Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| GPT-5.6 Terra openai/gpt-5.6-terra | Jev 1.14 typesafe/jev-1.14.0 | |
|---|---|---|
| Provider | OpenAI | Typesafe |
| Family | GPT-5 | |
| Modality | text | text |
| Context window | 1,050,000 tok | 32,000 tok |
| Max output | 128,000 tok | 32,000 tok |
| Released | 2026-07-10 | 2026-10-16 |
| Input price | $2.00 /1M | $0.042 /1M |
| Output price | $12.00 /1M | $0.0000 /1M |
| Cache read | — | — |
| Tools | yes | — |
| Streaming | yes | yes |
| Vision | yes | — |
| JSON mode | yes | — |
| Reasoning | yes | — |
| Prompt caching | — | — |
GPT-5.6 Terra is an OpenAI GPT-5.6 model that balances intelligence and cost, using the Responses API for reasoning and stateful context management.
Jev (1.14) is TypeSafe's decision model for structured evaluation. Classify inputs and score decisions using typed questions, probabilities, and confidence.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try GPT-5.6 Terra
client.chat.completions.create(
model="openai/gpt-5.6-terra",
messages=[{"role":"user","content":"hello"}],
)
# Try Jev 1.14 — same client, same key
client.chat.completions.create(
model="typesafe/jev-1.14.0",
messages=[{"role":"user","content":"hello"}],
)