z-ai logo
z-ai

Z.ai: GLM 5.3 Flash

Description de la source (anglais)

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...

Présentation

Caractéristiques du modèle

Contexte
1 310 720 tokens
Sortie maximale
943 717 tokens
Architecture
text+image+video->text
Tokenizer
Other
Limite des connaissances
Non indiqué
Modéré
Non
OPENROUTER

Tarification complète

Tarifs synchronisés depuis OpenRouter, par million de tokens.

Entrée
$0.15
par million de tokens
Sortie
$0.5
par million de tokens
Lecture du cache
$0.03
par million de tokens
API

Configuration du modèle

Paramètres par défaut

temperature
1
top_p
0.95

Raisonnement

Raisonnement obligatoire
Oui
Paramètres par défaut
max
Capacités et modalités
max, high, low
API

Démarrage rapide

Définissez OPENROUTER_API_KEY localement. Python nécessite requests ; JavaScript s’exécute dans Node.js. Gardez la clé côté serveur.

Documentation de l’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!"}]}'
Capacités et modalités

Entrée → Sortie

Entrée
textimagevideo
Sortie
text
Raisonnement

Oui · max · high · low

API

Paramètres API pris en charge

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Fournisseurs disponibles

33 fournisseurs

Vérifié: 28 septembre 2026

Fournisseurs en direct sur OpenRouter

Disponibilité, latence, débit et routage évoluent en continu. Consultez la source pour les données en temps réel.

OpenRouter

InferenceNet

fp4
Contexte
1.0M
Sortie maximale
128K
Entrée
$0.045
Sortie
$0.14
Lecture du cache
$0.01
Écriture du cache
Non indiqué

Sail Research

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.045
Sortie
$0.6
Lecture du cache
$0.0285
Écriture du cache
Non indiqué

Sail Research

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.045
Sortie
$0.6
Lecture du cache
$0.0285
Écriture du cache
Non indiqué

OpenInference

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.05
Sortie
$0.5
Lecture du cache
$0.02
Écriture du cache
Non indiqué

Relace

Non indiqué
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.07
Sortie
$0.5
Lecture du cache
$0.02
Écriture du cache
Non indiqué

DeepInfra

fp4
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.075
Sortie
$0.25
Lecture du cache
$0.015
Écriture du cache
Non indiqué

GMICloud

fp8
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.09
Sortie
$0.3
Lecture du cache
$0.018
Écriture du cache
Non indiqué

Inceptron

fp8
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.11
Sortie
$0.45
Lecture du cache
$0.07
Écriture du cache
Non indiqué

Novita

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.1125
Sortie
$0.375
Lecture du cache
$0.0225
Écriture du cache
Non indiqué

Decart

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.1275
Sortie
$0.425
Lecture du cache
$0.0255
Écriture du cache
Non indiqué

Phala

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.1275
Sortie
$0.425
Lecture du cache
$0.0255
Écriture du cache
Non indiqué

Io Net

fp8
Contexte
262K
Sortie maximale
66K
Entrée
$0.135
Sortie
$0.45
Lecture du cache
$0.027
Écriture du cache
Non indiqué

StreamLake

fp8
Contexte
1.0M
Sortie maximale
128K
Entrée
$0.141
Sortie
$0.47
Lecture du cache
$0.0282
Écriture du cache
Non indiqué

Modal

nvfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

BaseTen

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Near AI

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.035
Écriture du cache
Non indiqué

Crusoe

fp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

CoreWeave

nvfp4
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.05
Écriture du cache
Non indiqué

AtlasCloud

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Fireworks

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Friendli

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

SiliconFlow

fp8
Contexte
1.0M
Sortie maximale
262K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

DigitalOcean

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Together

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Reka

Non indiqué
Contexte
262K
Sortie maximale
236K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Parasail

fp8
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

BaseTen

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Venice

Non indiqué
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Z.AI

fp8
Contexte
1.0M
Sortie maximale
131K
Entrée
$0.15
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Morph

fp8
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.1623
Sortie
$0.5681
Lecture du cache
$0.0325
Écriture du cache
Non indiqué

NextBit

fp8
Contexte
1.0M
Sortie maximale
128K
Entrée
$0.165
Sortie
$0.55
Lecture du cache
$0.033
Écriture du cache
Non indiqué

Cloudflare

Non indiqué
Contexte
1.3M
Sortie maximale
1.2M
Entrée
$0.3
Sortie
$1
Lecture du cache
$0.03
Écriture du cache
Non indiqué

Wafer

Non indiqué
Contexte
1.0M
Sortie maximale
944K
Entrée
$0.559
Sortie
$0.5
Lecture du cache
$0.03
Écriture du cache
Non indiqué
z-ai

4 modèles

Tous les modèles
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...

Contexte
1M
Entrée
text
Sortie
text
Entrée: $2.8Sortie: $8.8par million de tokens
Voir la fiche du modèle →
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...

Contexte
1.0M
Entrée
text · image · video
Sortie
text
Entrée: $0.37Sortie: $1.25par million de tokens
Voir la fiche du modèle →
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...

Contexte
1.0M
Entrée
text · image · video
Sortie
text
Entrée: $0.06Sortie: $0.2par million de tokens
Voir la fiche du modèle →
z-ai logoz-ai

Z.ai: GLM 5.3

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...

Contexte
1.3M
Entrée
text
Sortie
text
Entrée: $1.4Sortie: $4.4par million de tokens
Voir la fiche du modèle →