Armand McQueen

basic-generation

ok

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

Produced 104 words (0 output tokens).

Result

{
  "wordCount": 104,
  "outputTokens": 0
}

79ddde6a-d03e-4221-9048-a1500128279e

Aug 8, 2026, 08:54:34

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

3.0s

TTFT

1.0s

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
}

845797d3-d21b-4acc-aa66-96ea4ecdd8cd

Aug 8, 2026, 08:54:43

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

9.0s

TTFT

7.5s

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, 24 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 24,
  "textBlocks": 1,
  "textLen": 35
}

f5b605b7-8fe8-443f-8581-ed8395432243

Aug 8, 2026, 08:54:46

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

2.1s

TTFT

2.0s

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"
}

c2833e92-8c7b-43a7-809b-06b6bfae3e49

Aug 8, 2026, 08:54:46

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

887ms

TTFT

847ms

Tok/s

0.0

Tok/s (adj)

0.0

85dc124a-9849-4b9b-9819-a8bc0c2bd31b

Aug 8, 2026, 08:54:48

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

1.2s

Tok/s

5.9

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
}

b1f67c48-8047-43b7-9fe2-3ff9ebd4a946

Aug 8, 2026, 08:54:57

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

9.7s

TTFT

628ms

Tok/s

0.0

Tok/s (adj)

0.0

621bee90-e280-4958-a086-ebac57ac0d0b

Aug 8, 2026, 08:55:04

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

6.6s

TTFT

3.5s

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
}

d6145020-f6ec-4b46-a60d-5601af75035c

Aug 8, 2026, 08:55:08

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

4.1s

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
}

f555b23c-72e5-4ac9-8c32-3a6e57b5eb07

Aug 8, 2026, 08:55:11

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

2.7s

Tok/s

0.0

0b13dbba-ca01-4221-8904-871f4f3b7672

Aug 8, 2026, 08:55:12

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

1.5s

TTFT

1.3s

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`:** $1,234.00 **Calculation (5% annual"

Result

{
  "signatureType": "none",
  "tokenCaptured": false,
  "reasoned": false,
  "answered": true,
  "continuation": "**Balance for account `acme-42`:** $1,234.00\n\n**Calculation (5% annual compound growth for 7 years):**\n\n\\[\n\\text{Future Balance} = 1234 \\tim"
}

9f43c195-96e5-4dff-b78a-178d1f6ee3e8

Aug 8, 2026, 08:55:24

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Reasoning

~0

Answer

~0

Cost

$0.000000

Mode

streaming

Latency

5.6s

Tok/s

0.0

d48efc47-3880-4b70-94e4-795290d18929

Aug 8, 2026, 08:55:32

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

8.3s

TTFT

2.4s

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
}

468e0fd8-61c3-4699-b2a7-b9a9dc6a1cc8

Aug 8, 2026, 08:55:35

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

3.0s

TTFT

2.3s

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 457 words (0 output tokens) in 18214ms.

Result

{
  "wordCount": 457,
  "inputTokens": 0,
  "outputTokens": 0,
  "latencyMs": 18214
}

f79e4f47-8779-409e-b643-675fd159d0ca

Aug 8, 2026, 08:55:53

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

18.2s

TTFT

2.4s

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
}

8afa8db7-60e9-40a8-b08c-4f9857522775

Aug 8, 2026, 08:55:56

togetherai:moonshotai/Kimi-K3

Input

0

Output

0

Cost

$0.000000

Mode

streaming

Latency

3.2s

TTFT

1.7s

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"
}