Armand McQueen

basic-generation

ok

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

Produced 96 words (139 output tokens).

Result

{
  "wordCount": 96,
  "outputTokens": 139
}

80bc696b-c284-40cd-91f2-97040235f533

Aug 17, 2026, 07:15:53

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

15

Output

139

Reasoning

0

Answer

139

Cost

$0.000381

Mode

streaming

Cost breakdown

Input $0.000019Output $0.000361

Latency

4.6s

TTFT

483ms

Tok/s

30.0

Tok/s (adj)

33.5

usage-cost

ok

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

in=14 out=6 rt=0 cost=$0.000034 (paid).

Result

{
  "inputTokens": 14,
  "outputTokens": 6,
  "reasoningTokens": 0,
  "costUsd": 0.0000338,
  "paid": true
}

74a7cd71-5f14-4617-9518-0f039afed0b5

Aug 17, 2026, 07:15:53

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

14

Output

6

Reasoning

0

Answer

6

Cost

$0.000034

Mode

streaming

Cost breakdown

Input $0.000018Output $0.000016

Latency

439ms

TTFT

437ms

Tok/s

13.7

Tok/s (adj)

2898.6

streaming-structure

ok

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

mode=streaming, 8 stream events, 1 text block(s), 35 chars.

Result

{
  "mode": "streaming",
  "streamEventCount": 8,
  "textBlocks": 1,
  "textLen": 35
}

44376e3f-f14f-4d55-8dbd-2a3c086db2f8

Aug 17, 2026, 07:15:54

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

17

Output

30

Reasoning

0

Answer

30

Cost

$0.000100

Mode

streaming

Cost breakdown

Input $0.000022Output $0.000078

Latency

641ms

TTFT

607ms

Tok/s

46.8

Tok/s (adj)

875.7

complete-stream-parity

ok

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

stream="Paris" · complete="Paris"

Result

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

69c7049f-b79b-4cb6-b570-768a472072b3

Aug 17, 2026, 07:15:54

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

18

Output

2

Reasoning

0

Answer

2

Cost

$0.000029

Mode

streaming

Cost breakdown

Input $0.000023Output $0.000005

Latency

426ms

TTFT

425ms

Tok/s

4.7

Tok/s (adj)

3571.4

98b12aff-c3cc-466a-8beb-4eca5793b8d5

Aug 17, 2026, 07:15:54

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

18

Output

2

Reasoning

0

Answer

2

Cost

$0.000029

Mode

non-streaming

Cost breakdown

Input $0.000023Output $0.000005

Latency

288ms

Tok/s

6.9

reasoning-conformance

ok

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

Class (from reasoning-config): toggleable.
off: out=559 · mid: out=775 (rt=0).

Result

{
  "class": "toggleable",
  "mode": "deterministic",
  "offOutputTokens": 559,
  "midOutputTokens": 775,
  "midReasoningTokens": 0
}

0d07697e-5951-4a6d-8784-ec2ba0b593bd

Aug 17, 2026, 07:16:05

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

89

Output

559

Reasoning

0

Answer

559

Cost

$0.0016

Mode

streaming

Cost breakdown

Input $0.000116Output $0.0015

Latency

10.4s

TTFT

673ms

Tok/s

53.8

Tok/s (adj)

57.6

27af1a80-e597-44f8-b652-45bfdbccb14c

Aug 17, 2026, 07:16:18

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

89

Output

775

Reasoning

0

Answer

775

Cost

$0.0021

Mode

streaming

Cost breakdown

Input $0.000116Output $0.0020

Latency

12.8s

TTFT

10.2s

Tok/s

60.7

Tok/s (adj)

297.3

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
}

371d814d-9dae-4d91-b923-29e71250cf85

Aug 17, 2026, 07:16:19

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

351

Output

60

Reasoning

0

Answer

60

Cost

$0.000612

Mode

streaming

Cost breakdown

Input $0.000456Output $0.000156

Latency

921ms

Tok/s

65.1

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
}

c2a16663-b93a-4962-8cde-4bd69628e866

Aug 17, 2026, 07:16:19

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

347

Output

60

Reasoning

0

Answer

60

Cache Read

256

Cost

$0.000300

Mode

streaming

Cost breakdown

Input $0.000118Output $0.000156Cache read $0.000026

Latency

701ms

Tok/s

85.6

6ea1e357-c54d-4992-b180-704f78386370

Aug 17, 2026, 07:16:21

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

422

Output

10

Reasoning

0

Answer

10

Cache Read

256

Cost

$0.000267

Mode

streaming

Cost breakdown

Input $0.000216Output $0.000026Cache read $0.000026

Latency

1.4s

TTFT

1.3s

Tok/s

7.2

Tok/s (adj)

195.4

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 **$1,234.00**. --- ### "

Result

{
  "signatureType": "none",
  "tokenCaptured": false,
  "reasoned": false,
  "answered": true,
  "continuation": "The current balance for account `acme-42` is **$1,234.00**.\n\n---\n\n### Compound Interest Calculation\n\nWe assume 5% annual compounding for 7 y"
}

b4844874-f34e-4457-b20a-b755406f9fd8

Aug 17, 2026, 07:16:25

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

377

Output

120

Reasoning

0

Answer

120

Cache Read

256

Cost

$0.000495

Mode

streaming

Cost breakdown

Input $0.000157Output $0.000312Cache read $0.000026

Latency

1.8s

Tok/s

68.3

27689aca-d187-45a4-ac71-b48699721603

Aug 17, 2026, 07:16:31

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

444

Output

369

Reasoning

0

Answer

369

Cache Read

256

Cost

$0.0012

Mode

streaming

Cost breakdown

Input $0.000244Output $0.000959Cache read $0.000026

Latency

6.0s

TTFT

1.8s

Tok/s

61.1

Tok/s (adj)

87.8

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

d86db7c9-839d-4647-871a-029c595c645d

Aug 17, 2026, 07:16:31

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

63

Output

32

Reasoning

0

Answer

32

Cost

$0.000165

Mode

streaming

Cost breakdown

Input $0.000082Output $0.000083

Latency

529ms

TTFT

375ms

Tok/s

60.5

Tok/s (adj)

207.8

summarize-memex

ok

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

Read ~10232 input tokens, wrote 412 words (514 output tokens) in 24135ms.

Result

{
  "wordCount": 412,
  "inputTokens": 10232,
  "outputTokens": 514,
  "latencyMs": 24135
}

9155944d-6016-48b4-80bc-44b21043446d

Aug 17, 2026, 07:16:56

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

10,232

Output

514

Reasoning

0

Answer

514

Cost

$0.0146

Mode

streaming

Cost breakdown

Input $0.0133Output $0.0013

Latency

24.1s

TTFT

2.7s

Tok/s

21.3

Tok/s (adj)

24.0

truncation

ok

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

finishReason=length, out=100 tokens.

Result

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

5c4baf09-93b2-4f58-ad6f-3f1df47579cb

Aug 17, 2026, 07:16:59

deepinfra:deepseek-ai/DeepSeek-V4-Pro

Input

21

Output

100

Reasoning

0

Answer

100

Cost

$0.000287

Mode

streaming

Cost breakdown

Input $0.000027Output $0.000260

Latency

3.3s

TTFT

1.0s

Tok/s

30.6

Tok/s (adj)

44.8

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"
}