KovAPIKovAPI
Chat ● Operational Service status →

GPT-6.2 Sol

⧉
gpt-6.2-sol
Model Type Astra6.2 Astra6.2 Sol6.1 SolSolLuna

GPT-6.2 Sol is the new Sol that OpenAI released alongside GPT-6.2 Astra on November 17, 2026, at the same list price as GPT-6.1 Sol ($2 input and $10 output per million tokens), a quarter of Astra's. It has a 1,050,000-token context, up to 128,000 output tokens per call, reasoning_effort in five steps (low / medium / high / xhigh / max), image input, tool calling and structured output. Fully OpenAI-SDK compatible: set model to gpt-6.2-sol on /chat/completions or /responses. Pay-as-you-go, failed calls are never billed; cached input bills at one twentieth of the input rate, and we do not add the official surcharge for prompts above 272,000 tokens.

ChatGPT-6 familyAgentic coding1.05M contextPrompt caching

Live Test · Playground

Try out GPT-6.2 Sol right here (available after login).

Input

Advanced

The upstream for this model does not accept temperature / top_p / max_tokens (they are silently ignored). Use reasoning_effort below for thinking depth, and prompt wording for length.

Web search
Memory · multi-turn

Conversation

Start a conversationType a message below to begin

About GPT-6.2 Sol

GPT-6.2 Sol is the new Sol OpenAI released alongside GPT-6.2 Astra on November 17, 2026, served on KovAPI through the OpenAI-compatible API. Its list price matches GPT-6.1 Sol at $2 input and $10 output per million tokens, a quarter of Astra's. It has a 1,050,000-token context, up to 128,000 output tokens per call, reasoning_effort in five steps (low / medium / high / xhigh / max), image input, tool calling and structured output, on both /chat/completions and /responses. Set model to gpt-6.2-sol. Pay-as-you-go, failed calls are never billed, and cached input settles at one twentieth of the input rate.

Use cases

Everyday coding workhorse

Writing features, fixing bugs, reading code, adding tests: most coding work fits Sol at a quarter of Astra's cost.

Agentic workflows

Long tasks that plan, call tools and check their own work. Tool calls come back in the OpenAI format, so Codex, Cursor and similar tools switch with one field.

Professional documents and analysis

Report writing, spreadsheet and data analysis, long-document review, with a 1,050,000-token context that reads the whole file at once.

Structured batch processing

Strict json_schema output is steady enough for batch extraction, classification and rewriting; long repeated prefixes that hit the cache bill at one twentieth.

How to choose

Pick GPT-6.2 Sol for most coding, agent and analysis work: it is the best value. Give the hardest, deepest reasoning to GPT-6.2 Astra from the same release, and use GPT-6 Luna for simpler high-volume jobs. They all belong to the GPT-6 family and share a 1,050,000-token context, so switching is a one-field change.

FAQ

How is it different from GPT-6.1 Sol?
GPT-6.2 Sol is the new Sol OpenAI released with GPT-6.2 Astra in November, at the same list price as GPT-6.1 Sol ($2 / $10) and with the same context and output limits; on KovAPI the two cost the same.
How does it compare with GPT-6.2 Astra?
Astra is the flagship of the same release, for the hardest reasoning. Sol's list price is a quarter of Astra's, which makes it the better buy for everyday coding and agent work. Integration is identical.
Which reasoning_effort levels are supported?
Five: low / medium / high / xhigh / max. The upstream rejects none and minimal, so the gateway maps both to low. When omitted the gateway requests medium and returns the thinking summary; more thinking means more output tokens, billed at actual usage.
What are the context and output limits?
A 1,050,000-token context and up to 128,000 output tokens per call. The official API charges more for prompts above 272,000 tokens; we do not.
How is caching billed?
Cached input settles at one twentieth of the input rate ($0.03 per million tokens). The upstream decides what is cached, and a hit is not guaranteed every time.
Am I charged for failed calls?
No. Only calls that return a proper response are settled at actual usage; upstream errors and timeouts never touch your balance.

Related Models

Explore other models you can integrate.

View all →