GPT-5.6 Terra: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100%◆ (best) | 100% | 99.98% | 99.93% | 4.04s | 24.8s | 66 tps | 1.1M | $2.00 / $12.00 |
Azureazure/eu | Healthy | 100%◆ (best) | 100% | 99.99% | 100% | 2.53s | 4.50s | 82 tps | 1.1M | $2.20 / $13.20 |
OpenAIopenai | Healthy | 100%◆ (best) | 100% | 99.99% | 99.79% | 2.44s | 24.7s | 61 tps | 1.1M | $2.00 / $12.00 |
OpenAIopenai/fast | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.99% | 1.11s | 2.53s◆ (best) | 58 tps | 1.1M | $4.00 / $24.00 |
OpenAIopenai/flex | Healthy | 100%◆ (best) | 99.50% | 99.91% | 99.93% | 1.30s | 10.1s | 120 tps◆ (best) | 1.1M | $1.00 / $6.00◆ (best) |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | — | 100%◆ (best) | 100%◆ (best) | 467ms◆ (best) | 7.28s | 100 tps | 1.1M | $2.20 / $13.20 |
Azureazure/us | No data | — | 100% | 100%◆ (best) | 99.95% | 3.25s | 6.64s | 84 tps | 1.1M | $2.20 / $13.20 |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 1.1M | $4.00 / $24.00 |
- Azure100%◆ (best)Healthy24h 100%
- 7d
- 99.98%
- 30d
- 99.93%
- p50
- 4.04s
- p99
- 24.8s
- Throughput
- 66 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $12.00
azure - Azure100%◆ (best)Healthy24h 100%
- 7d
- 99.99%
- 30d
- 100%
- p50
- 2.53s
- p99
- 4.50s
- Throughput
- 82 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
azure/eu - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 99.99%
- 30d
- 99.79%
- p50
- 2.44s
- p99
- 24.7s
- Throughput
- 61 tps
- Context
- 1.1M
- $/Mtok
- $2.00 / $12.00
openai - OpenAI100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.99%
- p50
- 1.11s
- p99
- 2.53s◆ (best)
- Throughput
- 58 tps
- Context
- 1.1M
- $/Mtok
- $4.00 / $24.00
openai/fast - OpenAI100%◆ (best)Healthy24h 99.50%
- 7d
- 99.91%
- 30d
- 99.93%
- p50
- 1.30s
- p99
- 10.1s
- Throughput
- 120 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $1.00 / $6.00◆ (best)
openai/flex - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 467ms◆ (best)
- p99
- 7.28s
- Throughput
- 100 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
amazon-bedrock/us-east-1 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.95%
- p50
- 3.25s
- p99
- 6.64s
- Throughput
- 84 tps
- Context
- 1.1M
- $/Mtok
- $2.20 / $13.20
azure/us - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $4.00 / $24.00
openai/priority
Measured 3m 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, averaged over the hour.
Throughput
Median tokens per second.