Making Fable Cheaper Than Opus | Cognition<br>Menu
Close
We replaced Opus 4.8 with Fable 5, and Devin’s bill went down.<br>Fable 5 costs twice as much per token as Opus 4.8. But when we ran both models on FrontierCode 1.1 using our new Fusion architecture, Fable cost less. Unsurprisingly, it also scored higher. This post explains why, and what that means for pricing agentic work.
Introduction#<br>Everyone who runs coding agents knows that stronger models give you better results, but you eat the cost.<br>When we introduced Devin Fusion, we showed a way out: keep a frontier model in charge, let it delegate to a cheaper and faster sidekick, and you get frontier-level performance at 35% lower cost.<br>But once the lead model delegates most of the work, does its price-per-token still dominate the bill? Fable 5 costs 2x more per token than Opus 4.8, so a Fable-led agent should cost more. To find out, we ran 3,000 evaluation sessions on FrontierCode 1.1 across four configurations: Fable and Opus in the lead seat, each with and without the same cheap sidekick.<br>The pure runs behave exactly as intuition would suggest: Fable outscores Opus (60.8 vs 55.4) and costs more. Better model, bigger bill.<br>The sidekick-enabled runs are where things get interesting.
FrontierCode 1.1 ExtendedScore vs Cost<br>$1.50$2.00$2.50$3.00$3.50$4.00$4.50Cost per run53545556575859606162Score9% cheaper,11% smarterFable 5 (low)Opus 4.8 (medium)Fable 5 + SidekickOpus 4.8 + Sidekick
Given the same sidekick, the cost ordering reverses: Fable + Sidekick costs less than Opus + Sidekick ($1.86 vs. $2.04), while scoring higher (60.7 vs. 54.6). Compared with pure Fable, Fable + Sidekick cuts cost by 54% while leaving the score nearly unchanged.<br>ConfigScoreCost/run (mean)Fable 5 (low) + Sidekick60.7$1.86 Opus 4.8 (medium) + Sidekick54.6$2.04Fable 5 (low)60.8$4.03Opus 4.8 (medium)55.4$3.06<br>The 2x per-token premium turns out to be the wrong number to look at. The cost of an agent is dominated by how many turns the lead model takes, how much context it drags along, and above all, what it decides not to do itself. The difference comes down to management style: Opus behaves like a micromanager with an intern; Fable is a manager with a capable engineer.
The setup#<br>A quick refresher on how Fusion’s sidekick architecture works. The lead agent owns the session: it talks to the user, plans, reviews the work, and commits. It also has a persistent sidekick subagent for delegating tasks. The lead writes a handoff brief in plain language, and the subagent, powered by a much cheaper model, carries it out in its own context and reports back. The lead reviews the result and decides what happens next.<br>To find out where the cost goes, we did two things. First, we parsed every LLM call across all 3,000 sessions: which model was speaking, what tool it called, how many tokens it read and wrote, and what each call cost. Second, we picked 40 tasks for a closer look: the ones where Fable was dramatically cheaper, the ones where Opus was, and another random sample from the middle. For each one, we analyzed the Fable-led run against the Opus-led run side by side, examining the trajectories and observing where the dollars went.
Cost of an agent#<br>Here's how cost splits between the lead and the sidekick in our experiment:<br>Lead $Sidekick $Total $/runLead turns/runLead input tokens (cumulative)Fable + Sidekick$1.28$0.58$1.8611.5545k tokOpus + Sidekick$1.73$0.31$2.0426.51,679k tok<br>Fable spends more on its sidekick than Opus does — $0.27 more per run. But it spends $0.45 less on itself. Fable's lead takes 11.5 turns per run to Opus's 26.5, writes a third of the output tokens (6.1k vs 19.0k), and consumes a third of the input tokens. Fable is significantly more expensive per token, but wins on context management and turn count.<br>Fable’s token savings arise from avoiding work outright. Interestingly, in 81% of Fable-led runs, the lead never makes a single code edit . For Opus, that’s true for only 24% of the runs. In 13% of the Fable-led runs, the lead never even reads a repo file itself.
A micromanager with an intern vs a manager with an engineer#<br>Here's what makes the gap interesting: both leads delegate the same number of times , about 3 handoffs per run. The per-call logs debunk the easy explanation that Fable simply delegates more. What differs is when and what they delegate. Fable’s first handoff comes early. Opus often delegates late, after a long stretch of solo exploration and implementation; by then, the design decisions are made, the important files are in its context, and the expensive work is done.
A manager with an engineer vs a micromanager with an intern<br>The same task, the same sidekick. What differs is how much the lead trusts its sidekick: when it delegates, and what it keeps for itself.<br>Fable 5 + Sidekick<br>lead (Fable 5)sidekick<br>User task
Explores repo, maps OIDC SSO, reports paths + snippets
Reviews report, writes spec-quality brief
Implements + tests + fixes lint
Reviews...