Public story · 2026-07-01 · high
OpenAI's GPT-5.6 Sol hits 750 tokens per second on Cerebras
Sol lands with two cheaper siblings, Terra and Luna, but part of the rollout stays gated to trusted partners at the government's request.
Why now: OpenAI just previewed the Sol/Terra/Luna family for a July launch, and Cerebras is the first hard performance number attached to it.
Story
OpenAI's GPT-5.6 Sol hits 750 tokens per second on Cerebras hardware in July, per OpenAI.
That speed matters most for developers building interactive agent loops, where every extra second of waiting breaks the experience. Latency is a product feature, and a jump to 750 tokens per second is a large cut to it.
Sol is the flagship of a three-model family that also includes Terra and Luna, all previewed together.
Sol prices at $5 per million input tokens and $30 per million output tokens. Luna, the cheaper model in the family, runs $1 and $6. Terra's price hasn't been published.
OpenAI is keeping part of the rollout gated to trusted partners at the request of the US government, per the announcement. The Cerebras speed tier is one of the clearer signs of where that access is opening up first.
I'd bet the trusted-partner gate loosens within a quarter once the 750-tokens-per-second tier proves out elsewhere. If it's still locked down by October, the government's request is doing more gatekeeping than OpenAI is letting on.
OpenAI just previewed the Sol/Terra/Luna family for a July launch, and Cerebras is the first hard performance number attached to it.
Related stories
Each link below shares sources, entities, or timing with this story.
Shared entities / Same source / Earlier coverage
OpenAI shipped GPT-5.6 'Sol' and then handed the keys to Washington
Both cover GPT, Luna, OpenAI, Terra; cite the same source (OpenAI); earlier GPT coverage from 2026-06-26.
Shared entities / Earlier coverage
OpenAI is staging GPT-5.6 (Sol, Terra, Luna) behind a government-coordinated limited preview.
Both cover GPT, July, Luna, OpenAI; earlier GPT coverage from 2026-06-28.
Frontier capability and general availability are now decoupled by policy.
Both cover GPT, Luna, OpenAI, Terra; earlier GPT coverage from 2026-06-29.
Shared entities / Same source domain / Shared topic / Earlier coverage
OpenAI Deploys GPT-5.4 Thinking to Monitor Its Own Coding Agents for Misalignment — In Production
Both cover GPT, OpenAI; reported by the same outlet (openai.com); overlapping topics (access, agent).
GPT-5.4 Launches: Computer Use, Tool Search API, 1M Context
Both cover GPT, OpenAI; reported by the same outlet (openai.com); overlapping topics (agent, token).
Shared entities / Same source domain / Earlier coverage / Tension
OpenAI ships LifeSciBench plus a near-autonomous AI chemist.
Both cover GPT, OpenAI; reported by the same outlet (openai.com); earlier GPT coverage from 2026-06-18.
OpenAI publishes cybersecurity strategy alongside GPT-5.4-Cyber.
Both cover GPT, OpenAI; reported by the same outlet (openai.com); earlier GPT coverage from 2026-04-30.
GPT-5.5 Is Here. It's Fast, It's Expensive, and It Changes How You Prompt.
Both cover GPT, OpenAI; reported by the same outlet (openai.com); earlier GPT coverage from 2026-04-25.
Source trail
Entities
Claim evidence
- OpenAI's GPT-5.6 Sol hits 750 tokens per second on Cerebras
Provenance
- Canonical issue
- 2026-07-01
- AI generated
- yes
- Story unit
- 2026-07-01-gpt-5-6-sol-is-launching-on-cerebras-at-up-to-750-tokens-per-second
- Labels
- source-backed, canonical briefing excerpt