Armand McQueen

basic-generation

ok

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

Produced 98 words (117 output tokens).

Result

{
  "wordCount": 98,
  "outputTokens": 117
}

64e51cd3-4e4c-4a7a-b5b4-8c1270dc03a0

Aug 8, 2026, 08:52:33

google:gemini-3.5-flash-lite

Input

14

Output

117

Reasoning

0

Answer

117

Cost

$0.000297

Mode

streaming

Cost breakdown

Input $0.000004Output $0.000293

Latency

988ms

TTFT

563ms

Tok/s

118.4

Tok/s (adj)

275.0

usage-cost

ok

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

in=10 out=5 rt=0 cost=$0.000016 (paid).

Result

{
  "inputTokens": 10,
  "outputTokens": 5,
  "reasoningTokens": 0,
  "costUsd": 0.0000155,
  "paid": true
}

0344db4e-7b05-49bf-b458-90083f9c3d65

Aug 8, 2026, 08:52:33

google:gemini-3.5-flash-lite

Input

10

Output

5

Reasoning

0

Answer

5

Cost

$0.000016

Mode

streaming

Cost breakdown

Input $0.000003Output $0.000013

Latency

519ms

TTFT

472ms

Tok/s

9.6

Tok/s (adj)

105.8

streaming-structure

ok

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

mode=streaming, 8 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 8,
  "textBlocks": 1,
  "textLen": 35
}

379f0c6f-4db8-451e-93ad-5627343f9447

Aug 8, 2026, 08:52:34

google:gemini-3.5-flash-lite

Input

15

Output

35

Reasoning

0

Answer

35

Cost

$0.000092

Mode

streaming

Cost breakdown

Input $0.000005Output $0.000087

Latency

447ms

TTFT

401ms

Tok/s

78.3

Tok/s (adj)

757.4

complete-stream-parity

ok

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

stream="Paris" · complete="Paris"

Result

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

ef5f97ec-d68a-4f3f-a335-ba335528b6c2

Aug 8, 2026, 08:52:34

google:gemini-3.5-flash-lite

Input

15

Output

1

Reasoning

0

Answer

1

Cost

$0.000007

Mode

streaming

Cost breakdown

Input $0.000005Output $0.000002

Latency

359ms

TTFT

354ms

Tok/s

2.8

Tok/s (adj)

214.6

28fe6069-9af1-41c3-a145-e2d15629aa74

Aug 8, 2026, 08:52:35

google:gemini-3.5-flash-lite

Input

15

Output

1

Reasoning

0

Answer

1

Cost

$0.000007

Mode

non-streaming

Cost breakdown

Input $0.000005Output $0.000002

Latency

381ms

Tok/s

2.6

reasoning-conformance

ok

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

Class (from reasoning-config): toggleable.
off: out=629 · mid: out=1702 (rt=1098).

Result

{
  "class": "toggleable",
  "mode": "deterministic",
  "offOutputTokens": 629,
  "midOutputTokens": 1702,
  "midReasoningTokens": 1098
}

a57a20aa-538b-458e-9676-3338a440731b

Aug 8, 2026, 08:52:36

google:gemini-3.5-flash-lite

Input

92

Output

629

Reasoning

0

Answer

629

Cost

$0.0016

Mode

streaming

Cost breakdown

Input $0.000028Output $0.0016

Latency

1.9s

TTFT

361ms

Tok/s

332.5

Tok/s (adj)

410.9

bb93b9c1-afb1-4c7c-b656-b65dff357834

Aug 8, 2026, 08:52:41

google:gemini-3.5-flash-lite

Input

92

Output

1,702

Reasoning

1,098

Answer

604

Cost

$0.0043

Mode

streaming

Cost breakdown

Input $0.000028Output $0.0043

Latency

4.4s

TTFT

3.1s

Tok/s

389.3

Tok/s (adj)

459.4

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
}

4bbe413f-f9f8-4743-b3fd-2ad1d531be83

Aug 8, 2026, 08:52:41

google:gemini-3.5-flash-lite

Input

99

Output

18

Reasoning

0

Answer

18

Cost

$0.000075

Mode

streaming

Cost breakdown

Input $0.000030Output $0.000045

Latency

428ms

Tok/s

42.1

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: "The product of 23 and 17 is 391."

Result

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

8c975d16-ed21-40c4-889f-d3edaaa10ca4

Aug 8, 2026, 08:52:42

google:gemini-3.5-flash-lite

Input

95

Output

18

Reasoning

0

Answer

18

Cost

$0.000073

Mode

streaming

Cost breakdown

Input $0.000029Output $0.000045

Latency

444ms

Tok/s

40.5

023f4047-95cf-423b-a38a-0124d539f8f9

Aug 8, 2026, 08:52:42

google:gemini-3.5-flash-lite

Input

133

Output

16

Reasoning

0

Answer

16

Cost

$0.000080

Mode

streaming

Cost breakdown

Input $0.000040Output $0.000040

Latency

433ms

TTFT

378ms

Tok/s

37.0

Tok/s (adj)

291.5

web-search

ok

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

Skipped: model does not support the catalog's web_search tool version.

Result

{
  "skipped": "no server-side web search support"
}

reasoning-tool-continuity

ok

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

reasoned=true, google token captured; follow-up → "The current balance for account 'acme-42' is **$1,234**. ### Calculat"

Result

{
  "signatureType": "google",
  "tokenCaptured": true,
  "reasoned": true,
  "answered": true,
  "continuation": "The current balance for account 'acme-42' is **$1,234**.\n\n### Calculation\n\n1. **Formula for compound growth:**\n   $$\\text{Future Balance} = "
}

79b64ed7-b4e5-4917-8f48-0540ac949a31

Aug 8, 2026, 08:52:43

google:gemini-3.5-flash-lite

Input

123

Output

140

Reasoning

120

Answer

20

Cost

$0.000387

Mode

streaming

Cost breakdown

Input $0.000037Output $0.000350

Latency

671ms

Tok/s

208.6

1e1fe581-2ed7-4acd-aafe-1a3b05117dd0

Aug 8, 2026, 08:52:44

google:gemini-3.5-flash-lite

Input

290

Output

316

Reasoning

0

Answer

316

Cost

$0.000877

Mode

streaming

Cost breakdown

Input $0.000087Output $0.000790

Latency

1.3s

TTFT

373ms

Tok/s

248.8

Tok/s (adj)

352.2

prompt-cache

ok

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

implicit cache; cacheRead per attempt [0, 0, 0]; hit=no.

Result

{
  "cacheStyle": "implicit",
  "cacheReadPerAttempt": [
    0,
    0,
    0
  ],
  "cacheReadTokens": 0,
  "cacheHitCost": null
}

37d59678-1317-4c8a-8cc2-23a78e25572a

Aug 8, 2026, 08:52:45

google:gemini-3.5-flash-lite

Input

10,121

Output

59

Reasoning

0

Answer

59

Cost

$0.0032

Mode

non-streaming

Cost breakdown

Input $0.0030Output $0.000148

Latency

836ms

Tok/s

70.6

ff7b729b-89e9-4174-80a4-ad42581dcaa0

Aug 8, 2026, 08:52:46

google:gemini-3.5-flash-lite

Input

10,121

Output

60

Reasoning

0

Answer

60

Cost

$0.0032

Mode

non-streaming

Cost breakdown

Input $0.0030Output $0.000150

Latency

736ms

Tok/s

81.5

ffb30e0b-9215-4917-864f-0717843a22f8

Aug 8, 2026, 08:52:46

google:gemini-3.5-flash-lite

Input

10,121

Output

62

Reasoning

0

Answer

62

Cost

$0.0032

Mode

non-streaming

Cost breakdown

Input $0.0030Output $0.000155

Latency

728ms

Tok/s

85.2

252eb6a6-efad-430c-82ea-b7867a59c2ab

Aug 8, 2026, 08:52:47

google:gemini-3.5-flash-lite

Input

10,121

Output

56

Reasoning

0

Answer

56

Cost

$0.0032

Mode

non-streaming

Cost breakdown

Input $0.0030Output $0.000140

Latency

731ms

Tok/s

76.6

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

cbfc663a-9702-4485-bc13-c1a0bce2e0bc

Aug 8, 2026, 08:52:48

google:gemini-3.5-flash-lite

Input

57

Output

26

Reasoning

0

Answer

26

Cost

$0.000082

Mode

streaming

Cost breakdown

Input $0.000017Output $0.000065

Latency

465ms

TTFT

464ms

Tok/s

55.9

Tok/s (adj)

27083.3

summarize-memex

ok

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

Read ~10155 input tokens, wrote 514 words (654 output tokens) in 3369ms.

Result

{
  "wordCount": 514,
  "inputTokens": 10155,
  "outputTokens": 654,
  "latencyMs": 3369
}

ba9f212b-5da9-45e9-889d-6c272d2cbf05

Aug 8, 2026, 08:52:51

google:gemini-3.5-flash-lite

Input

10,155

Output

654

Reasoning

0

Answer

654

Cost

$0.0047

Mode

streaming

Cost breakdown

Input $0.0030Output $0.0016

Latency

3.4s

TTFT

500ms

Tok/s

194.1

Tok/s (adj)

227.9

truncation

ok

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

finishReason=length, out=96 tokens.

Result

{
  "finishReason": "length",
  "outputTokens": 96
}

0f51fb18-f25e-4b94-be1b-d1424e992b6f

Aug 8, 2026, 08:52:52

google:gemini-3.5-flash-lite

Input

21

Output

96

Reasoning

0

Answer

96

Cost

$0.000246

Mode

streaming

Cost breakdown

Input $0.000006Output $0.000240

Latency

691ms

TTFT

389ms

Tok/s

138.9

Tok/s (adj)

317.4

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"
}