NewHow we catch a seller listing the wrong model, and refund you if one does.
OpenAI logo

How do I use GPT-6.2 Sol in Codex CLI?

openai/gpt-6.2-sol

Codex CLI reaches GPT-6.2 Sol through the Responses API of MartLLM. In ~/.codex/config.toml, add a model provider with base_url set to https://api.martllm.com/v1 and wire_api = "responses", put your MartLLM key in the UBERLLM_API_KEY environment variable, and set model to openai/gpt-6.2-sol. model_context_window is set to 1,050,000, the context size of GPT-6.2 Sol, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.

toml
model = "openai/gpt-6.2-sol"
model_provider = "uberllm"
model_context_window = 1050000
web_search = "disabled"

[model_providers.uberllm]
name = "MartLLM"
base_url = "https://api.martllm.com/v1"
env_key = "UBERLLM_API_KEY"
wire_api = "responses"

Codex CLI calls: OpenAI Responses API https://api.martllm.com/v1/responses · Full Codex CLI guide

Replace ull_your_key with your MartLLM API key. One key works in every tool and for every model.

By API, GPT-6.2 Sol answers on three addresses with the same MartLLM key and the model id openai/gpt-6.2-sol: OpenAI chat completions at https://api.martllm.com/v1/chat/completions, the OpenAI Responses API at https://api.martllm.com/v1/responses and the Anthropic Messages API at https://api.martllm.com/v1/messages.

How much does the GPT-6.2 Sol API cost?

On November 20, 2026, GPT-6.2 Sol costs $0.1595 per million input tokens and $0.7974 per million output tokens through MartLLM, 92% below its list price of $2.00 and $10.00. 30 sellers on the market can serve it. In the 7 days before, half of its 560 streamed requests got their first token within 3.9 seconds, with a typical prompt of 102,609 tokens. It reads up to 1,050,000 tokens of context. MartLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 11:00 UTC.

GPT-6.2 Sol in other tools

Other models in Codex CLI