GPT-3.5 Turbo 16k: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 782ms
- p99
- 1.32s
- Throughput
- 92 tps◆ (best)
- Context
- 16K
- $/Mtok
- $3.00 / $4.00◆ (best)
azure - No data24h 100%
- 7d
- 99.85%
- 30d
- 99.91%
- p50
- 752ms◆ (best)
- p99
- 907ms◆ (best)
- Throughput
- 61 tps
- Context
- 16K
- $/Mtok
- $3.00 / $4.00◆ (best)
openai
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.