GPT-5.3-Codex: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
OpenAIopenai | Healthy | 100% | 100% | 99.98%◆ (best) | 99.95% | 3.46s◆ (best) | 21.3s | 79 tps◆ (best) | 400K | $1.75 / $14.00◆ (best) |
Azureazure | No data | — | 100% | 99.98% | 100% | 3.57s | 12.8s◆ (best) | 51 tps | 400K | $1.75 / $14.00◆ (best) |
OpenAIopenai/fast | No data | — | — | — | 100%◆ (best) | — | — | — | 400K | $3.50 / $28.00 |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 400K | $3.50 / $28.00 |
- OpenAI100%Healthy24h 100%
- 7d
- 99.98%◆ (best)
- 30d
- 99.95%
- p50
- 3.46s◆ (best)
- p99
- 21.3s
- Throughput
- 79 tps◆ (best)
- Context
- 400K
- $/Mtok
- $1.75 / $14.00◆ (best)
openai - No data24h 100%
- 7d
- 99.98%
- 30d
- 100%
- p50
- 3.57s
- p99
- 12.8s◆ (best)
- Throughput
- 51 tps
- Context
- 400K
- $/Mtok
- $1.75 / $14.00◆ (best)
azure - No data24h —
- 7d
- —
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $3.50 / $28.00
openai/fast - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $3.50 / $28.00
openai/priority
Measured 1m 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.