GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

alibaba

Qwen 3.8 Max

Modello IA Uscita Aug 2, 2026

Finestra di contesto: 1.000.000 tokens^*
Output massimo: 131.072 tokens^*
Pesi aperti: No^*

Capacità e preferenze

Capacità generale · ECI

Stima delle capacità basata su più benchmark. Punti di indice, non una percentuale; gli intervalli mostrano l’incertezza.

Qwen 3.8 Max 158,0^* Qwen 3.8 Max · Intervallo 95% 155,7–160,8

Prestazioni dei modelli

Punteggio Radar: quattro test, peso uguale. Una sintesi sperimentale di queste prove, non una misura universale di intelligenza.

Qwen 3.8 Max

Configurazione testata Punteggio Radar

62,8^* / 100

4/4 test principali · v1 sperimentale

7 risultati di benchmark per questa configurazione

Ragionamento scientifico

GPQA Diamond · 25%

Domande scientifiche di esperti; correzione rigorosa a scelta multipla. Il caso vale il 25%.

Qwen 3.8 Max 92,7^*% Intervallo 95% appross.: 89,4–96,0% · 2026-08-04

Soluzione di problemi nuovi

Mystery Game Puzzles · 25%

Scelta della mossa migliore in una variante di gioco non divulgata. Una prova circoscritta di ragionamento, non di intelligenza generale.

Qwen 3.8 Max 38,0^*% Intervallo 95% appross.: 28,4–47,6% · 2026-08-05

Matematica avanzata

FrontierMath Tiers 1-3 · 25%

Problemi matematici privati v2 con strumenti Python. Esclusi versioni precedenti e Tier 4.

Qwen 3.8 Max 74,7^*% Intervallo 95% appross.: 69,7–79,8% · 2026-08-04

Risposte fattuali

SimpleQA Verified · 25%

Risposte fattuali corrette con invito a tentare, valutate da un modello. Non misura allucinazioni o astensione.

Qwen 3.8 Max 45,8^*% Intervallo 95% appross.: 42,7–48,9% · 2026-08-27

Software completo

MirrorCode · Risultato separato

Reimplementazione di programmi con test nascosti; ML + Private, due linguaggi. Budget: sette giorni e dieci miliardi di token per tentativo.

Qwen 3.8 Max 52,2^*% Intervallo 95% appross.: 30,9–73,6% · 2026-10-21

Matematica da competizione

OTIS Mock AIME 2024-2025 · Risultato separato

Problemi da competizione: risposte estratte da un modello e confrontate con la soluzione esatta. Escluse le procedure di valutazione precedenti.

Qwen 3.8 Max 99,4^*% Intervallo 95% appross.: 98,7–100,0% · 2026-08-04

Matematica di ricerca

FrontierMath Tier 4 v2 · Risultato separato

I problemi privati più difficili di FrontierMath, versione corretta v2, con strumenti Python. Separati dai Tiers 1-3 del punteggio principale.

Qwen 3.8 Max 46,3^*% Intervallo 95% appross.: 30,9–61,8% · 2026-08-04

Le barre mostrano i risultati delle prove. I segmenti indicano intervalli approssimativi al 95% quando è disponibile l’errore standard. Budget di ragionamento diversi non implicano costi uguali. I risultati mancanti non valgono zero.

Risultati dei benchmark

Esecuzione locale

Inferenza · stima della memoria

Qwen 3.8 Max

Pesi chiusi. Non sono pubblicati un impiego locale supportato o requisiti GPU.

Capacità

Finestra di contesto: 1.000.000 tokens^*
Output massimo: 131.072 tokens^*
Ragionamento: Sì^*
Uso di strumenti: Sì^*
Pesi aperti: No^*

Modalità di input

text^*
image^*
video^*
pdf^*

Modalità di output

text^*

Configurazione di sistema

Specifiche dettagliate

Specifiche 1 · 4 campi

Modalità di accesso: API access^*
Pesi aperti: No^*
Organizzazione: Alibaba^*
Paese dell’organizzazione: China^*

Specifiche 2 · 32 campi

QwenSWEBench

suite: QwenSWEBench
workload: reported score · Claude Code · Internal · avg@3
score: 80,7^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Statistic: avg@3^*
Timeout: 8 hours^*
Task set: Internal^*
Maximum output: 32.768^*
Temperature: 1,0^*
Context length: 256K tokens^*

QwenQoderBench

suite: QwenQoderBench
workload: reported score · Claude Code · Internal · avg@5
score: 58,4^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Statistic: avg@5^*
Timeout: 6 hours^*
Task set: Internal^*
Maximum output: 32.768^*
Temperature: 1,0^*
Context length: 256K tokens^*

QwenReactBench

suite: QwenReactBench
workload: reported score · Claude Code · Internal
score: 1.724,0^*
unit: Elo

Ambito e condizioni

Test conditions

Metric: BT/Elo rating^*
Checkpoint version: Not specified^*
Languages: English and Chinese^*
Judge: Multimodal automatic judge^*
Task set: Internal^*
Harness: Claude Code^*

QwenSVGBench

suite: QwenSVGBench
workload: reported score · Not specified · Internal
score: 1.713,0^*
unit: Elo

Ambito e condizioni

Test conditions

Metric: BT/Elo rating^*
Checkpoint version: Not specified^*
Languages: English and Chinese^*
Judge: Multimodal automatic judge^*
Task set: Internal^*
Harness: Not specified^*

CoWorkBench

suite: CoWorkBench
workload: reported score · Internal
score: 74,8^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Task set: Internal^*

WorkSpaceBench

suite: WorkSpaceBench
workload: reported score
score: 67,7^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

JobBench

suite: JobBench
workload: reported score
score: 53,4^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

SkillsBench

suite: SkillsBench
workload: reported score · OpenCode · Public SkillsBench v1.1 · Average of three runs per task
score: 70,2^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: OpenCode^*
Tasks: 87^*
Statistic: Average of three runs per task^*
Task set: Public SkillsBench v1.1^*

Agents' Last Exam (Pass / Score)

suite: Agents' Last Exam (Pass / Score)
workload: Pass
score: 27,0^*

Ambito e condizioni

Test conditions

Metric: Pass^*
Checkpoint version: Not specified^*

Agents' Last Exam (Pass / Score)

suite: Agents' Last Exam (Pass / Score)
workload: Score
score: 52,4^*

Ambito e condizioni

Test conditions

Metric: Score^*
Checkpoint version: Not specified^*

Terminal Bench 2.1

suite: Terminal Bench 2.1
version: 2.1
workload: reported score · Claude Code · avg@10
score: 86,6^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Statistic: avg@10^*
Timeout: 5 hours^*
Maximum output: 131.072^*

Automation-Bench (Pass@1)

suite: Automation-Bench (Pass@1)
workload: reported score · Public subset
score: 27,3^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tasks: 600^*
Task set: Public subset^*

Toolathlon Verified (Pass@1)

suite: Toolathlon Verified (Pass@1)
workload: reported score
score: 72,5^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

WideSearch

suite: WideSearch
workload: reported score · Qwen-Agent · Average item F1 over four runs
score: 81,9^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Qwen-Agent^*
Statistic: Average item F1 over four runs^*

HLE w/ tools

suite: HLE w/ tools
workload: reported score · Enabled
score: 56,2^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Enabled^*

GPQA Diamond

suite: GPQA Diamond
workload: reported score
score: 92,6^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

HLE

suite: HLE
workload: reported score · Disabled
score: 43,6^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Disabled^*

IFBench

suite: IFBench
workload: reported score
score: 82,8^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

$OneMillion-Bench (expert score)

suite: $OneMillion-Bench (expert score)
workload: reported score
score: 52,5^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Judge: gemini-3.1-pro-preview^*

HealthBench

suite: HealthBench
workload: reported score
score: 60,2^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

SWE-bench Pro

suite: SWE-bench Pro
workload: reported score · Claude Code · Refined task set with corrected problematic tasks
score: 67,7^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Task set: Refined task set with corrected problematic tasks^*
Temperature: 1,0^*
Top p: 0,95^*
Context length: 256K tokens^*

PLawBench

suite: PLawBench
workload: reported score
score: 73,2^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Judge: gemini-3.1-pro-preview^*

PRBench-Legal

suite: PRBench-Legal
workload: reported score
score: 57,6^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

PRBench-Finance

suite: PRBench-Finance
workload: reported score
score: 58,3^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

MRCR v2 256K (8-needle)

suite: MRCR v2 256K (8-needle)
version: 2
workload: reported score
score: 92,9^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Variant: 8-needle^*
Context length: 256K tokens^*

LongBench v2

suite: LongBench v2
version: 2
workload: reported score
score: 66,3^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

DeepSWE 1.1

suite: DeepSWE 1.1
version: 1.1
workload: reported score · Claude Code · Highest result across two harnesses
score: 56,6^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Statistic: Highest result across two harnesses^*
Temperature: 1,0^*
Top p: 0,95^*
Context length: 256K tokens^*

NL2Repo-Bench

suite: NL2Repo-Bench
workload: reported score · Claude Code · Repository acquisition commands disabled
score: 55,9^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Tool access: Repository acquisition commands disabled^*

FrontierSWE

suite: FrontierSWE
workload: reported score · Claude Code · Dominance recomputed from raw results
score: 73,5^*

Ambito e condizioni

Test conditions

Metric: Dominance score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Statistic: Dominance recomputed from raw results^*
Evaluation date: 2026-08-03^*
Variant: MEAN@5 submissions^*

MLS-Bench-Lite

suite: MLS-Bench-Lite
workload: reported score · Claude Code
score: 41,0^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Timeout: 5 hours^*
Maximum output: 131.072^*

PaperBench

suite: PaperBench
workload: reported score · BasicAgent
score: 93,0^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: BasicAgent^*
Variant: Code-Dev^*
Judge: Claude Opus 4.6^*
Runs: 3^*
Timeout: 12 hours per run^*

AndroidBench

suite: AndroidBench
workload: reported score · Public subset · avg@3
score: 75,1^*

Ambito e condizioni

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tasks: 95^*
Statistic: avg@3^*
Task set: Public subset^*

Specifiche 3 · 48 campi

File allegati

Sì^*

Finestra di contesto

1.000.000^* tokens

Famiglia del modello

qwen^*

Modalità di input

text^*
image^*
video^*
pdf^*

Output massimo

131.072^* tokens

Modalità di output

text^*

Servizio API · DigitalOcean · qwen3.8-max

Provider

DigitalOcean^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 262.144^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- high^*
- max^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,2^*

Servizio API · Requesty · qwen3.8-max

Provider

Requesty^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.048.576^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- high^*
- max^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · CrossModel · qwen/qwen3.8-max

Provider

CrossModel^*

Model

qwen/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 1,88^*
output: 5,63^*
cache_read: 0,23^*
cache_write: 2,35^*

Servizio API · OrcaRouter · qwen/qwen3.8-max

Provider

OrcaRouter^*

Model

qwen/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · OpenCode Go · qwen3.8-max

Provider

OpenCode Go^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · 302.AI · qwen3.8-max

Provider

302.AI^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2,16^*
output: 6,36^*
cache_read: 0,168^*
cache_write: 2,58^*

Servizio API · Alibaba · qwen3.8-max

Provider

Alibaba^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · Eden AI · qwen/qwen3.8-max

Provider

Eden AI^*

Model

qwen/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · AI/ML API · alibaba/qwen3.8-max

Provider

AI/ML API^*

Model

alibaba/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · Novita AI · qwen/qwen3.8-max

Provider

Novita AI^*

Model

qwen/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · Opper · qwen3.8-max

Provider

Opper^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 983.616^*
output: 131.072^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Sì^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · Vancine · qwen3.8-max

Provider

Vancine^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 1,6^*
output: 4,8^*
cache_read: 0,2^*

Servizio API · GMI Cloud · Qwen/Qwen3.8-Max

Provider

GMI Cloud^*

Model

Qwen/Qwen3.8-Max^*

Snapshot

2026-10-26^*

Token limits

context: 262.144^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · Fireworks AI · accounts/fireworks/routers/qwen-max-latest

Provider

Fireworks AI^*

Model

accounts/fireworks/routers/qwen-max-latest^*

Snapshot

2026-10-26^*

Token limits

context: 262.144^*
output: 131.072^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · Deep Infra · Qwen/Qwen3.8-Max

Provider

Deep Infra^*

Model

Qwen/Qwen3.8-Max^*

Snapshot

2026-10-26^*

Token limits

context: 256.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

No^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 1,65^*
output: 4,951^*
cache_read: 0,206^*

Servizio API · Merge Gateway · qwen/qwen3.8-max

Provider

Merge Gateway^*

Model

qwen/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · SCX.ai · Qwen3.8-Max

Provider

SCX.ai^*

Model

Qwen3.8-Max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
input: 983.616^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 1,815^*
output: 5,4461^*
cache_read: 0,17^*
cache_write: 2,5^*

Servizio API · Alibaba (China) · qwen3.8-max

Provider

Alibaba (China)^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 1,77744^*
output: 5,33231^*
cache_read: 0,22218^*
cache_write: 2,22179^*

Servizio API · LLM Gateway · alibaba/qwen3.8-max

Provider

LLM Gateway^*

Model

alibaba/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 983.616^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Sì^*

Structured output

No^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · AIHubMix · qwen3.8-max-free

Provider

AIHubMix^*

Model

qwen3.8-max-free^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Servizio API · above.dev · qwen3.8-max

Provider

above.dev^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 32.768^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2,2^*
output: 6,6^*
cache_read: 0,275^*

Servizio API · Ofox · qwen/qwen3.8-max

Provider

Ofox^*

Model

qwen/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 1,71^*
output: 5,14^*
cache_read: 0,17^*
cache_write: 2,14^*

Servizio API · Alibaba Token Plan (China) · qwen3.8-max

Provider

Alibaba Token Plan (China)^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Servizio API · ClinePass · cline-pass/qwen3.8-max

Provider

ClinePass^*

Model

cline-pass/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · NanoGPT · qwen/qwen3.8-max:thinking

Provider

NanoGPT^*

Model

qwen/qwen3.8-max:thinking^*

Snapshot

2026-10-26^*

Token limits

context: 991.000^*
input: 991.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- high^*
- max^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · CommandCode · Qwen/Qwen3.8-Max

Provider

CommandCode^*

Model

Qwen/Qwen3.8-Max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · LLM Gateway · scx-ai-gp/qwen3.8-max

Provider

LLM Gateway^*

Model

scx-ai-gp/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Sì^*

Structured output

No^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 1,54^*
output: 4,631^*
cache_read: 0,198^*
cache_write: 2,5^*

Servizio API · Cloudflare AI Gateway · alibaba/qwen3.8-max

Provider

Cloudflare AI Gateway^*

Model

alibaba/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · Alibaba Token Plan · qwen3.8-max

Provider

Alibaba Token Plan^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Servizio API · Fireworks AI · accounts/fireworks/models/qwen3p8-max

Provider

Fireworks AI^*

Model

accounts/fireworks/models/qwen3p8-max^*

Snapshot

2026-10-26^*

Token limits

context: 262.144^*
output: 131.072^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · LLM Gateway · novita/qwen3.8-max

Provider

LLM Gateway^*

Model

novita/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · Kenari · qwen3-8-max

Provider

Kenari^*

Model

qwen3-8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2,4^*
output: 6,85714286^*
cache_read: 0,29714286^*
cache_write: 2,97142857^*

Servizio API · EmpirioLabs AI · qwen3-8-max

Provider

EmpirioLabs AI^*

Model

qwen3-8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- high^*
- max^*
type
budget_tokens^*
min
1^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 2^*

Servizio API · NanoGPT · qwen/qwen3.8-max

Provider

NanoGPT^*

Model

qwen/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 991.000^*
input: 991.000^*
output: 65.536^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

No^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · AIHubMix · qwen3.8-max

Provider

AIHubMix^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 991.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 1,69^*
output: 5,07^*
cache_read: 0,169^*
cache_write: 2,1125^*

Servizio API · OpenCode · qwen3.8-max

Provider

OpenCode^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 262.144^*
output: 131.072^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
1.024^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · Abacus · qwen3.8-max

Provider

Abacus^*

Model

qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Sì^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*

Servizio API · Ofox · bailian/qwen3.8-max

Provider

Ofox^*

Model

bailian/qwen3.8-max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*
min
0^*
max
262.144^*

Tool calling

Sì^*

Structured output

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Prices (USD per million tokens)

input: 2^*
output: 6^*
cache_read: 0,25^*
cache_write: 2,5^*

Servizio API · SCNet Token Plan · Qwen3.8-Max

Provider

SCNet Token Plan^*

Model

Qwen3.8-Max^*

Snapshot

2026-10-26^*

Token limits

context: 1.000.000^*
output: 131.072^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Sì^*

Reasoning controls

type
toggle^*

Tool calling

Sì^*

Temperature control

Sì^*

File attachments

Sì^*

Interleaved reasoning

field: reasoning_content^*

Ragionamento

Sì^*

Controllo della temperatura

Sì^*

Uso di strumenti

Sì^*

* Dati provvisori