z-ai logo
z-ai

Z.ai: GLM 5.3

Descrizione della fonte (inglese)

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

Panoramica

Specifiche del modello

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

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$1.4
per milione di token
Output
$4.4
per milione di token
Lettura cache
$0.26
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","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
text
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

40 provider

Verificato: 28 settembre 2026

Provider live su OpenRouter

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

OpenRouter

Reka

Non indicato
Contesto
262K
Output massimo
236K
Input
$0.3556
Output
$2.574
Lettura cache
$0.066
Scrittura cache
Non indicato

Inceptron

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.4204
Output
$2.7392
Lettura cache
$0.0967
Scrittura cache
Non indicato

Morph

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.4522
Output
$2.805
Lettura cache
$0.1466
Scrittura cache
Non indicato

Io Net

fp8
Contesto
262K
Output massimo
66K
Input
$0.5005
Output
$1.898
Lettura cache
$0.091
Scrittura cache
Non indicato

Relace

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$0.55
Output
$1.7
Lettura cache
$0.1
Scrittura cache
Non indicato

DeepInfra

fp4
Contesto
1.0M
Output massimo
131K
Input
$0.5625
Output
$2.5
Lettura cache
$0.125
Scrittura cache
Non indicato

InferenceNet

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$0.684
Output
$2.28
Lettura cache
$0.114
Scrittura cache
Non indicato

Sail Research

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.77
Output
$4
Lettura cache
$0.19
Scrittura cache
Non indicato

Sail Research

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.77
Output
$4
Lettura cache
$0.19
Scrittura cache
Non indicato

Novita

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.7826
Output
$2.4596
Lettura cache
$0.1453
Scrittura cache
Non indicato

DigitalOcean

Non indicato
Contesto
1.0M
Output massimo
128K
Input
$0.91
Output
$2.86
Lettura cache
$0.169
Scrittura cache
Non indicato

Phala

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$0.98
Output
$3.08
Lettura cache
$0.182
Scrittura cache
Non indicato

GMICloud

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.98
Output
$3.08
Lettura cache
$0.182
Scrittura cache
Non indicato

Makora

fp4
Contesto
980K
Output massimo
128K
Input
$1.05
Output
$4.2
Lettura cache
$0.19
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
1.0M
Output massimo
262K
Input
$1.12
Output
$3.52
Lettura cache
$0.208
Scrittura cache
Non indicato

Alibaba

Non indicato
Contesto
1M
Output massimo
131K
Input
$1.19
Output
$3.74
Lettura cache
$0.238
Scrittura cache
Non indicato

Decart

fp4
Contesto
1.0M
Output massimo
944K
Input
$1.19
Output
$3.74
Lettura cache
$0.1955
Scrittura cache
Non indicato

Friendli

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$1.26
Output
$3.96
Lettura cache
$0.234
Scrittura cache
Non indicato

AkashML

fp8
Contesto
1.0M
Output massimo
131K
Input
$1.3
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Mistral

nvfp4
Contesto
1.0M
Output massimo
131K
Input
$1.4
Output
$4.4
Lettura cache
$0.14
Scrittura cache
Non indicato

Wafer

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Baidu

fp8
Contesto
1.0M
Output massimo
131K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

BaseTen

fp4
Contesto
1.0M
Output massimo
262K
Input
$1.4
Output
$4.4
Lettura cache
$0.14
Scrittura cache
Non indicato

Mistral

nvfp4
Contesto
1.0M
Output massimo
131K
Input
$1.4
Output
$4.4
Lettura cache
$0.14
Scrittura cache
Non indicato

Crusoe

fp4
Contesto
1.0M
Output massimo
944K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

PrimeIntellect

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Venice

Non indicato
Contesto
1M
Output massimo
131K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Together

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Parasail

fp8
Contesto
1.0M
Output massimo
944K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Modal

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

BaseTen

fp4
Contesto
1.0M
Output massimo
262K
Input
$1.4
Output
$4.4
Lettura cache
$0.14
Scrittura cache
Non indicato

Fireworks

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Cloudflare

Non indicato
Contesto
1.3M
Output massimo
1.2M
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

AtlasCloud

fp8
Contesto
1.0M
Output massimo
131K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Z.AI

fp8
Contesto
1.0M
Output massimo
131K
Input
$1.4
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

Mistral

nvfp4
Contesto
1.0M
Output massimo
131K
Input
$1.54
Output
$4.84
Lettura cache
$0.154
Scrittura cache
Non indicato

Wafer

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$1.82
Output
$4.4
Lettura cache
$0.26
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
262K
Input
$2.1
Output
$6.6
Lettura cache
$0.21
Scrittura cache
Non indicato

BaseTen

fp8
Contesto
1.0M
Output massimo
262K
Input
$2.1
Output
$6.6
Lettura cache
$0.21
Scrittura cache
Non indicato

Alibaba

Non indicato
Contesto
1M
Output massimo
131K
Input
$2.8
Output
$8.8
Lettura cache
$0.56
Scrittura cache
Non indicato
z-ai

4 modelli

Tutti i modelli
z-ai logoz-ai

Z.ai: GLM 5.3 Prime

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

Contesto
1M
Input
text
Output
text
Input: $2.8Output: $8.8per milione di token
Vedi i dettagli del modello →
z-ai logoz-ai

Z.ai: GLM 5.3 FlashX

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

Contesto
1.0M
Input
text · image · video
Output
text
Input: $0.37Output: $1.25per milione di token
Vedi i dettagli del modello →
z-ai logoz-ai

Z.ai: GLM 5.3 Flash

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...

Contesto
1.3M
Input
text · image · video
Output
text
Input: $0.15Output: $0.5per milione di token
Vedi i dettagli del modello →
z-ai logoz-ai

Z.ai: GLM 5.3 Flash (batch)

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...

Contesto
1.0M
Input
text · image · video
Output
text
Input: $0.06Output: $0.2per milione di token
Vedi i dettagli del modello →