docs(console): add GPT 6 Luna Decision and Gemini Decision 1 (#63440)

Co-authored-by: opencode-agent[bot] <219766164+opencode-agent[bot]@users.noreply.github.com>
This commit is contained in:
opencode-agent[bot]
2026-11-11 18:54:37 -08:00
committed by GitHub
Unverified
parent f5ca39a97d
commit 5c965609cf
@@ -113,6 +113,8 @@ translates. See [Base URLs](/console/harnesses#base-urls) for the full set.
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Mistral Large 4 | mistral-large-4 | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GPT 6 Luna Decision | gpt-6-luna-decision | `https://opencode.ai/inference/systemone/v1/systemone` | - |
| Gemini Decision 1 | gemini-decision-1 | `https://opencode.ai/inference/systemone/v1/systemone` | - |
| Jev 1.13 | jev-1.13 | `https://opencode.ai/inference/systemone/v1/systemone` | - |
| Jev 1.13 Free | jev-1.13-free | `https://opencode.ai/inference/systemone/v1/systemone` | - |
| Big Pickle | big-pickle | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -201,6 +203,26 @@ curl https://opencode.ai/inference/systemone/v1/systemone \
Use `jev-1.13-free` instead of `jev-1.13` to use the limited-time free model. See the [TypeSafe AI documentation](https://docs.typesafe.ai/) for details about question types and response fields.
### GPT 6 Luna Decision and Gemini Decision 1
`gpt-6-luna-decision` and `gemini-decision-1` take the same System One request as Jev, on the same endpoint. Pass images, audio, video, and PDFs in `state` as chat-style parts (`image_url`, `input_audio`, `video_url`, `file`). GPT 6 Luna Decision accepts text and images; Gemini Decision 1 also accepts audio, video, and PDFs.
```bash
curl https://opencode.ai/inference/systemone/v1/systemone \
-H "Authorization: Bearer $OPENCODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-decision-1",
"state": "I was charged twice for my order.",
"questions": {
"refund": {
"type": "noul",
"instructions": "Is this a refund request?"
}
}
}'
```
## Pricing
Console uses pay-as-you-go pricing. Below are the prices **per 1M tokens**.
@@ -224,6 +246,9 @@ Console uses pay-as-you-go pricing. Below are the prices **per 1M tokens**.
| Nemotron 3.5 Super VL Free | Free | Free | Free | - |
| Jev 1.13 Free | Free | Free | - | - |
| Jev 1.13 | $0.042 | Free | - | - |
| Gemini Decision 1 | $0.10 | Free | - | - |
| GPT 6 Luna Decision (≤ 272K tokens) | $0.10 | Free | $0.01 | $0.125 |
| GPT 6 Luna Decision (> 272K tokens) | $0.20 | Free | $0.02 | $0.25 |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | - |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | - |