GPT-5.6 Terra API
OpenAI's GPT-5.6 model that balances intelligence and cost, with configurable reasoning.
openai/gpt-5.6-terra
Top up $20 and we add 50%. That gives you about 5.0M input tokens extra on this model, on us.
Create an accountPricing
USD per 1M tokens| Input | $2.00 |
| Output | $12.00 |
| Cached input | $0.2090% below fresh input |
| Cache write (5m) | $2.50 |
Billed per token with no minimum and no monthly fee. Price your workload
Capabilities and limits
- Context window
- 266K tokens
- Max output
- 125K tokens
- Modality
- multimodal
- Tool calling
- Supported
- Vision
- Supported
- Reasoning
- Optional
- Reasoning effort
- low, medium, high, xhigh, max (default: medium)
- Prompt caching
- Supported (automatic)
- Cache minimum
- 1K tokens
Routing
Run BiOS manages capacity for this model and fails over automatically, so there is nothing to provision and no outage of ours becomes yours.
Not sure which model to use? BiOS Adaptive routes to the best model per request, including this one.
curl https://api.runbios.ai/v1/chat/completions \
-H "Authorization: Bearer $BIOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.6-terra",
"messages": [{ "role": "user", "content": "Hello" }]
}'Existing OpenAI SDK code works by changing the base URL and the key. API overview
Model card
Curated by Run BiOS · benchmark figures, where present, are the card’s own, not our measurements
GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families.
Model details
| Property | Value |
|---|---|
| Developer | OpenAI |
| Model ID | gpt-5.6-terra |
| OpenAI default snapshot | gpt-5.6-terra |
| Input | Text, image |
| Output | Text |
| Context window | 272,000 tokens on Run BiOS (OpenAI's full window is 1,050,000 tokens) |
| Max output tokens | 128,000 |
| Knowledge cutoff | Feb 16, 2026 |
| Reasoning | Yes |
Details above are from OpenAI's official model page. Context window and input types are as served on Run BiOS.
On Run BiOS
- Configurable reasoning. Reasoning levels
low,medium,high,xhigh,max. The default ismedium. Turn reasoning off withreasoning_effort: "none"(OpenAI API) orthinking: {"type": "disabled"}(Anthropic Messages API). - Reasoning summaries. When reasoning is on, OpenAI may return a summary of the model's reasoning: in
reasoning_contenton the OpenAI API, and in thinking blocks on the Anthropic Messages API whenthinking.displayissummarized. OpenAI does not return a summary for every request. - Tool calling. Function tools with
tool_choiceauto, required, a named function or none, including parallel tool calls and together with reasoning. - Structured outputs.
response_formatwithjson_schemaorjson_object. - Image input. Text and image input, text output.
- Sampling parameters. With reasoning off,
temperature,top_pandseedare supported. With reasoning on, sampling parameters are not applied. The request is still served.stopis not supported by this model. - Prompt caching. Automatic for repeated prompt prefixes of at least 1,024 tokens. Cache reads bill at 0.1× the input rate and cache writes at 1.25×, as OpenAI charges.
- Two APIs. Works with the OpenAI Chat Completions API (
/v1/chat/completions) and the Anthropic Messages API (/v1/messages).