together:inkling-small

8/8/2026, 8:57:34 AM · 15 tests · run dd754b70-f21d-476b-9bb9-2d041577ec66

basic-generation

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

Produced 88 words (0 output tokens).

Result

{
  "wordCount": 88,
  "outputTokens": 0
}

1cdb4dbe-b437-4e35-b925-5bec4da82993

Aug 8, 2026, 08:57:11

togetherai:thinkingmachines/Inkling-Small

Input

Output

Cost

$0.000000

Mode

streaming

Latency

781ms

TTFT

216ms

Tok/s

0.0

Tok/s (adj)

0.0

usage-cost

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
}

dd5eccac-c07c-4e2c-8d11-e72e92f9af1e

Aug 8, 2026, 08:57:13

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000000

Mode

streaming

Latency

1.9s

TTFT

1.8s

Tok/s

0.0

Tok/s (adj)

0.0

streaming-structure

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

mode=streaming, 116 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 116,
  "textBlocks": 1,
  "textLen": 35
}

c3575d4a-832d-46d7-8438-977a47b523ee

Aug 8, 2026, 08:57:13

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000000

Mode

streaming

Latency

719ms

TTFT

581ms

Tok/s

0.0

Tok/s (adj)

0.0

complete-stream-parity

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

stream="Paris" · complete="Paris"

Result

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

439e1c9d-56ee-43dd-b4e1-0ae2002766ae

Aug 8, 2026, 08:57:14

togetherai:thinkingmachines/Inkling-Small

Input

Output

Cost

$0.000000

Mode

streaming

Latency

153ms

TTFT

143ms

Tok/s

0.0

Tok/s (adj)

0.0

da0d7102-eec2-45b0-aa2a-de583b85eff1

Aug 8, 2026, 08:57:14

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000018

Mode

non-streaming

Cost breakdown

Input $0.000013Output $0.000005

Latency

153ms

Tok/s

26.1

reasoning-conformance

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
}

6aed1d9e-9dde-461a-a475-d293eec88bb0

Aug 8, 2026, 08:57:16

togetherai:thinkingmachines/Inkling-Small

Input

Output

Cost

$0.000000

Mode

streaming

Latency

2.7s

TTFT

137ms

Tok/s

0.0

Tok/s (adj)

0.0

177c6e3c-4efc-4fe2-ac7b-1e731c6a9d29

Aug 8, 2026, 08:57:23

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000000

Mode

streaming

Latency

6.6s

TTFT

2.9s

Tok/s

0.0

Tok/s (adj)

0.0

single-tool-call

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
}

90b5b08b-771c-4cf4-b796-48f9a184b9a3

Aug 8, 2026, 08:57:23

togetherai:thinkingmachines/Inkling-Small

Input

Output

Cost

$0.000000

Mode

streaming

Latency

322ms

Tok/s

0.0

tool-loop

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

step1 (required): multiply({"a":23,"b":17}) → step2: "The product of23 and17 is391."

Result

{
  "toolName": "multiply",
  "args": {
    "a": 23,
    "b": 17
  },
  "product": 391,
  "continuation": "The product of23 and17 is391.",
  "usesResult": true,
  "forced": true
}

a4909f63-94da-43d5-a342-d9a143268a42

Aug 8, 2026, 08:57:24

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000000

Mode

streaming

Latency

389ms

Tok/s

0.0

246dbc08-adad-4ada-9b7e-f1606d06f6d9

Aug 8, 2026, 08:57:24

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000000

Mode

streaming

Latency

357ms

TTFT

270ms

Tok/s

0.0

Tok/s (adj)

0.0

web-search

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

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 → "Using `get_balance`, account **acme-42** has a balance of **$1,234**. "

Result

{
  "signatureType": "none",
  "tokenCaptured": false,
  "reasoned": false,
  "answered": true,
  "continuation": "Using `get_balance`, account **acme-42** has a balance of **$1,234**.\n\nCalculation (5% annual compound growth for7 years):\n\n\\[\nB =1234 \\time"
}

22ea5907-080e-4323-b83c-f59d566ddeea

Aug 8, 2026, 08:57:25

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000000

Mode

streaming

Latency

357ms

Tok/s

0.0

01fca536-cb54-4e97-8564-aed6ac2dd7cd

Aug 8, 2026, 08:57:28

togetherai:thinkingmachines/Inkling-Small

Input

Output

Reasoning

Answer

Cost

$0.000000

Mode

streaming

Latency

3.2s

TTFT

2.4s

Tok/s

0.0

Tok/s (adj)

0.0

prompt-cache

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

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
}

d1931184-4892-471d-ae04-72eda21883ae

Aug 8, 2026, 08:57:29

togetherai:thinkingmachines/Inkling-Small

Input

Output

Cost

$0.000000

Mode

streaming

Latency

269ms

TTFT

164ms

Tok/s

0.0

Tok/s (adj)

0.0

summarize-memex

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

Read ~0 input tokens, wrote 377 words (0 output tokens) in 3877ms.

Result

{
  "wordCount": 377,
  "inputTokens": 0,
  "outputTokens": 0,
  "latencyMs": 3877
}

cddf69c5-4bc2-474c-8cb4-2a70479d0295

Aug 8, 2026, 08:57:32

togetherai:thinkingmachines/Inkling-Small

Input

Output

Cost

$0.000000

Mode

streaming

Latency

3.9s

TTFT

416ms

Tok/s

0.0

Tok/s (adj)

0.0

truncation

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

finishReason=length, out=0 tokens.

Result

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

771ab170-584f-464e-b723-7ee8abcda30d

Aug 8, 2026, 08:57:34

togetherai:thinkingmachines/Inkling-Small

Input

Output

Cost

$0.000000

Mode

streaming

Latency

1.0s

TTFT

209ms

Tok/s

0.0

Tok/s (adj)

0.0

streaming-only-rejection

Streaming-only models reject complete(); all others accept it.

streamingOnly=false; complete() succeeded.

Result

{
  "streamingOnly": false,
  "completeThrew": false
}

abort

A pre-aborted signal rejects the call (abort is threaded + honored).

pre-aborted signal → rejected (AbortError).

Result

{
  "rejected": true,
  "errorName": "AbortError"
}