Use GPT-5.5 in Kilo Code
Kilo Code runs GPT-5.5 on OceanToken with three settings: a base URL, your key and the model id. Tested on October 18, 2026 with Kilo CLI 7.8.12.
Settings
| Setting | Value |
|---|---|
| Provider ID | oceantoken |
| Provider API | OpenAI Compatible |
| Base URL | https://api.oceantoken.ai/v1 |
| API key | your OceanToken API key |
| Model | openai/gpt-5.5 |
| Reasoning | On |
| Image | On |
From the command line
{
"provider": {
"oceantoken": {
"npm": "@ai-sdk/openai-compatible",
"name": "OceanToken",
"env": [
"OCEANTOKEN_API_KEY"
],
"options": {
"baseURL": "https://api.oceantoken.ai/v1"
},
"models": {
"openai/gpt-5.5": {
"name": "GPT-5.5",
"reasoning": true,
"attachment": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 32000
}
}
}
}
},
"model": "oceantoken/openai/gpt-5.5"
}What it costs
An agent resends a long prompt on every turn, so the cached input price matters as much as the input price. GPT-5.5 caches the repeated part of the prompt on its own: from the second turn of a task it is billed at the cached input price.
About these prices
Frequently asked questions
Does GPT-5.5 work with Kilo Code’s tools?
Yes. It was tested on October 18, 2026 with Kilo CLI 7.8.12: tool calls, streaming, image input, reasoning effort and prompt caching.
How much does GPT-5.5 cost in Kilo Code?
Every request Kilo Code makes is billed at the model’s price: $4.50 / $27.00 per 1M input / output tokens. The repeated part of a long prompt is billed at $0.50 per 1M cached input tokens. Each request’s charge is in the console under Logs.
Where do I put my OceanToken key?
Create a key in the OceanToken console and give it a credit limit: an agent sends many requests, and the limit caps what this key can spend. Keep it in an environment variable, never in a file in your repository.
Other models tested with Kilo Code
Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Haiku 4.5 · DeepSeek V4 Pro · DeepSeek V4.1 Flash · Qwen3.8 Flash · GLM 5.3