Armand McQueen

basic-generation

ok

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

Produced 67 words (193 output tokens).

Result

{
  "wordCount": 67,
  "outputTokens": 193
}

2152047f-ade4-4bbf-8421-953009fa3bb8

Aug 18, 2026, 07:13:57

mixedbread:toast-1

Input

403

Output

193

Reasoning

0

Answer

193

Cost

$0.000433

Mode

streaming

Cost breakdown

Input $0.000201Output $0.000232

Latency

1.1s

TTFT

1.0s

Tok/s

175.3

Tok/s (adj)

2494.5

usage-cost

ok

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

in=398 out=37 rt=0 cost=$0.000243 (paid).

Result

{
  "inputTokens": 398,
  "outputTokens": 37,
  "reasoningTokens": 0,
  "costUsd": 0.0002434,
  "paid": true
}

99ac8f85-eceb-450a-a7fe-5e1fca0bd432

Aug 18, 2026, 07:13:58

mixedbread:toast-1

Input

398

Output

37

Reasoning

0

Answer

37

Cost

$0.000243

Mode

streaming

Cost breakdown

Input $0.000199Output $0.000044

Latency

840ms

TTFT

751ms

Tok/s

44.0

Tok/s (adj)

417.7

streaming-structure

ok

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

mode=streaming, 10 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 10,
  "textBlocks": 1,
  "textLen": 35
}

8ba913e6-092f-4222-97a9-ecd02002997e

Aug 18, 2026, 07:13:59

mixedbread:toast-1

Input

404

Output

97

Reasoning

0

Answer

97

Cost

$0.000318

Mode

streaming

Cost breakdown

Input $0.000202Output $0.000116

Latency

623ms

TTFT

562ms

Tok/s

155.7

Tok/s (adj)

1593.3

complete-stream-parity

ok

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

stream="Paris" · complete="Paris"

Result

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

f51e7f2f-ca2f-4d5a-8af0-5b169ac99e47

Aug 18, 2026, 07:13:59

mixedbread:toast-1

Input

404

Output

29

Reasoning

0

Answer

29

Cost

$0.000237

Mode

streaming

Cost breakdown

Input $0.000202Output $0.000035

Latency

634ms

TTFT

510ms

Tok/s

45.7

Tok/s (adj)

234.1

2373df3b-70ca-456a-bd22-ffdbb7f8d012

Aug 18, 2026, 07:14:00

mixedbread:toast-1

Input

404

Output

2

Reasoning

0

Answer

2

Cache Read

256

Cost

$0.000092

Mode

non-streaming

Cost breakdown

Input $0.000074Output $0.000002Cache read $0.000015

Latency

685ms

Tok/s

2.9

reasoning-conformance

ok

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

Class (from reasoning-config): always-on.
reasoningTokens=0, outputTokens=448.

Result

{
  "class": "always-on",
  "reasoningTokens": 0,
  "outputTokens": 448
}

b58cabd2-9e97-4849-bfaa-9e7ac46735be

Aug 18, 2026, 07:14:01

mixedbread:toast-1

Input

481

Output

448

Reasoning

0

Answer

448

Cache Read

256

Cost

$0.000665

Mode

streaming

Cost breakdown

Input $0.000112Output $0.000538Cache read $0.000015

Latency

1.2s

TTFT

1.1s

Tok/s

367.8

Tok/s (adj)

3942.3

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
}

910d9249-3a79-486b-9bde-0f7590d8d23d

Aug 18, 2026, 07:14:02

mixedbread:toast-1

Input

554

Output

58

Reasoning

0

Answer

58

Cost

$0.000347

Mode

streaming

Cost breakdown

Input $0.000277Output $0.000070

Latency

628ms

Tok/s

92.4

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 equals 391."

Result

{
  "toolName": "multiply",
  "args": {
    "a": 23,
    "b": 17
  },
  "product": 391,
  "continuation": "23 multiplied by 17 equals 391.",
  "usesResult": true,
  "forced": true
}

32b95564-377c-4c73-adfc-c09f14edd3cd

Aug 18, 2026, 07:14:02

mixedbread:toast-1

Input

568

Output

67

Reasoning

0

Answer

67

Cost

$0.000364

Mode

streaming

Cost breakdown

Input $0.000284Output $0.000080

Latency

652ms

Tok/s

102.8

cf0174b0-0300-4974-bf9c-122173c04ec6

Aug 18, 2026, 07:14:03

mixedbread:toast-1

Input

612

Output

53

Reasoning

0

Answer

53

Cache Read

512

Cost

$0.000144

Mode

streaming

Cost breakdown

Input $0.000050Output $0.000064Cache read $0.000031

Latency

644ms

TTFT

534ms

Tok/s

82.3

Tok/s (adj)

483.7

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 → "Current balance: $1,234. After 7 years at 5% annual compounding: $1,23"

Result

{
  "signatureType": "none",
  "tokenCaptured": false,
  "reasoned": false,
  "answered": true,
  "continuation": "Current balance: $1,234. After 7 years at 5% annual compounding: $1,234 × (1.05)^7 = $1,738.66 ≈ $1,739. Double the original balance: $2,468"
}

62c71a3a-daaf-4b56-b1d8-83613ed1d049

Aug 18, 2026, 07:14:05

mixedbread:toast-1

Input

576

Output

56

Reasoning

0

Answer

56

Cache Read

512

Cost

$0.000130

Mode

streaming

Cost breakdown

Input $0.000032Output $0.000067Cache read $0.000031

Latency

651ms

Tok/s

86.0

ebdbe68c-dc5d-4080-8b1b-aa62ab5f9022

Aug 18, 2026, 07:14:06

mixedbread:toast-1

Input

633

Output

230

Reasoning

0

Answer

230

Cache Read

512

Cost

$0.000367

Mode

streaming

Cost breakdown

Input $0.000061Output $0.000276Cache read $0.000031

Latency

899ms

TTFT

843ms

Tok/s

255.8

Tok/s (adj)

4077.3

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 had leading prose or a code fence before the JSON.

Result

{
  "parsed": {
    "name": "Anthropic",
    "founded": 2021,
    "headquarters": "San Francisco, California"
  },
  "validJson": true,
  "missingKeys": [],
  "bareJson": false
}

3cc15424-6925-488b-9318-d370c070c541

Aug 18, 2026, 07:14:07

mixedbread:toast-1

Input

448

Output

33

Reasoning

0

Answer

33

Cache Read

256

Cost

$0.000151

Mode

streaming

Cost breakdown

Input $0.000096Output $0.000040Cache read $0.000015

Latency

736ms

TTFT

505ms

Tok/s

44.8

Tok/s (adj)

142.6

summarize-memex

ok

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

Read ~10762 input tokens, wrote 342 words (440 output tokens) in 2404ms.

Result

{
  "wordCount": 342,
  "inputTokens": 10762,
  "outputTokens": 440,
  "latencyMs": 2404
}

44b534bb-4ae5-43d8-98c5-ffd0ec95892c

Aug 18, 2026, 07:14:09

mixedbread:toast-1

Input

10,762

Output

440

Reasoning

0

Answer

440

Cost

$0.0059

Mode

streaming

Cost breakdown

Input $0.0054Output $0.000528

Latency

2.4s

TTFT

2.3s

Tok/s

183.0

Tok/s (adj)

4854.9

truncation

ok

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

finishReason=length, out=100 tokens.

Result

{
  "finishReason": "length",
  "outputTokens": 100
}

8e3528f0-a0d1-45b0-ae43-30bfef834890

Aug 18, 2026, 07:14:10

mixedbread:toast-1

Input

409

Output

100

Reasoning

0

Answer

100

Cost

$0.000325

Mode

streaming

Cost breakdown

Input $0.000205Output $0.000120

Latency

751ms

TTFT

706ms

Tok/s

133.2

Tok/s (adj)

2244.7

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"
}