OpenAI launches Ultrafast inference mode for GPT-5.6 Sol
OpenAI launched Ultrafast, an inference mode that runs GPT-5.6 Sol at up to 750 output tokens per second using Cerebras hardware. It joins Standard and Fast to form a three-tier pricing structure.
First seen 14 Aug, 14:21 UTC on The Decoder3 sourcesLast update 60d ago
OpenAILaunch · 14 Aug
GPT-5.6 Sol
New product or feature
How GPT-5.6 Sol compares
List prices per million tokens, context and Arena's text leaderboard, against OpenAI's other top models and the leading labs' best. The percentages are GPT-5.6 Sol's price against each.
| Model | Released | Input | Output | Context | Arena |
|---|---|---|---|---|---|
| GPT-5.6 Sol | Jul 2026 | $4.00 | $20.00 | 1M | #17 1485 |
| GPT-5.6 Terra | Jul 2026 | $2.50 +60% | $15.00 +33% | 1M | #43 1466 |
| GPT-5.6 Luna | Jul 2026 | $1.00 +300% | $6.00 +233% | 1M | not ranked yet |
| Claude Opus 5.5 | September 2026 | $4.00 | $20.00 | 1M | #2 1507 |
| Gemini 4 Argon | October 2026 | $2.00 +100% | $10.00 +100% | 1M | #1 1525 |
| Muse Wonder | October 2026 | $4.00 | $20.00 | 1M | not ranked yet |
Arena ranks the best effort setting of each model among all models on its text leaderboard. Every model and price.
What the sources say
Linked, never rewritten. Official means the lab itself.
How it unfolded
Every source in the order it appeared. Times in UTC.
Keep up with OpenAI
OpenAI on the ScoreIts timelineFollow to mark OpenAI's stories across the site. No account needed.