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
1.048.576 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

44 provider

Verificato: 18 novembre 2026

Provider live su OpenRouter

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

OpenRouter

Relace

fp4
Contesto
1.0M
Output massimo
131K
Input
$0.0399
Output
$0.0784
Lettura cache
$0.03
Scrittura cache
Non indicato

Wafer

nvfp4
Contesto
1.0M
Output massimo
944K
Input
$0.042
Output
$0.184
Lettura cache
$0.041
Scrittura cache
Non indicato

OpenInference

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.06
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Darkbloom

fp4
Contesto
262K
Output massimo
66K
Input
$0.065
Output
$0.18
Lettura cache
$0.012
Scrittura cache
Non indicato

Wafer

nvfp4
Contesto
1.0M
Output massimo
944K
Input
$0.065
Output
$0.24
Lettura cache
$0.064
Scrittura cache
Non indicato

Particle AI

nvfp4
Contesto
1.0M
Output massimo
131K
Input
$0.065
Output
$0.25
Lettura cache
$0.02
Scrittura cache
Non indicato

Tenstorrent

fp8
Contesto
262K
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
$0.075
Output
$0.25
Lettura cache
$0.015
Scrittura cache
Non indicato

Near AI

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.08
Output
$0.5
Lettura cache
$0.012
Scrittura cache
Non indicato

Novita

fp8
Contesto
1.0M
Output massimo
131K
Input
$0.084
Output
$0.28
Lettura cache
$0.0168
Scrittura cache
Non indicato

StreamLake

fp8
Contesto
1.0M
Output massimo
128K
Input
$0.0885
Output
$0.295
Lettura cache
$0.0177
Scrittura cache
Non indicato

SiliconFlow

fp8
Contesto
1.0M
Output massimo
262K
Input
$0.1
Output
$0.4
Lettura cache
$0.03
Scrittura cache
Non indicato

DekaLLM

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.1
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

InferenceNet

fp4
Contesto
1.0M
Output massimo
262K
Input
$0.108
Output
$0.35
Lettura cache
$0.035
Scrittura cache
Non indicato

InferenceNet

fp4
Contesto
1.0M
Output massimo
262K
Input
$0.108
Output
$0.35
Lettura cache
$0.035
Scrittura cache
Non indicato

DigitalOcean

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$0.1125
Output
$0.375
Lettura cache
$0.03
Scrittura cache
Non indicato

Morph

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.119
Output
$0.342
Lettura cache
$0.059
Scrittura cache
Non indicato

Reka

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.12
Output
$0.3
Lettura cache
$0.03
Scrittura cache
Non indicato

CoreWeave

nvfp4
Contesto
1.0M
Output massimo
944K
Input
$0.12
Output
$0.38
Lettura cache
$0.02
Scrittura cache
Non indicato

River

Non indicato
Contesto
1.0M
Output massimo
131K
Input
$0.12
Output
$0.4
Lettura cache
$0.024
Scrittura cache
Non indicato

NextBit

fp4
Contesto
1.0M
Output massimo
128K
Input
$0.12
Output
$0.45
Lettura cache
$0.03
Scrittura cache
Non indicato

Particle AI

nvfp4
Contesto
1.0M
Output massimo
131K
Input
$0.13
Output
$0.5
Lettura cache
$0.04
Scrittura cache
Non indicato

Makora

fp4
Contesto
1.0M
Output massimo
131K
Input
$0.14
Output
$0.24
Lettura cache
$0.03
Scrittura cache
Non indicato

Baidu

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

Mistral

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

KT

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

Cohere

nvfp4
Contesto
1.0M
Output massimo
131K
Input
$0.15
Output
$0.5
Lettura cache
$0.03
Scrittura cache
Non indicato

Nebius

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

Modal

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

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

Together

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

Parasail

fp4
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

DeepInfra

fp4
Contesto
1.0M
Output massimo
944K
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

Inceptron

fp8
Contesto
1.0M
Output massimo
944K
Input
$0.175
Output
$0.49
Lettura cache
$0.04
Scrittura cache
Non indicato

Sail Research

fp4
Contesto
1.0M
Output massimo
131K
Input
$0.175
Output
$0.625
Lettura cache
$0.0225
Scrittura cache
Non indicato

Sail Research

fp4
Contesto
1.0M
Output massimo
131K
Input
$0.175
Output
$0.625
Lettura cache
$0.0225
Scrittura cache
Non indicato

Parasail

fp4
Contesto
1.0M
Output massimo
944K
Input
$0.1875
Output
$0.625
Lettura cache
$0.0375
Scrittura cache
Non indicato

Fireworks

Non indicato
Contesto
1.0M
Output massimo
944K
Input
$0.225
Output
$0.75
Lettura cache
$0.045
Scrittura cache
Non indicato
z-ai

4 modelli

Tutti i modelli
z-ai logoz-ai

Z.ai: GLM 5.3 FlashX Legal

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...

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 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: $1.68Output: $5.28per 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 (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: $0.024Output: $0.069per milione di token
Vedi i dettagli del modello →