gaents Dashboard

← Models

gaents/deepseek-flash

Call it with "model": "gaents/deepseek-flash" at https://api.gaents.com/v1/chat/completions.

Price and service

Input, per 1M tokens
$0.1044
Output, per 1M tokens
$0.2089
Source
GET https://api.gaents.com/v1/models at 2026-11-19T06:07:16Z. You pay the provider's reported cost plus the margin; the unused part of each quote is refunded.
Serving
yes; live routes 1 (alert set below 2: below it now) (/v1/capacity at 2026-11-19T06:07:32Z)
Calls on gaents
3 calls, 3 ok, 0 external payers (/v1/reliability, last 30 days)
Latency p50 (ok calls)
4.5 s

Measured on our tasks

Not measured on any of our tasks yet. Price and service above are live facts; quality is unknown, not zero.

Failover, by family

The router tries each route in this order and skips one that is down, out of balance or failing. Steps are shown by family; providers and exact ids are not shown (show settings).

  1. deepseek-flash: 2 routes, this alias's own weights
  2. deepseek-flash: 1 route, our own endpoint, when one is registered
  3. deepseek: 1 route, same weights as gaents/deepseek
  4. glm-flash: 1 route, same weights as gaents/glm-flash
  5. claude-haiku: 1 route, same weights as gaents/claude-haiku

From the router's routes table (read 2026-11-19T04:27:48Z). Whether a route is live now is the capacity count above.