GPT-5.6 Sol
GPT-5.6 Sol is a text and image-input model by OpenAI, available through the AgentSky API as openai/gpt-5.6-sol at $2.80 per million input tokens and $14.00 per million output tokens, with a 1.1M context window.
The flagship GPT-5.6 tier for complex professional work, with reasoning effort configurable from none to maximum.
Run GPT-5.6 Sol with an agent
Each guide pairs this model with a compatible agent and opens the composer with both selected.
- Hermes + GPT-5.6 Sol
- Claude Code + GPT-5.6 Sol
- Codex + GPT-5.6 Sol
- OpenClaw + GPT-5.6 Sol
- pi + GPT-5.6 Sol
- DeepSeek Harness + GPT-5.6 Sol
- Kimi Code + GPT-5.6 Sol
- OpenCode + GPT-5.6 Sol
- Cline + GPT-5.6 Sol
- DeepAgents + GPT-5.6 Sol
- goose + GPT-5.6 Sol
- Grok Build + GPT-5.6 Sol
- Kilo + GPT-5.6 Sol
- MiniMax Code + GPT-5.6 Sol
- Qwen Code + GPT-5.6 Sol
Pricing
USD per million tokens, using your plan when signed in. Each request uses the tier matching its full input context, including cached input; output tokens do not choose the tier.
| Input context (tokens) | Cache mode | Thinking | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|---|
| Up to 272,000 | Automatic | Standard | — | |||
| 272,001–1,050,000 | Automatic | Standard | — |
Use it
Point your client at the gateway and pass this model id. Nothing else changes.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gateway.agentsky.dev/v1",
apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});
const completion = await client.chat.completions.create({
model: "openai/gpt-5.6-sol",
messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response