AI Gateway Monitor

01/05/2026 06:24:41 • Groq • Cerebras • Gemini • Arliai

✕ Critique

🔢 Tokens Utilisés

1 386 316

Aujourd'hui

↘ -58,1% vs hier

Ce mois : 1 386 316

Total : 411 899 416

📡 Requêtes

191

Aujourd'hui

↘ -79,0% vs hier

Ce mois : 191

Total : 108 446

⚠️ Erreurs

23,6% aujourd'hui

↘ -59,8% vs hier

Ce mois : 45

Total : 7 217

⚡ Latence Moyenne

12,3s

Aujourd'hui

↗ +27,2% vs hier

Ce mois : 12,3s

Moy. totale : 4,8s

💰 Économies

1,13 $

Aujourd'hui

Ce mois : 1,13 $

Total : 333,54 $

État des Providers

Cerebras

1 compte(s) • 2 modèle(s)

Priorité 10

Tokens Aujourd'hui 1 856 822 / 2 000 000

Utilisés: 143 178 tokens

Requêtes Aujourd'hui 28 733 / 28 800

Utilisées: 67 requêtes

7 derniers jours

3 482 220

tokens utilisés

Latence moyenne

568ms

performances

Groq

1 compte(s) • 11 modèle(s)

Priorité 10

Tokens Aujourd'hui 2 530 107 / 2 600 000

Utilisés: 69 893 tokens

Requêtes Aujourd'hui 29 875 / 29 900

Utilisées: 25 requêtes

7 derniers jours

3 038 127

tokens utilisés

Latence moyenne

591ms

performances

Google Gemini

1 compte(s) • 7 modèle(s)

Priorité 5

Tokens Aujourd'hui ∞ Illimité

Utilisés: 1 111 921 tokens

Requêtes Aujourd'hui 30 679 / 30 720

Utilisées: 41 requêtes

7 derniers jours

14 816 315

tokens utilisés

Latence moyenne

24.5s

performances

Mistral AI

1 compte(s) • 11 modèle(s)

Priorité 4

Tokens Aujourd'hui 7 919 938 676 / 7 920 000 000

Utilisés: 61 324 tokens

Requêtes Aujourd'hui 0 / 0

Utilisées: 13 requêtes

7 derniers jours

935 361

tokens utilisés

Latence moyenne

19.5s

performances

OpenRouter

1 compte(s) • 3 modèle(s)

Priorité 1

Tokens Aujourd'hui ∞ Illimité

Utilisés: 0 tokens

Requêtes Aujourd'hui 0 / 0

Utilisées: 0 requêtes

7 derniers jours

tokens utilisés

Latence moyenne

performances

Activité Récente

30 dernières requêtes 133 erreur(s) 24h

Heure	Provider	Modèle	Tokens	Durée	Statut
06:21:34	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	12 026 → 340 Tot: 13 222	34.5s	✓ OK
06:20:58	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	9 933 → 277 Tot: 10 928	28.5s	✓ OK
06:20:27	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 519 → 326 Tot: 1 845	688ms	✓ OK
06:15:15	Google Gemini	`gemini-3-flash-preview` Gemini 3 Flash	-	-	⚠ Limite ⓘ Rate Limit: Gemini API Error (HTTP 429): You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. * Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 20, model: gemini-3-flash Please retry in 44.371885544s.
06:10:50	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	10 440 → 284 Tot: 11 442	29.2s	✓ OK
06:10:19	Groq	`llama-3.1-8b-instant`	4 099 → 338 Tot: 4 437	848ms	✓ OK
06:10:15	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 413 → 278 Tot: 1 691	642ms	✓ OK
06:01:05	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 827 → 273 Tot: 2 100	622ms	✓ OK
06:01:02	Mistral AI	`mistral-small-2503` Mistral Small (Mar 2025)	10 097 → 380 Tot: 10 477	3.3s	✓ OK
06:00:56	Google Gemini	`gemma-4-26b-a4b-it` Gemma 4 26B	10 708 → 267 Tot: 12 002	28.2s	✓ OK
06:00:26	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	-	-	✕ Erreur ⓘ Erreur: Gemini API Error (HTTP 500): Internal error encountered.
06:00:12	Google Gemini	`gemini-3-flash-preview` Gemini 3 Flash	-	-	⚠ Limite ⓘ Rate Limit: Gemini API Error (HTTP 429): You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. * Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 20, model: gemini-3-flash Please retry in 47.177998552s.
05:50:59	Groq	`llama-3.1-8b-instant`	4 741 → 359 Tot: 5 100	948ms	✓ OK
05:50:56	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 896 → 244 Tot: 2 140	626ms	✓ OK
05:50:53	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	10 455 → 294 Tot: 11 739	37.4s	✓ OK
05:50:02	Google Gemini	`gemini-3-flash-preview` Gemini 3 Flash	-	-	⚠ Limite ⓘ Rate Limit: Gemini API Error (HTTP 429): You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. * Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 20, model: gemini-3-flash Please retry in 57.344276403s.
05:45:18	Google Gemini	`gemini-3-flash-preview` Gemini 3 Flash	229 170 → 680 Tot: 230 639	11.4s	✓ OK
05:42:03	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	10 026 → 271 Tot: 10 967	28.2s	✓ OK
05:41:33	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	9 735 → 303 Tot: 10 737	29.6s	✓ OK
05:41:02	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	10 333 → 311 Tot: 11 604	36.8s	✓ OK
05:33:19	Mistral AI	`mistral-large-2411` Mistral Large (Nov 2024)	1 294 → 701 Tot: 1 995	16s	✓ OK
05:30:56	Google Gemini	`gemma-4-31b-it` Gemma 4 31B	10 271 → 336 Tot: 11 771	44.1s	✓ OK
05:30:10	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 496 → 321 Tot: 1 817	448ms	✓ OK
05:30:07	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 621 → 245 Tot: 1 866	731ms	✓ OK
05:30:07	Google Gemini	`gemini-3-flash-preview` Gemini 3 Flash	-	-	⚠ Limite ⓘ Rate Limit: Gemini API Error (HTTP 429): You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. * Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 20, model: gemini-3-flash Please retry in 52.851935401s.
05:22:02	Mistral AI	`mistral-large-2411` Mistral Large (Nov 2024)	-	-	⚠ Limite ⓘ Rate Limit: Rate limit exceeded: Service tier capacity exceeded for this model.
05:20:31	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 854 → 261 Tot: 2 115	670ms	✓ OK
05:20:28	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 674 → 241 Tot: 1 915	421ms	✓ OK
05:20:25	Cerebras	`llama3.1-8b` Llama 3.1 8B (Cerebras)	1 586 → 241 Tot: 1 827	792ms	✓ OK
05:16:53	Mistral AI	`mistral-large-2411` Mistral Large (Nov 2024)	1 265 → 2 415 Tot: 3 680	51.2s	✓ OK

Comptes API

Provider	Compte	Statut	Priorité	Requêtes	Tokens	Santé
Groq	Groq	✓ Actif	10	18 151 774 erreur(s)	55 001 939	96% 17377 OK / 806 KO
Cerebras	Cerebras Main	✓ Actif	9	56 383 623 erreur(s)	122 663 530	99% 56288 OK / 629 KO
Google Gemini	Gemini Main	✓ Actif	8	12 824 2404 erreur(s)	149 204 354	81% 10420 OK / 2404 KO
Mistral AI	Mistral Experiment	✓ Actif	8	21 052 3416 erreur(s)	82 690 421	84% 17636 OK / 3416 KO
OpenRouter	OpenRouter Main	✓ Actif	10	36	2 339 172	100% 36 OK / 0 KO

Modèles par Provider

Cerebras

Flagship (1)


																gpt-oss-120b

✓

GPT OSS 120B (Cerebras)

Rapide (1)


																llama3.1-8b

✓

Llama 3.1 8B (Cerebras)

Groq

Flagship (6)


																groq/compound

✓


																groq/compound-mini

✓


																llama-3.3-70b-versatile

✓


																moonshotai/kimi-k2-instruct

✓


																moonshotai/kimi-k2-instruct-0905

✓


																openai/gpt-oss-120b

✓

Performant (2)


																meta-llama/llama-4-scout-17b-16e-instruct

✓


																openai/gpt-oss-20b

✓

Rapide (2)


																allam-2-7b

✓


																llama-3.1-8b-instant

✓

Spécialisé (1)


																whisper-large-v3-turbo

✓

Whisper Large V3 Turbo

Google Gemini

Elite (2)


																gemini-2.5-pro

✓

Gemini 2.5 Pro


																gemini-3-pro-preview

✓

Gemini 3 Pro

Flagship (2)


																gemini-2.5-flash

✓

Gemini 2.5 Flash


																gemini-3-flash-preview

🔒 Bloqué

Gemini 3 Flash

Déblocage : 0min

Performant (1)


																gemini-2.5-flash-lite

✓

Gemini 2.5 Flash-Lite

Rapide (2)


																gemma-4-26b-a4b-it

✓

Gemma 4 26B


																gemma-4-31b-it

✓

Gemma 4 31B

Mistral AI

Flagship (1)


																mistral-large-2411

✓

Mistral Large (Nov 2024)

Performant (2)


																mistral-medium

✓

Mistral Medium


																open-mixtral-8x22b

✓

Mixtral 8x22B

Rapide (7)


																ministral-8b-2410

✓

Ministral 8B


																mistral-small-2409

✓

Mistral Small (Sep 2024)


																mistral-small-2501

✓

Mistral Small (Jan 2025)


																mistral-small-2503

✓

Mistral Small (Mar 2025)


																open-mistral-7b

✓

Mistral 7B


																open-mistral-nemo

✓

Mistral Nemo


																open-mixtral-8x7b

✓

Mixtral 8x7B

OpenRouter

Elite (1)


																x-ai/grok-4.1-fast

✓

Grok 4.1 Fast (OR)

Flagship (1)


																openai/gpt-oss-120b

✓

GPT OSS 120B (OR)

Performant (1)


																openai/gpt-oss-20b

✓

GPT OSS 20B (OR)

Dashboard AI Gateway Multi-Provider v2.0

Actualisation automatique dans 30s