> ## Documentation Index
> Fetch the complete documentation index at: https://docs.flatkey.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Flatkey Model Health: Live Success Rates and Latency

> Flatkey tracks real-time success rates, average latency, and request volume for every supported model. All metrics come from production traffic, not synthetic tests.

Flatkey measures the health of every model based on real production traffic routed through the platform — not synthetic benchmarks. Health metrics are updated daily and reflect the last 30 days of actual requests.

## What health metrics mean

| Metric                  | Description                                                             |
| ----------------------- | ----------------------------------------------------------------------- |
| **30-day success rate** | Percentage of requests that completed without error in the last 30 days |
| **Average latency**     | Mean time to full response across all requests in the last 30 days      |
| **30-day volume**       | Total number of requests and tokens for the period                      |

A "success" means the upstream vendor returned a valid completion response. Errors caused by invalid prompts or context-length violations are counted separately.

## Platform-wide stats

Across all models and providers, Flatkey achieves:

* **99.9% average 30-day success rate** — measured on production traffic
* **Automatic failover** — when a provider endpoint degrades, Flatkey routes to a healthy alternative
* **Live dashboards** — health data refreshed daily from real traffic

## Top models by usage (recent)

The following models have the highest traffic volume on the Flatkey platform:

| Rank | Model             | Monthly tokens | Traffic share |
| ---- | ----------------- | -------------- | ------------- |
| 1    | gpt-5.5           | 7.9T           | 39.2%         |
| 2    | deepseek-v4-flash | 210B           | 1.0%          |
| 3    | claude-sonnet-4-6 | 70B            | 0.4%          |

This leaderboard updates daily. See the full live ranking at [flatkey.ai/rankings](https://flatkey.ai/rankings).

## How to use health data

When choosing a model for production:

1. **Prefer high success-rate models** for reliability-sensitive workloads.
2. **Check average latency** for real-time or streaming applications where time-to-first-token matters.
3. **Monitor your own usage** in the [Usage dashboard](/dashboard/usage) — filter by model to see your success rate.

<Tip>
  For critical production workloads, choose models with a 30-day success rate above 99.5%. The [Model Directory](https://flatkey.ai/models) shows health data alongside pricing so you can optimize for both cost and reliability.
</Tip>

## Failover behavior

Flatkey monitors upstream provider health continuously. When a provider returns elevated error rates or latency spikes:

* Requests are automatically retried on a healthy provider endpoint.
* Your client receives a valid response without needing to implement retry logic.
* The failover is transparent — you see a successful response, not an error.

This mechanism underpins the 99.9% platform success rate. You benefit from it automatically without any configuration.

## Viewing live health data

Real-time model health, latency rankings, and volume data are available at:

* [flatkey.ai/rankings](https://flatkey.ai/rankings) — full leaderboard with token volume and share
* [flatkey.ai/models](https://flatkey.ai/models) — per-model health alongside pricing