Armand McQueen

basic-generation

ok

Plain streaming generation with a soft length constraint (~100 words).

Produced 98 words (199 output tokens).

Result

{
  "wordCount": 98,
  "outputTokens": 199
}

297441ba-ba2a-4e78-b95a-2324d7cdd058

Sep 5, 2026, 00:55:55

anthropic:claude-fable-5-1

Input

22

Output

199

Reasoning

0

Answer

199

Cost

$0.0102

Mode

streaming

Cost breakdown

Input $0.000220Output $0.0100

Latency

5.7s

TTFT

2.5s

Tok/s

34.9

Tok/s (adj)

62.2

usage-cost

ok

Asserts usage tokens populate and cost computes from the ChatReq contract.

in=22 out=11 rt=0 cost=$0.000770 (paid).

Result

{
  "inputTokens": 22,
  "outputTokens": 11,
  "reasoningTokens": 0,
  "costUsd": 0.0007700000000000001,
  "paid": true
}

6af7a4d8-c32c-4574-99cf-3753c33c6e64

Sep 5, 2026, 00:55:58

anthropic:claude-fable-5-1

Input

22

Output

11

Reasoning

0

Answer

11

Cost

$0.000770

Mode

streaming

Cost breakdown

Input $0.000220Output $0.000550

Latency

3.6s

TTFT

2.4s

Tok/s

3.1

Tok/s (adj)

9.4

streaming-structure

ok

Asserts a streaming call captures events that reconstruct into the final text.

mode=streaming, 11 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 11,
  "textBlocks": 1,
  "textLen": 35
}

a3e3a94e-75ce-45f4-b5e4-66018848efcf

Sep 5, 2026, 00:56:02

anthropic:claude-fable-5-1

Input

23

Output

31

Reasoning

0

Answer

31

Cost

$0.0018

Mode

streaming

Cost breakdown

Input $0.000230Output $0.0016

Latency

3.3s

TTFT

2.2s

Tok/s

9.3

Tok/s (adj)

27.0

complete-stream-parity

ok

Same prompt via stream() and complete() both return valid, matching results.

stream="Paris" · complete="Paris"

Result

{
  "streamText": "Paris",
  "completeText": "Paris"
}

1533afa4-adbf-4da6-9d42-4351d94c4626

Sep 5, 2026, 00:56:05

anthropic:claude-fable-5-1

Input

25

Output

5

Reasoning

0

Answer

5

Cost

$0.000500

Mode

streaming

Cost breakdown

Input $0.000250Output $0.000250

Latency

3.4s

TTFT

2.3s

Tok/s

1.5

Tok/s (adj)

4.7

322ffe22-7b36-4989-a83f-f629059b752f

Sep 5, 2026, 00:56:08

anthropic:claude-fable-5-1

Input

25

Output

5

Cost

$0.000500

Mode

non-streaming

Cost breakdown

Input $0.000250Output $0.000250

Latency

3.0s

Tok/s

1.7

reasoning-conformance

ok

Asserts the model's reasoning knob behaves as its reasoning-config declares.

Class (from reasoning-config): always-on.
reasoningTokens=0, outputTokens=573.

Result

{
  "class": "always-on",
  "reasoningTokens": 0,
  "outputTokens": 573
}

2b9db652-464a-4a26-901a-1c646aec2274

Sep 5, 2026, 00:56:18

anthropic:claude-fable-5-1

Input

129

Output

573

Reasoning

0

Answer

573

Cost

$0.0299

Mode

streaming

Cost breakdown

Input $0.0013Output $0.0287

Latency

9.4s

TTFT

2.9s

Tok/s

60.9

Tok/s (adj)

88.0

single-tool-call

ok

Offers a calculator tool and checks the model calls it for an arithmetic question.

Called "multiply" with args {"a":23,"b":17}.

Result

{
  "toolCalled": true,
  "toolName": "multiply",
  "args": {
    "a": 23,
    "b": 17
  },
  "correct": true
}

b5a9c9a9-6bd5-49e7-b5d2-fbe861000432

Sep 5, 2026, 00:56:22

anthropic:claude-fable-5-1

Input

470

Output

68

Reasoning

0

Answer

68

Cost

$0.0081

Mode

streaming

Cost breakdown

Input $0.0047Output $0.0034

Latency

4.4s

Tok/s

15.6

tool-loop

ok

Forces a tool call, feeds the result back, and checks the continuation uses it.

step1 (auto): multiply({"a":23,"b":17}) → step2: "The product of 23 multiplied by 17 is 391."

Result

{
  "toolName": "multiply",
  "args": {
    "a": 23,
    "b": 17
  },
  "product": 391,
  "continuation": "The product of 23 multiplied by 17 is 391.",
  "usesResult": true,
  "forced": false
}

e671b1ea-4294-4cb3-b32d-17d8ca4e0377

Sep 5, 2026, 00:56:27

anthropic:claude-fable-5-1

Input

473

Output

68

Reasoning

0

Answer

68

Cost

$0.0081

Mode

streaming

Cost breakdown

Input $0.0047Output $0.0034

Latency

4.4s

Tok/s

15.4

fc0d56a8-3188-4b66-8140-8bd7a37ea40e

Sep 5, 2026, 00:56:29

anthropic:claude-fable-5-1

Input

552

Output

20

Reasoning

0

Answer

20

Cost

$0.0065

Mode

streaming

Cost breakdown

Input $0.0055Output $0.0010

Latency

2.6s

TTFT

2.5s

Tok/s

7.7

Tok/s (adj)

181.0

web-search

ok

Enables server-side web search and checks invocation counts, the per-request cost surcharge, and provider-executed output blocks.

Ran 1 web search(es); surcharge 0.0100 USD on top of token cost.

Result

{
  "searches": 1,
  "surchargeUsd": 0.01
}

aecae6a2-2af5-4ec8-803d-b709ab0d12cf

Sep 5, 2026, 00:56:52

anthropic:claude-fable-5-1

Input

13,511

Output

1,085

Reasoning

37

Answer

1,048

Web searches

1

Cost

$0.1994

Mode

streaming

Cost breakdown

Input $0.1351Output $0.0542Web search $0.0100

Latency

22.8s

TTFT

3.9s

Tok/s

47.6

Tok/s (adj)

55.5

reasoning-tool-continuity

ok

Reasoning model: continuity token captured on a tool call and replayed so the follow-up succeeds.

reasoned=true, anthropic token captured; follow-up → "The current balance for account **acme-42** is **$1,234.00**. **Calcu"

Result

{
  "signatureType": "anthropic",
  "tokenCaptured": true,
  "reasoned": true,
  "answered": true,
  "continuation": "The current balance for account **acme-42** is **$1,234.00**.\n\n**Calculation (5% compounded annually for 7 years):**\n\nFuture value = P × (1 "
}

ba7e034b-eb25-40a8-87e2-b1323bf16a82

Sep 5, 2026, 00:56:56

anthropic:claude-fable-5-1

Input

521

Output

90

Reasoning

23

Answer

67

Cost

$0.0097

Mode

streaming

Cost breakdown

Input $0.0052Output $0.0045

Latency

4.5s

TTFT

3.5s

Tok/s

20.1

Tok/s (adj)

67.9

e7e08a2a-980d-4e07-8ce0-e1d5e074ec13

Sep 5, 2026, 00:57:03

anthropic:claude-fable-5-1

Input

628

Output

400

Reasoning

0

Answer

400

Cost

$0.0263

Mode

streaming

Cost breakdown

Input $0.0063Output $0.0200

Latency

6.6s

TTFT

6.6s

Tok/s

60.7

Tok/s (adj)

11037.5

prompt-cache

ok

Repeat a large prefix; assert cache-read tokens are reported and cost drops.

anthropic cache; cacheRead per attempt [14458]; hit=yes.

Result

{
  "cacheStyle": "anthropic",
  "cacheReadPerAttempt": [
    14458
  ],
  "cacheReadTokens": 14458,
  "cacheHitCost": 0.0078445
}

6952036d-60b4-4461-a5ac-03caa3d8c827

Sep 5, 2026, 00:57:08

anthropic:claude-fable-5-1

Input

14,481

Output

80

Cache Write

14,458

Cost

$0.1850

Mode

non-streaming

Cost breakdown

Input $0.000230Output $0.0040Cache write $0.1807

Latency

5.1s

Tok/s

15.8

c87750d0-acb2-48bc-b3cb-b333d57d1074

Sep 5, 2026, 00:57:13

anthropic:claude-fable-5-1

Input

14,481

Output

80

Cache Read

14,458

Cost

$0.0078

Mode

non-streaming

Cost breakdown

Input $0.000230Output $0.0040Cache read $0.0036

Latency

5.2s

Tok/s

15.3

json-output

ok

Requests a strict JSON object and checks it parses with the required keys.

Output parsed as JSON.
All required keys present.
Output is bare JSON (no leading prose/fence).

Result

{
  "parsed": {
    "name": "Anthropic",
    "founded": 2021,
    "headquarters": "San Francisco, California, United States"
  },
  "validJson": true,
  "missingKeys": [],
  "bareJson": true
}

6aedc240-38c0-40de-8b1b-60f40ddee926

Sep 5, 2026, 00:57:18

anthropic:claude-fable-5-1

Input

88

Output

40

Reasoning

0

Answer

40

Cost

$0.0029

Mode

streaming

Cost breakdown

Input $0.000880Output $0.0020

Latency

4.9s

TTFT

3.5s

Tok/s

8.1

Tok/s (adj)

28.3

summarize-memex

ok

Summarizes an ~11k-token essay to ~500 words (long input, reasoning minimized).

Read ~14535 input tokens, wrote 569 words (1248 output tokens) in 23154ms.

Result

{
  "wordCount": 569,
  "inputTokens": 14535,
  "outputTokens": 1248,
  "latencyMs": 23154
}

27e47718-5a63-408b-a64b-9f7088a75775

Sep 5, 2026, 00:57:41

anthropic:claude-fable-5-1

Input

14,535

Output

1,248

Reasoning

60

Answer

1,188

Cost

$0.2077

Mode

streaming

Cost breakdown

Input $0.1453Output $0.0624

Latency

23.2s

TTFT

4.0s

Tok/s

53.9

Tok/s (adj)

62.1

truncation

ok

Tiny maxTokens on a long prompt yields finishReason:"length".

finishReason=length, out=100 tokens.

Result

{
  "finishReason": "length",
  "outputTokens": 100
}

0607b96e-24b0-4a77-b325-7e29f5b4c0ee

Sep 5, 2026, 00:57:46

anthropic:claude-fable-5-1

Input

32

Output

100

Reasoning

42

Answer

58

Cost

$0.0053

Mode

streaming

Cost breakdown

Input $0.000320Output $0.0050

Latency

4.5s

TTFT

3.2s

Tok/s

22.4

Tok/s (adj)

44.4

streaming-only-rejection

ok

Streaming-only models reject complete(); all others accept it.

streamingOnly=false; complete() succeeded.

Result

{
  "streamingOnly": false,
  "completeThrew": false
}

abort

ok

A pre-aborted signal rejects the call (abort is threaded + honored).

pre-aborted signal → rejected (AbortError).

Result

{
  "rejected": true,
  "errorName": "AbortError"
}