Skip to content
Skip to content
Model update7 min read

Bringing the Frontier to Critique

GPT-6 Astra and Claude Fable 5.1 are now available for the review runs where context, judgment, and a clean merge matter more than bargain-basement inference.

Critique
The short version

The frontier is now a routing choice inside Critique. GPT-6 Astra and Claude Fable 5.1 both sit at a 60-credit shelf floor, both cost $50 per million output tokens, and the input split is deliberate: Astra at $5/M, Fable at $10/M.

$5/M
GPT-6 Astra input tokens
$10/M
Claude Fable 5.1 input tokens
$50/M
Output tokens for both frontier lanes
60 cr
Managed shelf floor for each model

A model catalog is only useful when it changes what the system can do. Adding two impressive names to a dropdown is not the point. The point is giving a review system a credible escalation path when the change is large, ambiguous, or expensive to get wrong — without turning every routine pull request into a frontier-model invoice.

GPT-6 Astra and Claude Fable 5.1 are available anywhere Critique exposes its managed runtime catalog: lead review, specialist review, and Remedy. They are first-class routes, not one-off provider exceptions. That means the same receipt can show the selected model, token usage, model cost, and Critique execution cost together.

Frontier rate card

The expensive part is visible on purpose

Published managed rates per one million tokens. Credit floors cover the review slice; token usage remains visible as its own line item.

GPT-6 Astra
Managed · 60 cr
Input / 1M
$5
Output / 1M
$50
Context 1M+ context class

Lower input rate for context-heavy review and Remedy plans.

Claude Fable 5.1
Managed · 60 cr
Input / 1M
$10
Output / 1M
$50
Context 1M context class

Deep Anthropic escalation when the review deserves the premium lane.

Rates are USD per 1M input/output tokens. The 60-credit floor is the managed catalog floor, not a promise that every review consumes exactly 60 credits.

Input economics: Astra keeps more context in play
USD per 1M input tokens. Lower is better for context-heavy runs.
  • GPT-6 Astra5$ / 1M
  • Claude Fable 5.110$ / 1M

Astra’s input rate is half Fable’s. That matters when a review spends more tokens reading a repository than writing a verdict.

Output economics: a shared frontier ceiling
USD per 1M output tokens. Both models are priced at the same output rate.
  • GPT-6 Astra50$ / 1M
  • Claude Fable 5.150$ / 1M

The output rate is intentionally simple: both frontier routes are $50 per million output tokens.

Not for every diff. Flash and mid-tier models remain the right answer for volume, straightforward changes, and specialist checks. The frontier is for the moments where a missed dependency, incorrect security conclusion, or fragile repair plan costs more than the inference.

Normal change
Fast modelSpecialist checksHuman merge decision
Frontier change
Repo-aware scoutAstra or Fable leadEvidence-backed verdictRemedy if needed

That is the shape we want teams to adopt: cost-aware escalation, not model worship. Start economically. Escalate when the risk profile earns it. Keep the provider, model, tokens, and execution charges visible so the routing policy can improve over time.

The best place for a frontier model is not necessarily the first draft. It is the final judgment: the pass where the system has already gathered the diff, repository context, specialist findings, test output, and the facts a lead reviewer needs to decide. Astra and Fable give Critique two more serious options for that job.

Route the hard changes with intent
See the full managed catalog, compare credit floors, and keep the model bill visible before the change ships.
Independent reviewVerified repairReal repositoriesBuilt for developersLoved by agents