OpenAI: GPT Terra Latest
openai/gpt-terra-latestThis model always redirects to the latest model in the GPT Terra family.
Providers
7 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 OpenAI | $2.00 | $12 | $0.20 | 3.18s | 71 tps | 100% |
 Azureeastus2 | $2.20 | $13 | $0.22 | 7.46s | 66 tps | 100% |
 Amazon Bedrockus-east-1 | $2.20 | $13 | $0.22 | 3.42s | 81 tps | 100% |
| Azureswedencentral | $2.20 | $13 | $0.22 | 1.94s | 72 tps | 100% |
| OpenAI | $4.00 | $24 | $0.40 | 1.21s | 68 tps | 100% |
| Azure | $2.00 | $12 | $0.20 | 5.98s | 29 tps | 99.92% |
| OpenAI | $1.00 | $6.00 | $0.10 | 1.18s | 98 tps | 99.69% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GPT Terra Latest in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GPT Terra Latest costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
Share of requests that at least one provider served successfully.
Apps
Tools that most often run GPT Terra Latest, by tokens this week.
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Explore
Other models your pass can call.
