GPT-5.6 Terra API
Model ID: gpt-5.6-terra · Developer: OpenAI · Available on 7API: yes, as of 2026-11-20
Call GPT-5.6 Terra with any OpenAI- or Anthropic-compatible client. Use base URL https://7api.st/v1 (OpenAI) or https://7api.st (Anthropic) and send "model": "gpt-5.6-terra".
Specifications
| Model ID | gpt-5.6-terra |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Input | Text |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning effort | Model default |
| API formats | Chat Completions, Responses, Anthropic Messages |
Pricing
| USD per 1M tokens | |
|---|---|
| Input | $0.45 |
| Output | $0.45 |
| Cached input | $0.04 |
For example, an agent turn with 150,000 cached input tokens, 2,000 new input tokens and 800 output tokens costs about $0.0073 on GPT-5.6 Terra. Billing is pay per token from a prepaid balance. See Pricing and billing.
Benchmarks
Independent scores for GPT-5.6 Terra, as published by third parties (retrieved 2026-10-24). 7API serves the same model, so these scores apply to it here.
| Benchmark | Result |
|---|---|
Artificial Analysis Intelligence Index, max effort | 42 |
Artificial Analysis Intelligence Index, xhigh effort | 38 |
Artificial Analysis Intelligence Index, high effort | 34 |
Artificial Analysis Intelligence Index, medium effort | 30 |
Artificial Analysis Intelligence Index, low effort | 27 |
Example
from openai import OpenAI
client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
model="gpt-5.6-terra",
messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(r.choices[0].message.content)In Claude Code: /model claude-gpt-5.6-terra. Setup guides: Claude Code, OpenCode, Codex, Cursor.
Related models
- GPT-6 Astra: $0.65/M, $0.06/M cached, 1.05M context
- GPT-6.2 Astra: $0.65/M, $0.06/M cached, 1.05M context
- GPT-6.1 Sol: $0.15/M, $0.04/M cached, 1.05M context
- GPT-6.2 Sol: $0.15/M, $0.04/M cached, 1.05M context
- GPT-6 Sol: $0.15/M, $0.04/M cached, 1.05M context
- GPT-6 Luna: $0.05/M, $0.01/M cached, 1.05M context
- GPT-5.6 Sol: $0.45/M, $0.04/M cached, 1M context
- GPT-5.6 Luna: $0.45/M, $0.04/M cached, 1M context
- GPT-5.5: $0.45/M, $0.04/M cached, 1M context
