z-ai logo
z-ai

Z.ai: GLM 5.3 Flash

Descrizione della fonte (inglese)

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

Panoramica

Specifiche del modello

Contesto
1.310.720 tokens
Output massimo
943.717 tokens
Architettura
text+image+video->text
Tokenizer
Other
Limite di conoscenza
Non indicato
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.15
per milione di token
Output
$0.5
per milione di token
Lettura cache
$0.03
per milione di token
API

Configurazione del modello

Parametri predefiniti

temperature
1
top_p
0.95

Ragionamento

Ragionamento obbligatorio
Sì
Parametri predefiniti
max
Capacità e modalità
max, high, low
API

Avvio rapido

Imposta OPENROUTER_API_KEY localmente. Python richiede requests; JavaScript viene eseguito in Node.js. Conserva la chiave sul server.

Documentazione API

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"z-ai/glm-5.3-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
textimagevideo
Output
text
Ragionamento

Sì · max · high · low

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Provider disponibili

33 provider

Verificato: 28 settembre 2026

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

InferenceNet

fp4
Contesto
1.0M
Output massimo
128K
Input
$0.045
Output
$0.14
Lettura cache
$0.01
Scrittura cache
Non indicato

Sail Research

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.045
Output
$0.6
Lettura cache
$0.0285
Scrittura cache
Non indicato

Sail Research

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.045
Output
$0.6
Lettura cache
$0.0285
Scrittura cache
Non indicato

OpenInference

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.05
Output
$0.5
Lettura cache
$0.02
Scrittura cache
Non indicato

Relace

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$0.07
Output
$0.5
Lettura cache
$0.02
Scrittura cache
Non indicato

DeepInfra

fp4
Contesto
1.0M
Output massimo
131K
Input
$0.075
Output
$0.25
Lettura cache
$0.015
Scrittura cache
Non indicato

GMICloud

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.09
Output
$0.3
Lettura cache
$0.018
Scrittura cache
Non indicato

Inceptron

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.11
Output
$0.45
Lettura cache
$0.07
Scrittura cache
Non indicato

Novita

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.1125
Output
$0.375
Lettura cache
$0.0225
Scrittura cache
Non indicato

Decart

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.1275
Output
$0.425
Lettura cache
$0.0255
Scrittura cache
Non indicato

Phala

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.1275
Output
$0.425
Lettura cache
$0.0255
Scrittura cache
Non indicato

Io Net

fp8
Contesto
262K
Output massimo
66K
Input
$0.135
Output
$0.45
Lettura cache
$0.027
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1.0M
Output massimo
128K
Input
$0.141
Output
$0.47
Lettura cache
$0.0282
Scrittura cache
Non indicato

Modal

nvfp4
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Near AI

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.15
Output
$0.5
Lettura cache
$0.035
Scrittura cache
Non indicato

Crusoe

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

CoreWeave

nvfp4
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.05
Scrittura cache
Non indicato

AtlasCloud

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Fireworks

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Friendli

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
1.0M
Output massimo
262K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

DigitalOcean

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Together

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Reka

Non indicato
Contesto
262K
Output massimo
236K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Parasail

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Venice

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Z.AI

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Morph

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.1623
Output
$0.5681
Lettura cache
$0.0325
Scrittura cache
Non indicato

NextBit

fp8
Contesto
1.0M
Output massimo
128K
Input
$0.165
Output
$0.55
Lettura cache
$0.033
Scrittura cache
Non indicato

Cloudflare

Non indicato
Contesto
1.3M
Output massimo
1.2M
Input
$0.3
Output
$1
Lettura cache
$0.03
Scrittura cache
Non indicato

Wafer

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.559
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato
z-ai

4 modelli

Tutti i modelli