Armand McQueen

basic-generation

ok

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

Produced 98 words (124 output tokens).

Result

{
  "wordCount": 98,
  "outputTokens": 124
}

4b669569-1189-4ade-8d5a-8822f5def2d4

Aug 8, 2026, 08:52:55

google:gemini-3.6-flash

Input

14

Output

124

Reasoning

0

Answer

124

Cost

$0.000951

Mode

streaming

Cost breakdown

Input $0.000021Output $0.000930

Latency

1.7s

TTFT

738ms

Tok/s

72.5

Tok/s (adj)

127.5

usage-cost

ok

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

in=10 out=265 rt=260 cost=$0.002002 (paid).

Result

{
  "inputTokens": 10,
  "outputTokens": 265,
  "reasoningTokens": 260,
  "costUsd": 0.0020025,
  "paid": true
}

2a7bb7d5-aa68-46d8-971c-56517526cbf9

Aug 8, 2026, 08:52:57

google:gemini-3.6-flash

Input

10

Output

265

Reasoning

260

Answer

5

Cost

$0.0020

Mode

streaming

Cost breakdown

Input $0.000015Output $0.0020

Latency

1.8s

TTFT

1.8s

Tok/s

144.0

Tok/s (adj)

1101.3

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
}

91912ded-8cbe-4097-9fb4-4e96da97c1a3

Aug 8, 2026, 08:52:58

google:gemini-3.6-flash

Input

15

Output

193

Reasoning

158

Answer

35

Cost

$0.0015

Mode

streaming

Cost breakdown

Input $0.000023Output $0.0014

Latency

1.3s

TTFT

1.2s

Tok/s

153.5

Tok/s (adj)

379.2

complete-stream-parity

ok

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

stream="Paris" · complete="Paris"

Result

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

801eb317-ed42-4c0e-92e4-310ed1559b43

Aug 8, 2026, 08:52:58

google:gemini-3.6-flash

Input

15

Output

1

Reasoning

0

Answer

1

Cost

$0.000030

Mode

streaming

Cost breakdown

Input $0.000023Output $0.000007

Latency

598ms

TTFT

592ms

Tok/s

1.7

Tok/s (adj)

154.8

75a2b388-c643-4101-b316-d476a8ca423b

Aug 8, 2026, 08:52:59

google:gemini-3.6-flash

Input

15

Output

1

Reasoning

0

Answer

1

Cost

$0.000030

Mode

non-streaming

Cost breakdown

Input $0.000023Output $0.000007

Latency

536ms

Tok/s

1.9

reasoning-conformance

ok

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

Class (from reasoning-config): toggleable.
off: out=597 · mid: out=1990 (rt=1350).

Result

{
  "class": "toggleable",
  "mode": "deterministic",
  "offOutputTokens": 597,
  "midOutputTokens": 1990,
  "midReasoningTokens": 1350
}

b3676c51-c956-4aa6-bee2-3443b96ed2b6

Aug 8, 2026, 08:53:02

google:gemini-3.6-flash

Input

92

Output

597

Reasoning

0

Answer

597

Cost

$0.0046

Mode

streaming

Cost breakdown

Input $0.000138Output $0.0045

Latency

3.4s

TTFT

749ms

Tok/s

178.0

Tok/s (adj)

229.2

8cff0df6-69e5-454a-8ae5-58b363533260

Aug 8, 2026, 08:53:11

google:gemini-3.6-flash

Input

92

Output

1,990

Reasoning

1,350

Answer

640

Cost

$0.0151

Mode

streaming

Cost breakdown

Input $0.000138Output $0.0149

Latency

9.0s

TTFT

6.3s

Tok/s

222.1

Tok/s (adj)

242.2

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
}

494fcb4e-8396-4a5e-bd47-4537e49b171c

Aug 8, 2026, 08:53:12

google:gemini-3.6-flash

Input

99

Output

18

Reasoning

0

Answer

18

Cost

$0.000284

Mode

streaming

Cost breakdown

Input $0.000148Output $0.000135

Latency

757ms

Tok/s

23.8

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
}

b6ef0e30-a21c-43eb-8d00-95e0193db1d5

Aug 8, 2026, 08:53:13

google:gemini-3.6-flash

Input

95

Output

72

Reasoning

54

Answer

18

Cost

$0.000682

Mode

streaming

Cost breakdown

Input $0.000142Output $0.000540

Latency

849ms

Tok/s

84.8

f959390c-0016-48f7-ba83-9c09e856ce47

Aug 8, 2026, 08:53:14

google:gemini-3.6-flash

Input

187

Output

33

Reasoning

17

Answer

16

Cost

$0.000528

Mode

streaming

Cost breakdown

Input $0.000280Output $0.000247

Latency

867ms

TTFT

836ms

Tok/s

38.1

Tok/s (adj)

519.3

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**. ### Calcul"

Result

{
  "signatureType": "google",
  "tokenCaptured": true,
  "reasoned": true,
  "answered": true,
  "continuation": "The current balance for account **acme-42** is **$1,234**.\n\n### Calculations\n\n1. **Parameters:**\n   * Initial Balance ($P$) = $\\$1,234$\n   *"
}

588ad906-4d72-4798-bd88-22789fe12562

Aug 8, 2026, 08:53:15

google:gemini-3.6-flash

Input

123

Output

147

Reasoning

127

Answer

20

Cost

$0.0013

Mode

streaming

Cost breakdown

Input $0.000185Output $0.0011

Latency

1.3s

Tok/s

112.6

1c2d144a-c9bd-453d-b043-733ba0b11f4e

Aug 8, 2026, 08:53:17

google:gemini-3.6-flash

Input

297

Output

353

Reasoning

0

Answer

353

Cost

$0.0031

Mode

streaming

Cost breakdown

Input $0.000446Output $0.0026

Latency

2.2s

TTFT

530ms

Tok/s

161.2

Tok/s (adj)

212.6

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
}

d3b03c93-b837-42ba-96b1-33485224a7a8

Aug 8, 2026, 08:53:18

google:gemini-3.6-flash

Input

10,121

Output

77

Reasoning

77

Answer

0

Cost

$0.0158

Mode

non-streaming

Cost breakdown

Input $0.0152Output $0.000577

Latency

1.1s

Tok/s

72.4

f605ce7a-c377-4729-8706-7115c35bf34f

Aug 8, 2026, 08:53:20

google:gemini-3.6-flash

Input

10,121

Output

76

Reasoning

74

Answer

2

Cost

$0.0158

Mode

non-streaming

Cost breakdown

Input $0.0152Output $0.000570

Latency

1.2s

Tok/s

65.1

36004ccb-670e-447e-8870-7fb39ff612d1

Aug 8, 2026, 08:53:21

google:gemini-3.6-flash

Input

10,121

Output

76

Reasoning

76

Answer

0

Cost

$0.0158

Mode

non-streaming

Cost breakdown

Input $0.0152Output $0.000570

Latency

1.1s

Tok/s

71.5

986c4425-0f69-4e36-abe9-5599096cd7f4

Aug 8, 2026, 08:53:22

google:gemini-3.6-flash

Input

10,121

Output

76

Reasoning

72

Answer

4

Cost

$0.0158

Mode

non-streaming

Cost breakdown

Input $0.0152Output $0.000570

Latency

1.1s

Tok/s

72.4

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
}

bc6bf503-ec78-4909-92e6-932a190755da

Aug 8, 2026, 08:53:22

google:gemini-3.6-flash

Input

57

Output

26

Reasoning

0

Answer

26

Cost

$0.000280

Mode

streaming

Cost breakdown

Input $0.000086Output $0.000195

Latency

777ms

TTFT

666ms

Tok/s

33.5

Tok/s (adj)

233.3

summarize-memex

ok

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

Read ~10155 input tokens, wrote 377 words (462 output tokens) in 4987ms.

Result

{
  "wordCount": 377,
  "inputTokens": 10155,
  "outputTokens": 462,
  "latencyMs": 4987
}

462ed6a1-a83e-417f-b031-edf82f09b6d2

Aug 8, 2026, 08:53:27

google:gemini-3.6-flash

Input

10,155

Output

462

Reasoning

0

Answer

462

Cost

$0.0187

Mode

streaming

Cost breakdown

Input $0.0152Output $0.0035

Latency

5.0s

TTFT

1.6s

Tok/s

92.6

Tok/s (adj)

134.7

truncation

ok

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

finishReason=length, out=96 tokens.

Result

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

0fbc45eb-413b-46d3-bc55-bf148cd0ba47

Aug 8, 2026, 08:53:29

google:gemini-3.6-flash

Input

21

Output

96

Reasoning

0

Answer

96

Cost

$0.000751

Mode

streaming

Cost breakdown

Input $0.000031Output $0.000720

Latency

1.1s

TTFT

502ms

Tok/s

89.1

Tok/s (adj)

166.9

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"
}