Armand McQueen

basic-generation

ok

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

Produced 93 words (0 output tokens).

Result

{
  "wordCount": 93,
  "outputTokens": 0
}

4b4bbee2-e545-4dd4-8f8e-427694c00447

Aug 8, 2026, 08:57:42

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

7.9s

TTFT

4.9s

Tok/s

0.0

Tok/s (adj)

0.0

usage-cost

ok

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

in=0 out=0 rt=— cost=$0.000000 (paid).

Result

{
  "inputTokens": 0,
  "outputTokens": 0,
  "reasoningTokens": null,
  "costUsd": 0,
  "paid": true
}

71525ef2-1e96-4c17-a1ce-cd3b959ad897

Aug 8, 2026, 08:57:56

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

13.8s

TTFT

13.7s

Tok/s

0.0

Tok/s (adj)

0.0

streaming-structure

ok

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

mode=streaming, 23 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 23,
  "textBlocks": 1,
  "textLen": 35
}

defdf07a-231d-44e5-b1b7-b9149b42f414

Aug 8, 2026, 08:58:02

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

6.1s

TTFT

5.4s

Tok/s

0.0

Tok/s (adj)

0.0

complete-stream-parity

ok

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

stream="Paris" · complete="Paris"

Result

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

334ce7e1-c376-4201-bd15-e37175aafc4d

Aug 8, 2026, 08:58:04

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

1.7s

TTFT

1.7s

Tok/s

0.0

Tok/s (adj)

0.0

8f8fd2fa-e88c-4e10-826b-a0bf716eb13f

Aug 8, 2026, 08:58:06

togetherai:moonshotai/Kimi-K3

Input

32

Output

7

Reasoning

0

Answer

7

Cost

$0.000201

Mode

non-streaming

Cost breakdown

Input $0.000096Output $0.000105

Latency

2.0s

Tok/s

3.6

reasoning-conformance

ok

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

Class (from reasoning-config): toggleable.
off: out=0 · mid: out=0 (rt=—).

Result

{
  "class": "toggleable",
  "mode": "deterministic",
  "offOutputTokens": 0,
  "midOutputTokens": 0,
  "midReasoningTokens": null
}

750d35fb-db42-4957-a8fc-41395bb60308

Aug 8, 2026, 08:58:20

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

14.4s

TTFT

7.5s

Tok/s

0.0

Tok/s (adj)

0.0

1438a7f7-fee7-4690-932e-03dddbfd3907

Aug 8, 2026, 08:58:30

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

9.8s

TTFT

6.7s

Tok/s

0.0

Tok/s (adj)

0.0

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
}

2959f42d-da8d-41fc-9c48-6b45d9a07c03

Aug 8, 2026, 08:58:40

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

10.3s

Tok/s

0.0

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
}

d1e4ac6a-af0e-491a-b80b-d36f2b0ad5b5

Aug 8, 2026, 08:59:55

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

74.8s

Tok/s

0.0

b42ffcb6-85fb-4fa0-840e-8fbcb3a8b8bd

Aug 8, 2026, 09:00:08

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

13.1s

TTFT

13.0s

Tok/s

0.0

Tok/s (adj)

0.0

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.

Step 1 didn't engage reasoning (adaptive discretion) — signature not exercised this run.
reasoned=false, none token —; follow-up → "Balance for account 'acme-42': **$1,234** **Calculation:** - Growth f"

Result

{
  "signatureType": "none",
  "tokenCaptured": false,
  "reasoned": false,
  "answered": true,
  "continuation": "Balance for account 'acme-42': **$1,234**\n\n**Calculation:**\n- Growth factor: 1.05^7 = 1.40710042265625\n- Future balance: 1,234 × 1.407100422"
}

d6def6bc-054b-4139-b2b5-0a371061946b

Aug 8, 2026, 09:00:53

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

21.7s

Tok/s

0.0

9bc01209-debc-46aa-afbc-ab08a143db12

Aug 8, 2026, 09:01:27

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

33.8s

TTFT

32.7s

Tok/s

0.0

Tok/s (adj)

0.0

prompt-cache

ok

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

Skipped: provider has no (known) prompt-cache reporting.

Result

{
  "skipped": "cacheStyle=none"
}

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
}

204c2b46-fe60-4b83-919f-36341b93f908

Aug 8, 2026, 09:01:50

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

23.5s

TTFT

23.2s

Tok/s

0.0

Tok/s (adj)

0.0

summarize-memex

ok

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

Read ~0 input tokens, wrote 488 words (0 output tokens) in 25439ms.

Result

{
  "wordCount": 488,
  "inputTokens": 0,
  "outputTokens": 0,
  "latencyMs": 25439
}

626c3366-9057-42ae-bf3f-119927d95365

Aug 8, 2026, 09:02:16

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

25.4s

TTFT

2.0s

Tok/s

0.0

Tok/s (adj)

0.0

truncation

ok

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

finishReason=length, out=0 tokens.

Result

{
  "finishReason": "length",
  "outputTokens": 0
}

555898eb-ccbe-48fc-9a97-520418c2ff4b

Aug 8, 2026, 09:02:27

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

11.0s

TTFT

7.6s

Tok/s

0.0

Tok/s (adj)

0.0

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"
}