Inference Cost Comparison: Sol vs. Fable
ZainHasan6 · x · 2026-07-15
Compares the performance and pricing of Sol and Fable across different levels of inference effort:
- Sol costs about $3.47/rollout at 69.2%.
- Fable costs about $13.41 at 69.9%, meaning it is roughly 4x the price for the same score.
- The author also noted that Sol's max tier set a record of $8.37, which is still cheaper than most Fable runs mentioned above.
Replies further noted that Fable's reasoning effort plateaus around 69.7%, whereas Sol's performance improves incrementally as effort scales from 45 → 61 → 69 → 71 → 73, indicating that this "effort knob" finally behaves more reasonably.
Related event: Sol vs Fable: Coding Agent Benchmarks Show Specialization, Not Dominance(9 posts)→
More from Models
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26
- Abliterated Model Flops in the Wild: It Got Worried About My Mental Health Instead — ryunuck · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26