Felo API PlatformFelo API Platform

Comparison

Felo OpenAPI vs OpenAI API

The OpenAI API is the maker's own endpoint. Felo is an OpenAI-compatible endpoint that serves the same models at rates below list — with Claude and the ⁦5,000+⁩ data APIs on the same key.

Create API keySee the price gap

  • ⁦10⁩%

    Starting rate, against the official API price

  • ⁦5,000+⁩

    APIs in the same catalog

Same model, two prices

The list column is the model's official API price; the Felo column is the rate published for that same model here. Both are read from the live catalog on every request.

OpenAI list priceFelo rate

On ⁦GPT-6.1 Terra⁩, 100M input and 10M output tokens cost ⁦$150⁩ at list price — ⁦$30⁩ here.

Rates are per 1M tokens, read from the live catalog on each request. The list column is the provider's official API price; the Felo column is what this platform charges for that route.

See every model and rate

What stays the same

Felo speaks the OpenAI Chat Completions schema, so the switch is two values — not a rewrite.

  • Your SDK: openai, the Anthropic SDK, or any client that takes a base URL.
  • Your request body: messages, tools, streaming, JSON mode.
  • Your response shape: the same fields and the same SSE frames.

If a call works against api.openai.com today, the same call works here with a different base URL and key.

What the OpenAI API doesn't include: the ⁦5,000+⁩ API catalog

Felo routes model calls and answers from a data layer too: ⁦5,000+⁩ APIs on the same key — search, page and document reading, slides and agent runs.

Search

Real-time web search with answers and cited sources.

Web Fetch

Any page as clean HTML, text or Markdown.

X Search

Posts, users, timelines and replies from X.

YouTube Subtitling

Transcripts for a video, with optional timestamps.

LiveDoc

Upload documents and URLs, then run semantic retrieval.

SuperAgent

Streaming, multi-step agent runs over SSE.

PPT

Slide decks generated page by page and exported to PPTX.

Mindmap

Structured maps from a topic or a LiveDoc.

Landing Page

Campaign pages generated as HTML.

An agent that researches, reads, remembers and ships — without a second vendor.

Browse the API directory

Claude on the same key

The same key reaches ⁦30⁩ chat models, ⁦15⁩ image models and ⁦10⁩ video models — GPT and Claude side by side, billed from one balance.

One integration, two model families, no second account.

What changes: two lines

Swap the base URL and the key. The model field still takes a model ID string from the catalog.

# before — against OpenAI
client = OpenAI(
    base_url="https://api.openai.com/v1",
    api_key=openai_key,
)

# after — the only two changed lines
client = OpenAI(
    base_url="https://openapi.felo.ai/api/v1",
    api_key=felo_key,
)

Model IDs are the catalog's own strings, and they differ from the ones you send today — check the model page for the exact ID before you flip the base URL.

Felo and the OpenAI API, in three rows

Felo API PlatformOpenAI API
Price basisFrom ⁦10⁩% of the official API priceThe official list price, billed by OpenAI
Where it runsHosted; one key across vendorsOpenAI's own API, OpenAI models only
Model familiesGPT and Claude on the same keyOpenAI models only

What the OpenAI API still does better

  • New models land on the first-party API first.
  • Fine-tuning and the Batch API are first-party features.
  • Official support, SLAs and enterprise agreements.
  • Data handling and billing under OpenAI's own terms.

If those are requirements, they decide it. If the SDK, the price and one key across vendors matter more, the rows above decide it.

OpenAI API alternative: questions before you switch

Is Felo OpenAI-compatible?

Yes. Chat calls use the OpenAI Chat Completions schema at https://openapi.felo.ai/api/v1, so the official openai SDK and any client that takes a base URL work unchanged. Anthropic clients use https://openapi.felo.ai/api — one level up, because that SDK appends /v1/messages itself.

Do I have to change my code?

Two values: base_url and api_key. The model field keeps taking a model ID string — check the model page for the exact ID in this catalog.

Why is the rate lower than OpenAI's list price?

Felo publishes its own rate for each route, starting at ⁦10⁩% of that model's official API price. The rate shown is what is charged per call; nothing is rebated afterwards.

Do I lose any model features?

The request schema is the same, so tools, streaming, JSON mode and vision inputs go through unchanged. Fine-tuning jobs and the Batch API are first-party features and are not part of this platform.

Can I still call Claude, image and video models?

Yes. The same key reaches ⁦30⁩ chat, ⁦15⁩ image and ⁦10⁩ video models, each billed at its own published rate, on the same balance.

Is there a subscription?

No. Usage is prepaid and charged per call at the published rate — no subscription, no seat fee, no minimum commitment.

Try it on one call before you switch

Create a key, add a balance from $1, and send a request with the SDK you already use.

Create API keyRead the LLM API docs