DeepSeek: DeepSeek V3.2 Performance
Try DeepSeek V3.2 on us. Starter credit covers your first requests, then one key reaches all 9 provider routes with automatic failover.
deepseek/deepseek-v3.2
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for DeepSeek: DeepSeek V3.2. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| amazon-bedrock | 1402 ms | 1972 ms | — | 100.00% | — | 3 |
| io-net | 1787 ms | 1787 ms | — | 100.00% | — | 1 |
| digitalocean | 1793 ms | 2734 ms | — | 100.00% | — | 3 |
| venice | 1818 ms | 9704 ms | — | 100.00% | — | 2 |
| atlas-cloud | 2511 ms | 2511 ms | — | 100.00% | — | 1 |
| sambanova | 3287 ms | 5348 ms | — | 83.33% | — | 6 |
| friendli | 6140 ms | 11838 ms | — | 100.00% | 1 provider_error |
5 |
| chutes | 9622 ms | 11833 ms | — | 100.00% | — | 2 |
Full provider & model leaderboard.
9 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.