Independent reliability evidence

The Meter · Model page

THE METER · MODELClaude Fable 5
Provider
Anthropic
Exact model id we call
claude-fable-5
Route
provider direct
Watching since
27 July 2026

What we check

Most checks are the same on every model. See what we check

This provider does not send our settings back. We record what the response does show, and never say a setting was applied.

Pattern

Time to answer

Latency, time-to-first-token and reasoning-token volume are recorded on every call across all checks.

Daily exam

The scored series

The daily exam is the only check with a published score.

Other checks

Reasoning-token volume

The panel reports the median by published day across all checks.

The settings

Settings and dated runs

The settings we send, every time

model:             "claude-fable-5"
max_tokens:        128000
output_config:     {"effort": "medium"}
temperature:       1.0
service_tier:      "standard_only"
thinking:          {"type": "adaptive"}
stream:            true
anthropic-version: "2023-06-01"

Dated runs

When we change our own settings, we close that run and start a new dated one. The earlier days stay published.

Dated runDatesRouteStatusDays
box-2026-07-23since 23 Julprovider directcurrent19 published

Gap register

3 August 2026: No run. Our prepaid credit with the provider had run out, so all 63 questions came back as billing errors.

5 August 2026: Run set aside. The provider was briefly overloaded on 4 of the 63 questions and we did not retry them.

8 August 2026: Run set aside. Our prepaid credit ran out partway through, so 9 of the 63 questions came back as billing errors.

9 to 13 August 2026 (5 days): No run. Our prepaid credit with the provider had run out, so all 63 questions came back as billing errors.

16 to 17 August 2026 (2 days): No run. Our prepaid credit with the provider had run out, so all 63 questions came back as billing errors.

20 to 23 August 2026 (4 days): No run. Our prepaid credit with the provider had run out, so all 63 questions came back as billing errors.

25 August 2026: No run recorded. Reason not yet written up.

26 August 2026: No run. The fable line was deliberately paused on 26 August 2026 to hold the rig inside what we can fund. Nothing about the questions, the sensors or the method changed; the line was simply switched off and can be switched back on unchanged.

27 August 2026: No run. The fable line has been paused since 26 August 2026 to hold the rig inside what we can fund. Nothing about the questions, the sensors or the method changed. The line can be switched back on unchanged.

What we do not claim: we never compare this model with another, and we never say a change was deliberate.