Meet GPT-6.1 Sol and Fast

OpenAI's latest Sol targets complex coding and professional work. Both options take 1.05M tokens of context and up to 128K output tokens.

Two models

• GPT-6.1 SolPublisher list: $2 input, $10 output per 1M tokens. The Standard option.openai/gpt-6.1-sol
• GPT-6.1 Sol FastPublisher list: $4 input, $20 output per 1M tokens. The faster serving option.openai/gpt-6.1-sol-fast

Try it

Check current catalog availability before calling. Chat Completions supports requests without tools; use Responses for tool calling. Reasoning defaults to medium; none and minimal are unsupported. Send openai/gpt-6.1-sol as the model.

curl https://api.minirouter.sh/v1/chat/completions \
  -H "Authorization: Bearer $MINIROUTER_API_KEY" \
  -H 'Content-Type: application/json' \
  --data '{
    "model": "openai/gpt-6.1-sol",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Fix this failing test." }]
  }'

Benchmarks and prices: OpenAI model documentation, Vercel model catalog.