~glm Flash Latest

~glm-flash-latest by Z.ai Released août 27, 2026
Raisonnement · Appel de fonctions · Sortie structurée · Mise en cache des prompts · Entrée image · Entrée vidéo · Hébergement UE
Input from
$0.025 / 1M
Output from
$0.07 / 1M
Cached input from
$0.0132 / 1M
Context window
1.05M
Endpoints
16
from 15 providers
Regions
Monde, Asie, Europe, États-Unis

About ~glm Flash Latest

GLM-5.3-Flash est un modèle multimodal natif développé par Z.ai. Il est adapté au codage efficace et aux tâches d'agent à long terme.

~glm Flash Latest est un modèle conversationnel développé par Z.ai, disponible sur Eden AI via 16 endpoints chez 15 fournisseurs, à partir de 0,025 $ par million de tokens en entrée et 0,07 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

16 endpoints from 15 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Greenference (Europe)greenference/glm-5.3-flash
Europe
1.05M
$0.025
$0.07
$0.025
Raisonnement · Outils · Cache · Vision
FlexAIflexai/GLM-5.3-Flash
Monde
1.05M
$0.088
$0.25
$0.0132
Raisonnement · Outils · JSON · Cache · Vision
GreenPT (Europe)greenpt/glm-5.3-flash
Europe
1M
$0.1209
$0.4835
$0.0242
Raisonnement · Outils · Cache · Vision
Arkane Cloudarkanecloud/zai-org/GLM-5.3-Flash
Monde
1M
$0.15
$0.5
$0.03
Outils · Cache · Vision
Mistral AImistral/zai-glm-5-3-flash
Monde
1.05M
$0.15
$0.5
$0.03
Raisonnement · Outils
Databricksdatabricks/databricks-glm-5-3-flash
Monde
1.05M
$0.15
$0.5
$0.015
Raisonnement · Outils · Cache · Vision
Fireworks AI (États-Unis)fireworks_ai/accounts/fireworks/models/glm-5p3-flash
États-Unis
1.05M
$0.15
$0.5
$0.03
Outils · JSON · Cache · Vision
Cloudflare (CF/ZAI-ORG/GLM-5.3-FLASH)cloudflare/@cf/zai-org/glm-5.3-flash
CF/ZAI-ORG/GLM-5.3-FLASH
1.05M
$0.15
$0.5
$0.03
Raisonnement · Outils · JSON · Cache · Vision
DeepInfra (États-Unis)deepinfra/zai-org/GLM-5.3-Flash
États-Unis
1.05M
$0.15
$0.5
$0.03
Raisonnement · Outils · JSON · Cache · Vision
Nebiusnebius/zai-org/GLM-5.3-Flash
Monde
1.05M
$0.15
$0.5
$0.15
Raisonnement · Outils · Cache · Vision
Together AItogether_ai/zai-org/GLM-5.3-Flash
Monde
1.05M
$0.15
$0.5
$0.03
Raisonnement · Outils · JSON · Cache · Vision
Z.ai (Asie)zai/glm-5.3-flash
Asie
1.05M
$0.15
$0.5
$0.03
Officiel · Raisonnement · Outils · JSON · Cache · Vision
Mistral AI (Europe)mistral/zai-glm-5-3-flash@eu
Europe
1.05M
$0.165
$0.55
$0.033
Raisonnement · Outils
sference (Europe)sference/zai-org/GLM-5.3-Flash
Europe
1.05M
$0.2
$0.6
$0.07
Raisonnement · Outils · JSON · Cache · Vision
TensorX (Europe)tensorx/z-ai/glm-5.3-flash
Europe
1.05M
$0.2
$0.5
$0.05
Raisonnement · Outils · Cache · Vision
Tsystems (Europe)tsystems/GLM-5.3-Flash
Europe
1M
$0.2198
$0.6593
$0.033
Raisonnement · Outils · JSON · Cache · Vision

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.41 s
sference (Europe)
Lowest latency
1.64 s
Greenference (Europe)
Highest throughput
162.91 tok/s
Databricks
Best availability
100%
Arkane Cloud
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Greenference (Europe)
0.84 s
1.64 s
17.8 s
65.44 tok/s
99.96%
70.19%
1.96%
95.96%
FlexAI
2.01 s
3.98 s
78.31 s
112.51 tok/s
99.28%
91.35%
0.76%
0%
GreenPT (Europe)
0.8 s
2.55 s
19.12 s
59.14 tok/s
99.84%
92.25%
0.34%
0.95%
Arkane Cloud
1.08 s
2.84 s
195.14 s
71.25 tok/s
100%
92.87%
0%
0%
Mistral AI
1.4 s
2.77 s
21.86 s
64.28 tok/s
99.9%
82.67%
0.88%
1.97%
Databricks
2.04 s
7.69 s
19.57 s
162.91 tok/s
99.96%
89.39%
0.06%
78.57%
Fireworks AI (États-Unis)
1.67 s
3.52 s
27.63 s
63.23 tok/s
99.95%
91.13%
0.16%
0%
DeepInfra (États-Unis)
1.81 s
3.03 s
15.2 s
43.36 tok/s
99.96%
91.55%
1.73%
0.03%
Nebius
1.38 s
32.42 s
155.37 s
139.04 tok/s
98.74%
53.19%
0%
1.6%
Together AI
0.85 s
8.25 s
104.29 s
136.86 tok/s
100%
52.31%
0%
0%
Z.ai (Asie)
3.21 s
6.23 s
70.43 s
32.93 tok/s
99.32%
90.84%
1.48%
21.55%
Mistral AI (Europe)
1.39 s
2.78 s
22.24 s
62.29 tok/s
99.89%
82.4%
0.92%
1.34%
sference (Europe)
0.41 s
2.4 s
32.97 s
145.63 tok/s
99.92%
93.55%
1.02%
0%
TensorX (Europe)
1.79 s
4.45 s
40.08 s
69.02 tok/s
99.8%
72.04%
0.21%
0.16%
Tsystems (Europe)
0.93 s
2.05 s
32.75 s
133.22 tok/s
98.81%
86.69%
11.53%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call ~glm Flash Latest with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "~glm-flash-latest",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about ~glm Flash Latest

On Eden AI, prices for this model start at $0.025 per million input tokens and $0.07 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 1.05M tokens, depending on the endpoint.

16 endpoints from 15 providers, available in: Monde, Asie, Europe, États-Unis. All of them are called with the same Eden AI API key.

Puis-je utiliser ~glm Flash Latest dans l'UE ? Oui. Au moins un endpoint est hébergé en Europe ; épinglez-le avec son ID d'endpoint depuis le tableau des fournisseurs pour garder vos requêtes dans l'UE. ‖ Quelle est la vitesse de ~glm Flash Latest ? Sur les 30 derniers jours, le premier token le plus rapide est arrivé en 0,41 s (sference (Europe)) et le débit le plus élevé a atteint 162,91 tokens par seconde (Databricks).