Cheaper Inference
Model record / OpenAI
gpt-5.6-terra
Access gpt-5.6-terra from OpenAI through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Text generationVision inputReasoningStreaming38% below list
What you pay
Current catalog rates.
Input / 1M tokens$2.00 list$1.233015
Output / 1M tokens$12.00 list$7.398089
Cached input / 1M tokens$0.246603
Current discount38%
Requests above -1 input tokens use $1.233015 input and $7.398089 output per 1M tokens.
Observed reliability
98.91
Successful provider-reaching requests
Output speed
138.5
Median tokens per second over sustained generations
TTFT
4.3 s
p50 · p90 11.5 s · n 3,224
Latency
7.3 s
p50 · p90 39.9 s · n 11,657
Evidence strength
—
At a glance
- Provider
- OpenAI
- Model ID
- gpt-5.6-terra
- Type
- Text generation
- Endpoints
- /v1/chat/completions, /v1/responses, /v1/messages
- Input
- image, pdf, text
- Output
- text
- Vision input
- Supported
- Image editing
- Not supported
- Video input
- Not supported
- Reasoning
- Supported
- Streaming
- Supported
- Context window
- 1,050,000 tokens
Parameters by endpoint
The request field of each parameter on each endpoint, and the values it takes.
POST /v1/chat/completions
| Field | Values |
|---|---|
| reasoning.exclude | |
| max_tokens | |
| reasoning | effort: none, minimal, low, medium, high, xhigh, max; enabled: true or false |
| response_format | |
| stop | |
| temperature | |
| tool_choice | |
| tools |
POST /v1/messages
| Field | Values |
|---|---|
| max_tokens | |
| thinking |
Pricing history
See how much this model saves and when its recorded price has been lowest.
Time zone
gpt-5.6-terra
Growing confidenceThis model averaged 45.8% below comparable direct provider prices across the selected range. Its strongest observed window was 8:00 PM–12:00 AM in UTC.
Last 24 hours
Average saved
45.8%
Last 24 hours
Cheapest time
8:00 PM–12:00 AM
60.0% average savings
Hourly coverage
23/24
23 total observations
Signal quality
Growing
Ready for planning
Typical unit savings$1.83 / 1M input tokens$8.25 / 1M output tokens
When this model is cheapest
Each bar is the average discount for that hour in UTC (UTC). Missing bars mean no observation was recorded.
ObservedCheapestNo data
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#33
of 408 ranked models
Last 7 days
#32
of 418 ranked models
Last 30 days
#25
of 418 ranked models
Ready when you are
Stop paying list price for tokens.
Marketplace pricing, capped at list, optimized further.