LIVE
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms
All endpoints

Uptime Rollup

1 credit
GET /api/premium/history/status/uptime

The uptime endpoint returns a daily rollup of one provider's status over a date range: operational day count, degraded day count, down day count, an SLA-style uptime percentage, and an incident_days list. Degraded days count as half-credit for the uptime calc; missing-data days are excluded from the denominator so a brief gap in our capture does not skew the result.

When to use this endpoint

When you need an SLA-grade uptime report on a specific provider, or when you want to surface provider reliability in a procurement decision.

Parameters

NameInTypeDescription
provider*querystringProvider name (anthropic, openai, google, etc.)
fromquerystringStart date YYYY-MM-DD UTC
toquerystringEnd date YYYY-MM-DD UTC

* required

Example response

{
  "ok": true,
  "provider": "anthropic",
  "days_total": 27,
  "days_with_data": 27,
  "days_operational": 24,
  "days_degraded": 2,
  "days_down": 1,
  "uptime_pct": 92.59,
  "incident_days": [
    { "date": "2026-04-09", "status": "degraded" },
    { "date": "2026-04-17", "status": "down" }
  ]
}

Code samples

Python SDK

from tensorfeed import TensorFeed

tf = TensorFeed(token="tf_live_...")
uptime = tf.status_uptime(provider="anthropic")
print(f"{uptime['uptime_pct']}% uptime")

TypeScript SDK

import { TensorFeed } from 'tensorfeed';

const tf = new TensorFeed({ token: 'tf_live_...' });
const u = await tf.statusUptime({ provider: 'anthropic' });

MCP tool

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

FAQ

How is uptime % calculated?

(days_operational + days_degraded * 0.5) / days_with_data * 100. Down days count zero. Days where we did not capture status data (any reason) are excluded from the denominator so brief outages in our own monitoring do not penalize the provider.

Related endpoints