TensorFeed API

Free AI model API with no key: models grouped by provider with pricing, context windows, capability tags and a composite intelligence score with coverage metadata. Tested example included.

No API key requiredCORS enabledHTTPSFree tier

Endpoint tested and returned HTTP 200 on 2026-08-21

What is the TensorFeed API?

TensorFeed publishes AI model data grouped by provider with no API key. Each model carries input and output pricing, context window, release month, capability tags and a composite intelligence index with an explicit note of which benchmarks it was computed from.

Composite model rankings are usually opaque — a single number with no indication of what went into it. TensorFeed at least shows its working: the `intelligence` object carries the score alongside `benchmarks_used`, a `coverage` figure and a `low_coverage` flag warning when a model has been scored from too little data. That does not make the ranking authoritative, but it makes it auditable, which is more than most offer.

The response is organised provider-first, with models nested underneath, which suits rendering a grouped comparison table directly but means flattening if you want a global ranking. `tier` labels models as flagship or otherwise, and `capabilities` is a flat array of tags such as text, vision, tool-use and reasoning. The same host serves news, service status and GPU pricing endpoints from the same base path, so the model catalogue is one slice of a broader feed.

Quick facts

Base URL: https://tensorfeed.ai/api
Authentication: No API key and no account for the public endpoints. Some premium endpoints on the same host are gated.
Rate limit: No published limit. `lastUpdated` tells you how fresh the snapshot is.
Pricing: Free for the public endpoints.
CORS: Enabled — callable directly from browser JavaScript
Official docs: Read the docs

How to use the TensorFeed API

Every request below was executed against the live API on 2026-08-21, and the response shown is the real body it returned — not an illustration.

1. Fetch AI models grouped by provider

GET https://tensorfeed.ai/api/models

curl

curl 'https://tensorfeed.ai/api/models'

JavaScript (fetch)

const res = await fetch("https://tensorfeed.ai/api/models");
if (!res.ok) throw new Error(`Request failed: ${res.status}`);
const data = await res.json();
console.log(data);

Python (requests)

import requests

res = requests.get("https://tensorfeed.ai/api/models", timeout=20)
res.raise_for_status()
print(res.json())

Response — HTTP 200 (truncated)

{
  "ok": true,
  "source": "tensorfeed.ai",
  "lastUpdated": "2026-08-16",
  "providers": [
    {
      "id": "anthropic",
      "name": "Anthropic",
      "logo": "/images/providers/anthropic.png",
      "url": "https://www.anthropic.com",
      "models": [
        {
          "id": "claude-opus-5",
          "name": "Claude Opus 5",
          "inputPrice": 5,
          "outputPrice": 25,
          "contextWindow": 1000000,
          "released": "2026-07",
          "capabilities": [
            "text",
            "vision",
            "tool-use",
            "code",
            "reasoning"
          ],
          "tier": "flagship",
          "intelligence": {
            "tfii": 67.7,
            "generation": "v2",
            "low_coverage": false,
            "coverage": 1,
            "benchmarks_used": [
              "frontier_code",
              "hle_tools",
              "osworld_2",
              "browsecomp"
            ],
            "methodology_version": "1.1",
            "as_of": "2026-08-21T07:00:08.563Z"
          }
        },
        {
          "id": "claude-fable-5",
          "name": "Claude Fable 5",
          "inputPrice": 10,
          "outputPrice": 50,
          "contextWindow": 1000000,
          "released": "2026-06",
          "capabilities": [
            "text",
            "vision",
            "tool-use",
            "code"
          ],
          "tier": "flagship",
          "intelligence": {
            "tfii": 65.9,
            "generation": "v2",
            "low_coverage": false,
            "coverage": 1,
            "benchmarks_u

Parameters

Parameter	Type	Required	Description
`(none)`	n/a	Optional	The models endpoint returns the full grouped catalogue with no parameters.
`/news`	path	Optional	AI news feed on the same host.
`/status`	path	Optional	Provider service status, with summary and leaderboard variants.
`/gpu/pricing`	path	Optional	GPU rental pricing, with a time-series variant.

Response fields

okboolean: Envelope success flag.
source / lastUpdatedstring: Origin and the date of the snapshot, `YYYY-MM-DD`.
providersarray: Providers, each holding its own models.
providers[].id / name / url / logostring: Provider slug, display name, website and a site-relative logo path.
providers[].modelsarray: That provider's models.
providers[].models[].id / namestring: Model identifier and display name.
providers[].models[].inputPrice / outputPricefloat: USD per million tokens, as numbers rather than strings.
providers[].models[].contextWindowinteger: Maximum context in tokens.
providers[].models[].releasedstring: Release month as `YYYY-MM` — a month, not a date.
providers[].models[].capabilitiesarray: Tags such as `text`, `vision`, `tool-use`, `code`, `reasoning`.
providers[].models[].tierstring: Positioning label such as `flagship`.
providers[].models[].intelligenceobject: Composite score in `tfii`, plus `generation`, `coverage`, a `low_coverage` warning flag and `benchmarks_used` listing what fed the score.

What you can build with the TensorFeed API

Build a provider-grouped model comparison table
Filter models by capability tag before shortlisting
Show a capability score alongside an explicit confidence caveat
Combine model data with the GPU pricing endpoint for a cost view

Common errors and how to fix them

Cannot rank models globally

The response is grouped by provider.

Fix: Flatten the nested `models` arrays first if you want a single ordered list.

Misleading intelligence score

Some models are scored from very little benchmark data.

Fix: Check `low_coverage` and `coverage` before presenting `tfii` as meaningful, and show `benchmarks_used` alongside it.

Release date parsing fails

`released` is `YYYY-MM`, a month with no day.

Fix: Parse it as a year-month, or append a day if your date type demands one.

Logo image missing

`logo` is a site-relative path.

Fix: Prefix `https://tensorfeed.ai` before using it in an `img` tag.

TensorFeed API — frequently asked questions

Is the TensorFeed API free?

Yes, the public endpoints — models, news, status and GPU pricing — need no key. Some premium endpoints on the same host are gated.

What is the tfii score?

TensorFeed's composite intelligence index. The `intelligence` object also carries `benchmarks_used`, a `coverage` figure and a `low_coverage` flag, so you can see how much data the score rests on rather than taking it on trust.

Are the prices per token or per million?

Per million tokens, and returned as numbers rather than strings, which makes them directly comparable with other per-MTok sources.

Why is the data grouped by provider?

The structure suits rendering a grouped comparison table. If you want a global ranking, flatten the nested `models` arrays first.

Tools that pair with this API

Percentage Calculator

Calculate what X% of a number is, what percent one number is of another, and percentage increase or decrease between two values — instantly and free.

JSON to CSV Converter

Convert a JSON array of objects to CSV online. Automatic column headers from the union of all keys, delimiter choice and proper quoting — all in-browser.

CSV Column Statistics Calculator

Profile a CSV column by column: type, blanks, distinct values, min, max, mean, median, standard deviation and percentiles, plus top values — all in-browser.

TensorFeed is an independent third-party service and is not affiliated with ByteTools or ByteVancer. Details on this page were verified on 2026-08-21; always check the official documentation before relying on this API in production, as terms and limits can change.