GPT Sol Latest

The "~openai/gpt-sol-latest" slug functions as a routing alias rather than a fixed model, always pointing to the newest entry in the OpenAI GPT Sol family and at the time of the snapshot resolving to GPT-5.6 Sol. Because the alias is dynamic, anything tied to it shifts whenever OpenRouter repoints to a newer release, so it is best understood as a "track the latest" handle for users who want to stay current without manually updating their model string.

OpenRouter's listing surfaces the model as reasoning-enabled, exposing step-by-step thinking through a reasoning request parameter whose reasoning details can be preserved across conversation turns to keep multi-step reasoning coherent. Developers interact with it through an OpenAI-compatible API by swapping in the "~openai/gpt-sol-latest" slug, which makes it straightforward to drop the alias into existing SDKs and code paths that already target OpenAI-style chat completions.

OpenRouter~openai/gpt-sol-latestgpt-sol

Open provider page Provider docs

Quick Info

Provider: OpenRouter
Model key: ~openai/gpt-sol-latest
Release date: Sep 11, 2026
Last updated: Sep 11, 2026
Knowledge cutoff: 2026-02-16
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $2.00
Output token cost: $10.00

Limits

Output tokens: 128,000 tokens
Context window: 1,050,000 tokens

Transparent token rates

Compare GPT Sol Latest pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about GPT Sol Latest

OpenRouter

CoverageBenchmark

OpenAI's GPT Sol Latest is exposed on OpenRouter under the slug `openai/gpt-sol-latest`, an alias that always redirects to the current model in the GPT Sol family. At the time of retrieval the page pointed at the GPT-6.1 Sol snapshot, reflecting OpenAI's rolling-alias convention rather than a separate release. Developers invoke the model via OpenRouter's OpenAI-compatible `/api/v1/chat/completions` and `/api/v1/responses` endpoints, with no SDK changes beyond swapping the base URL. The OpenRouter page documents reasoning-token support, including reasoning-detail array propagation so conversations can resume mid-chain. It also surfaces optional `HTTP-Referer` and `X-Title` headers for OpenRouter leaderboard attribution, with example calls in TypeScript, Python, fetch, and OpenAI SDK flavors. Streaming is enabled by adding `"stream": true` to the request body for server-sent events.