Armand McQueen

basic-generation

ok

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

Produced 114 words (244 output tokens).

Result

{
  "wordCount": 114,
  "outputTokens": 244
}

5942d758-7cee-43fc-a52d-e9bf282db335

Aug 8, 2026, 08:50:51

anthropic:claude-opus-5

Input

20

Output

244

Reasoning

25

Answer

219

Cost

$0.0062

Mode

streaming

Cost breakdown

Input $0.000100Output $0.0061

Latency

4.5s

TTFT

1.7s

Tok/s

53.7

Tok/s (adj)

75.8

usage-cost

ok

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

in=20 out=11 rt=0 cost=$0.000375 (paid).

Result

{
  "inputTokens": 20,
  "outputTokens": 11,
  "reasoningTokens": 0,
  "costUsd": 0.000375,
  "paid": true
}

6a6ccb55-3023-4ed6-b68d-4ca9dc8e8e50

Aug 8, 2026, 08:50:53

anthropic:claude-opus-5

Input

20

Output

11

Reasoning

0

Answer

11

Cost

$0.000375

Mode

streaming

Cost breakdown

Input $0.000100Output $0.000275

Latency

2.3s

TTFT

1.3s

Tok/s

4.7

Tok/s (adj)

10.7

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
}

59a88467-70fa-40c4-a350-f5350d438460

Aug 8, 2026, 08:50:55

anthropic:claude-opus-5

Input

21

Output

53

Reasoning

22

Answer

31

Cost

$0.0014

Mode

streaming

Cost breakdown

Input $0.000105Output $0.0013

Latency

1.8s

TTFT

1.8s

Tok/s

29.8

Tok/s (adj)

2336.1

complete-stream-parity

ok

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

stream="Paris" · complete="Paris"

Result

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

43fe4831-083c-47fb-87e3-8de67e93218b

Aug 8, 2026, 08:50:57

anthropic:claude-opus-5

Input

23

Output

25

Reasoning

20

Answer

5

Cost

$0.000740

Mode

streaming

Cost breakdown

Input $0.000115Output $0.000625

Latency

2.1s

TTFT

2.1s

Tok/s

11.9

Tok/s (adj)

2840.9

4a117361-628d-4557-b54d-f7e3f8cb2246

Aug 8, 2026, 08:50:59

anthropic:claude-opus-5

Input

23

Output

25

Cost

$0.000740

Mode

non-streaming

Cost breakdown

Input $0.000115Output $0.000625

Latency

1.5s

Tok/s

16.2

reasoning-conformance

ok

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

Class (from reasoning-config): always-on.
reasoningTokens=153, outputTokens=829.

Result

{
  "class": "always-on",
  "reasoningTokens": 153,
  "outputTokens": 829
}

29c68b8a-1f51-4d80-b7e4-4affc8091ebe

Aug 8, 2026, 08:51:08

anthropic:claude-opus-5

Input

127

Output

829

Reasoning

153

Answer

676

Cost

$0.0214

Mode

streaming

Cost breakdown

Input $0.000635Output $0.0207

Latency

9.6s

TTFT

3.0s

Tok/s

86.8

Tok/s (adj)

103.5

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
}

90ac6886-7a62-4521-931f-88c2b57b8e05

Aug 8, 2026, 08:51:10

anthropic:claude-opus-5

Input

468

Output

68

Reasoning

0

Answer

68

Cost

$0.0040

Mode

streaming

Cost breakdown

Input $0.0023Output $0.0017

Latency

1.8s

Tok/s

37.0

tool-loop

ok

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

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

Result

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

82e06e0a-179d-4ced-8f6b-9de13489ef85

Aug 8, 2026, 08:51:15

anthropic:claude-opus-5

Input

591

Output

58

Reasoning

0

Answer

58

Cost

$0.0044

Mode

streaming

Cost breakdown

Input $0.0030Output $0.0014

Latency

4.4s

Tok/s

13.2

4edd5a56-ad94-46a9-8a3c-cb771cb4364f

Aug 8, 2026, 08:51:16

anthropic:claude-opus-5

Input

550

Output

16

Reasoning

0

Answer

16

Cost

$0.0032

Mode

streaming

Cost breakdown

Input $0.0028Output $0.000400

Latency

1.4s

TTFT

1.0s

Tok/s

11.6

Tok/s (adj)

46.7

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
}

768c80cc-be1d-4c0a-afa8-6461a08e3d19

Aug 8, 2026, 08:51:38

anthropic:claude-opus-5

Input

14,775

Output

960

Reasoning

107

Answer

853

Web searches

1

Cost

$0.1079

Mode

streaming

Cost breakdown

Input $0.0739Output $0.0240Web search $0.0100

Latency

21.7s

TTFT

1.8s

Tok/s

44.3

Tok/s (adj)

42.9

reasoning-tool-continuity

ok

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

Step 1 didn't engage reasoning (adaptive discretion) — signature not exercised this run.
reasoned=false, anthropic token —; follow-up → "## Balance lookup Account `acme-42`: **$1,234.00** ## Calculation F"

Result

{
  "signatureType": "anthropic",
  "tokenCaptured": false,
  "reasoned": false,
  "answered": true,
  "continuation": "## Balance lookup\n\nAccount `acme-42`: **$1,234.00**\n\n## Calculation\n\nFormula: A = P(1 + r)ⁿ = 1234 × (1.05)⁷\n\nStep 1 — compute the growth fa"
}

bee5564e-43a3-4c5d-9a10-72c47f7c0a40

Aug 8, 2026, 08:51:45

anthropic:claude-opus-5

Input

519

Output

53

Reasoning

0

Answer

53

Cost

$0.0039

Mode

streaming

Cost breakdown

Input $0.0026Output $0.0013

Latency

1.6s

Tok/s

32.7

4bfd3d2c-d170-4b4e-88af-2248b35058bb

Aug 8, 2026, 08:51:56

anthropic:claude-opus-5

Input

589

Output

748

Reasoning

323

Answer

425

Cost

$0.0216

Mode

streaming

Cost breakdown

Input $0.0029Output $0.0187

Latency

10.8s

TTFT

6.5s

Tok/s

69.2

Tok/s (adj)

97.6

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": 0.009334
}

9bc05089-7e4f-47ea-ab19-9b9cd4acb250

Aug 8, 2026, 08:51:59

anthropic:claude-opus-5

Input

14,479

Output

80

Cache Write

14,458

Cost

$0.0925

Mode

non-streaming

Cost breakdown

Input $0.000105Output $0.0020Cache write $0.0904

Latency

3.3s

Tok/s

24.3

cd8e72ad-bc1a-4f99-a501-5ab41a02f494

Aug 8, 2026, 08:52:02

anthropic:claude-opus-5

Input

14,479

Output

80

Cache Read

14,458

Cost

$0.0093

Mode

non-streaming

Cost breakdown

Input $0.000105Output $0.0020Cache read $0.0072

Latency

2.8s

Tok/s

28.3

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, USA"
  },
  "validJson": true,
  "missingKeys": [],
  "bareJson": true
}

3e35e4ed-6a04-423e-af8c-431dfec9eb1e

Aug 8, 2026, 08:52:04

anthropic:claude-opus-5

Input

86

Output

40

Reasoning

0

Answer

40

Cost

$0.0014

Mode

streaming

Cost breakdown

Input $0.000430Output $0.0010

Latency

1.7s

TTFT

854ms

Tok/s

23.1

Tok/s (adj)

45.7

summarize-memex

ok

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

Read ~14533 input tokens, wrote 567 words (1345 output tokens) in 21309ms.

Result

{
  "wordCount": 567,
  "inputTokens": 14533,
  "outputTokens": 1345,
  "latencyMs": 21309
}

2a34edd3-89d2-44a3-9d26-5987c579ab9d

Aug 8, 2026, 08:52:25

anthropic:claude-opus-5

Input

14,533

Output

1,345

Reasoning

54

Answer

1,291

Cost

$0.1063

Mode

streaming

Cost breakdown

Input $0.0727Output $0.0336

Latency

21.3s

TTFT

1.9s

Tok/s

63.1

Tok/s (adj)

66.4

truncation

ok

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

finishReason=length, out=100 tokens.

Result

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

b679cfae-6149-4231-84d7-fc59697842a2

Aug 8, 2026, 08:52:27

anthropic:claude-opus-5

Input

30

Output

100

Reasoning

100

Answer

0

Cost

$0.0027

Mode

streaming

Cost breakdown

Input $0.000150Output $0.0025

Latency

2.3s

Tok/s

42.7

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"
}