first use, and it runs on wall-clock hours: a 2-day pack bought at 14:00 Monday expires 14:00 Wednesday. The exact timestamp is on your billing page. At expiry 10% of whatever is left converts to permanent credits, so an expired pack still leaves something on your balance. You can stack multiple packs — they add together, and we always spend the soonest-expiring one first.

Do credits expire? Can I get a refund?

Credits never expire. Token packs do — that is the trade-off for the lower price per token, softened by the 10% rollover described above. Unused credits can be refunded within 14 days of purchase, less any usage already metered; an expired pack is not refundable. Full terms are in the refund policy.

What are the rate limits?

Requests per minute, tokens per minute, requests per day and concurrent streams are all enforced per key, and the current values are shown on your dashboard. There is no daily request cap on paid balances. When you hit a limit you get a 429 with an accurate Retry-After header — never a silent stall.

What do you store about my requests?

By default we store the full request and response payload, alongside your user id and IP address, for 30 days. That is what lets us debug a failed call with you. We do not claim zero data retention while that is on. If you would rather we kept only metadata — token counts, model, latency, cost — switch on Zero Data Retention in Settings; from that moment payload storage is skipped for your account.

Are you affiliated with Anthropic, OpenAI or Google?

No. FuelOfAI is an independent API aggregator and is not affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or Google. All trademarks belong to their owners. We buy upstream capacity with our own paid accounts and resell metered access to it.

What happens when an upstream channel goes down?

Each model has an ordered list of upstream channels. A timeout, 429 or 5xx moves the request to the next channel automatically, and a repeatedly failing channel is taken out of rotation by a circuit breaker until it recovers. Once a stream has started sending bytes we do not switch mid-flight — you get a terminal error event instead, and you are billed only for what was delivered.

Which models can I use?

Only models we have verified on a live channel appear in the catalogue and in GET /v1/models. We would rather publish a short honest list than a long aspirational one.

Ship your first request in 60 seconds.

10 free requests, no card, no sales call. Bring the tools you already use.

Create free account →

FuelOfAI is an independent API aggregator and is not affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or Google. All trademarks belong to their owners.

One API key.Every model you ship with.

Run a real request before you sign up

Live playground

Works with the tools already on your machine

Models and prices, straight from our pricing table

Claims we can back, and nothing else

Prepaid credits, metered per token

Starter

Builder

Pro

Scale

From signup to first token in about a minute

Create a key

Point your base URL here

Ship

The questions that decide it

Ship your first request in 60 seconds.

One API key.
Every model you ship with.