LIVE
OPUS 4.7$15 / $75per Mtok
SONNET 4.6$3 / $15per Mtok
GPT-5.5$10 / $30per Mtok
GEMINI 3.1$3.50 / $10.50per Mtok
SWE-BENCHleader Claude Opus 4.772.1%
MMLU-PROleader Opus 4.788.4
VALS FINANCEleader Opus 4.764.4%
AFTAv1.0 whitepaper live at /whitepaper
OPUS 4.7$15 / $75per Mtok
SONNET 4.6$3 / $15per Mtok
GPT-5.5$10 / $30per Mtok
GEMINI 3.1$3.50 / $10.50per Mtok
SWE-BENCHleader Claude Opus 4.772.1%
MMLU-PROleader Opus 4.788.4
VALS FINANCEleader Opus 4.764.4%
AFTAv1.0 whitepaper live at /whitepaper
All systems operational0 AI providers monitored, polled every 2 minutes
Live status
All endpoints

What's New (Agent Brief)

1 credit
GET /api/premium/whats-new

The "what's new" endpoint is the single call an agent makes when it boots up. Returns a curated 1-7 day window across pricing changes (input/output deltas), new and removed models, status incidents that started or resolved in the period, current operational counts, and the top news headlines. Replaces the loop of "GET news, GET status, GET models, diff yesterday's snapshot" that agents would otherwise write themselves.

When to use this endpoint

On agent boot-up. The right cadence is once per session for short-lived agents, once per day for long-running agents.

Parameters

NameInTypeDescription
daysqueryintegerWindow in days (1-7, default 1)
news_limitqueryintegerMax news headlines (1-25, default 10)

* required

Example response

{
  "ok": true,
  "window": { "from": "2026-04-26T...", "to": "2026-04-27T...", "days": 1 },
  "summary": { "total_pricing_changes": 2, "new_models": 1, "incidents": 1, "news_articles": 8 },
  "pricing": {
    "changes": [{ "model": "Claude Opus 4.7", "field": "inputPrice", "from": 15, "to": 12, "delta_pct": -20 }]
  },
  "status": { "currently_operational": 8, "currently_degraded": 0, "currently_down": 0 },
  "news": [{ "title": "...", "url": "...", "published_at": "..." }]
}

Code samples

Python SDK

from tensorfeed import TensorFeed

tf = TensorFeed(token="tf_live_...")
brief = tf.whats_new(days=1, news_limit=10)
for c in brief["pricing"]["changes"]:
    print(f"{c['model']} {c['field']}: {c['from']} -> {c['to']}")

TypeScript SDK

import { TensorFeed } from 'tensorfeed';

const tf = new TensorFeed({ token: 'tf_live_...' });
const brief = await tf.whatsNew({ days: 1 });

MCP tool

Available via the TensorFeed MCP server as whats_new. Add npx -y @tensorfeed/mcp-server to your Claude Desktop or Claude Code MCP config.

Related endpoints