Armand McQueen

basic-generation

ok

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

Produced 91 words (123 output tokens).

Result

{
  "wordCount": 91,
  "outputTokens": 123
}

6aba53fe-1c40-4150-a60e-d092e75d29ec

Aug 17, 2026, 07:17:42

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

266

Output

123

Reasoning

0

Answer

123

Cache Read

224

Cost

$0.000456

Mode

streaming

Cost breakdown

Input $0.000042Output $0.000369Cache read $0.000045

Latency

2.5s

TTFT

1.2s

Tok/s

48.3

Tok/s (adj)

89.2

usage-cost

ok

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

in=259 out=178 rt=0 cost=$0.000614 (paid).

Result

{
  "inputTokens": 259,
  "outputTokens": 178,
  "reasoningTokens": 0,
  "costUsd": 0.0006138,
  "paid": true
}

38e65d46-c017-4cd3-99c3-874e30676c91

Aug 17, 2026, 07:17:44

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

259

Output

178

Reasoning

0

Answer

178

Cache Read

224

Cost

$0.000614

Mode

streaming

Cost breakdown

Input $0.000035Output $0.000534Cache read $0.000045

Latency

2.2s

TTFT

2.0s

Tok/s

79.2

Tok/s (adj)

649.0

streaming-structure

ok

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

mode=streaming, 28 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 28,
  "textBlocks": 1,
  "textLen": 35
}

a2cc5033-d31f-47d4-835b-62643abbdb19

Aug 17, 2026, 07:17:45

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

265

Output

60

Reasoning

0

Answer

60

Cache Read

224

Cost

$0.000266

Mode

streaming

Cost breakdown

Input $0.000041Output $0.000180Cache read $0.000045

Latency

781ms

TTFT

601ms

Tok/s

76.8

Tok/s (adj)

333.0

complete-stream-parity

ok

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

stream="Paris" · complete="Paris"

Result

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

9ac0b9b8-db13-4d4e-980c-b425ce85257b

Aug 17, 2026, 07:17:45

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

267

Output

2

Reasoning

0

Answer

2

Cache Read

224

Cost

$0.000094

Mode

streaming

Cost breakdown

Input $0.000043Output $0.000006Cache read $0.000045

Latency

321ms

TTFT

319ms

Tok/s

6.2

Tok/s (adj)

1234.6

913f873f-8f49-4014-bfa4-55e936275f96

Aug 17, 2026, 07:17:46

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

267

Output

2

Reasoning

0

Answer

2

Cache Read

240

Cost

$0.000081

Mode

non-streaming

Cost breakdown

Input $0.000027Output $0.000006Cache read $0.000048

Latency

292ms

Tok/s

6.8

reasoning-conformance

ok

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

Class (from reasoning-config): toggleable.
off: out=450 · mid: out=657 (rt=0).

Result

{
  "class": "toggleable",
  "mode": "deterministic",
  "offOutputTokens": 450,
  "midOutputTokens": 657,
  "midReasoningTokens": 0
}

12682344-d97e-4494-9b22-f1e4790aca99

Aug 17, 2026, 07:17:49

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

344

Output

450

Reasoning

0

Answer

450

Cache Read

224

Cost

$0.0015

Mode

streaming

Cost breakdown

Input $0.000120Output $0.0014Cache read $0.000045

Latency

3.7s

TTFT

231ms

Tok/s

122.3

Tok/s (adj)

130.6

7a2f6eff-9b19-4a3f-aa91-85c1e5d10e53

Aug 17, 2026, 07:17:59

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

342

Output

657

Reasoning

0

Answer

657

Cache Read

320

Cost

$0.0021

Mode

streaming

Cost breakdown

Input $0.000022Output $0.0020Cache read $0.000064

Latency

9.2s

TTFT

3.6s

Tok/s

71.1

Tok/s (adj)

115.8

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
}

7e175fe3-9e2a-4eb5-a70e-e3c6fcaa38f0

Aug 17, 2026, 07:18:02

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

334

Output

30

Reasoning

0

Answer

30

Cost

$0.000424

Mode

streaming

Cost breakdown

Input $0.000334Output $0.000090

Latency

3.0s

Tok/s

10.0

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: "<think>The tool returned product: 391. I need to state the product in a sentence"

Result

{
  "toolName": "multiply",
  "args": {
    "a": 23,
    "b": 17
  },
  "product": 391,
  "continuation": "<think>The tool returned product: 391. I need to state the product in a sentence. I should say something like \"The product of 23 multiplied by 17 is 391.\" Provi",
  "usesResult": true,
  "forced": true
}

ae8b2c97-4ab2-45bb-9279-9c4e0d5fe535

Aug 17, 2026, 07:18:02

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

326

Output

37

Reasoning

0

Answer

37

Cost

$0.000437

Mode

streaming

Cost breakdown

Input $0.000326Output $0.000111

Latency

626ms

Tok/s

59.1

79ff52bd-ad88-4722-9c5e-ec5135023b9a

Aug 17, 2026, 07:18:04

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

376

Output

76

Reasoning

0

Answer

76

Cache Read

304

Cost

$0.000361

Mode

streaming

Cost breakdown

Input $0.000072Output $0.000228Cache read $0.000061

Latency

1.5s

TTFT

396ms

Tok/s

51.5

Tok/s (adj)

70.3

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.

Step 1 didn't engage reasoning (adaptive discretion) — signature not exercised this run.
reasoned=false, none token —; follow-up → "The current balance for account 'acme-42' is **$1,234**. ## Calculati"

Result

{
  "signatureType": "none",
  "tokenCaptured": false,
  "reasoned": false,
  "answered": true,
  "continuation": "The current balance for account 'acme-42' is **$1,234**.\n\n## Calculation for 5% Annual Growth Over 7 Years\n\n**Formula for compound interest:"
}

0ed780f3-f5c1-4080-9821-f799fa26c13d

Aug 17, 2026, 07:18:09

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

343

Output

157

Reasoning

0

Answer

157

Cache Read

320

Cost

$0.000558

Mode

streaming

Cost breakdown

Input $0.000023Output $0.000471Cache read $0.000064

Latency

1.8s

TTFT

208ms

Tok/s

87.3

Tok/s (adj)

98.8

06fa2dc4-8479-4954-a910-afb5e05d903f

Aug 17, 2026, 07:18:12

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

523

Output

301

Reasoning

0

Answer

301

Cache Read

480

Cost

$0.0010

Mode

streaming

Cost breakdown

Input $0.000043Output $0.000903Cache read $0.000096

Latency

3.3s

TTFT

305ms

Tok/s

90.9

Tok/s (adj)

100.1

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, USA"
  },
  "validJson": true,
  "missingKeys": [],
  "bareJson": true
}

d30c47e6-ea51-499c-a78e-bf9eef40cb3a

Aug 17, 2026, 07:18:13

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

70

Output

25

Reasoning

0

Answer

25

Cost

$0.000145

Mode

streaming

Cost breakdown

Input $0.000070Output $0.000075

Latency

806ms

TTFT

580ms

Tok/s

31.0

Tok/s (adj)

110.7

summarize-memex

ok

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

Read ~10265 input tokens, wrote 496 words (619 output tokens) in 8972ms.

Result

{
  "wordCount": 496,
  "inputTokens": 10265,
  "outputTokens": 619,
  "latencyMs": 8972
}

2e517add-f36c-4c05-a994-0b3331a32d53

Aug 17, 2026, 07:18:22

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

10,265

Output

619

Reasoning

0

Answer

619

Cost

$0.0121

Mode

streaming

Cost breakdown

Input $0.0103Output $0.0019

Latency

9.0s

TTFT

746ms

Tok/s

69.0

Tok/s (adj)

75.3

truncation

ok

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

finishReason=length, out=100 tokens.

Result

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

7a8018cd-cad9-4ee5-a440-16964283c736

Aug 17, 2026, 07:18:25

deepinfra:XiaomiMiMo/MiMo-V2.5-Pro

Input

272

Output

100

Reasoning

0

Answer

100

Cache Read

224

Cost

$0.000393

Mode

streaming

Cost breakdown

Input $0.000048Output $0.000300Cache read $0.000045

Latency

3.8s

TTFT

2.7s

Tok/s

26.3

Tok/s (adj)

87.5

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"
}