- Contexte
- 1M
- Entrée
- $0.3 /Mt· · Lecture du cache $0.006 /Mt
- Sortie
- $1.2 /Mt
Explorez les tarifs de nos API de modèles et de nos ressources GPU. Trouvez la formule adaptée à vos besoins, avec des tarifs transparents et des options flexibles.
L’inférence par lots est disponible avec une remise de lancement de 50 % sur les tokens d’entrée et de sortie pour les modèles pris en charge. En savoir plus
Advanced AI models from DeepSeek, offering cutting-edge reasoning capabilities and competitive pricing for enterprise and research applications.
Advanced AI models from DeepSeek, offering cutting-edge reasoning capabilities and competitive pricing for enterprise and research applications.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1M | $0.3 /Mt· · Lecture du cache $0.006 /Mt | $1.2 /Mt | Plus |
| DeepSeek V4.1 Flash | 1M | $0.3 /Mt· · Lecture du cache $0.006 /Mt | $1.2 /Mt | Plus |
| DeepSeek V4 Pro 0813 | 1M | $1.32 /Mt· · Lecture du cache $0.044 /Mt | $3.96 /Mt | Plus |
| DeepSeek V4 Flash Vision Exp | 1M | $0.44 /Mt· · Lecture du cache $0.028 /Mt | $1.32 /Mt | Plus |
| DeepSeek V4 Flash 0731 | 1M | $0.44 /Mt· · Lecture du cache $0.028 /Mt | $1.32 /Mt | Plus |
| DeepSeek V4 Flash | 1M | $0.14 /Mt· · Lecture du cache $0.028 /Mt | $0.28 /Mt | Plus |
| DeepSeek V4 Pro | 1M | $1.6 /Mt· · Lecture du cache $0.135 /Mt | $3.2 /Mt | Plus |
| DeepSeek OCR 2 | 8K | $0.03 /Mt | $0.03 /Mt | Plus |
| DeepSeek R1 0528 | 160K | $0.7 /Mt· · Lecture du cache $0.35 /Mt | $2.5 /Mt | Plus |
| DeepSeek R1 Turbo | 63K | $0.7 /Mt | $2.5 /Mt | Plus |
GLM series models from Tsinghua University, featuring advanced Chinese language understanding and generation capabilities.
GLM series models from Tsinghua University, featuring advanced Chinese language understanding and generation capabilities.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| GLM 5.3 Flash | 1M | $0.15 /Mt· · Lecture du cache $0.03 /Mt | $0.5 /Mt | Plus |
| GLM 5.3 | 1M | $1.4 /Mt· · Lecture du cache $0.26 /Mt | $4.4 /Mt | Plus |
| GLM 5.2 | 1M | $1.4 /Mt· · Lecture du cache $0.26 /Mt | $4.4 /Mt | Plus |
| GLM 5.1 | 200K | $1.38 /Mt· · Lecture du cache $0.26 /Mt | $4.4 /Mt | Plus |
| GLM 5 | 198K | $1 /Mt· · Lecture du cache $0.2 /Mt | $3.2 /Mt | Plus |
| GLM 4.7 Flash | 195K | $0.07 /Mt· · Lecture du cache $0.01 /Mt | $0.4 /Mt | Plus |
| GLM 4.7 | 200K | $0.6 /Mt· · Lecture du cache $0.11 /Mt | $2.2 /Mt | Plus |
| AutoGLM Phone 9B Multilingual | 64K | $0.035 /Mt | $0.138 /Mt | Plus |
| GLM 4.6V | 128K | $0.3 /Mt· · Lecture du cache $0.055 /Mt | $0.9 /Mt | Plus |
| GLM 4.6 | 200K | $0.55 /Mt· · Lecture du cache $0.11 /Mt | $2.2 /Mt | Plus |
| GLM 4.5V | 64K | $0.6 /Mt· · Lecture du cache $0.11 /Mt | $1.8 /Mt | Plus |
| GLM 4.5 Air | 128K | $0.13 /Mt· · Lecture du cache $0.025 /Mt | $0.85 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Kimi K3 | 1M | $3 /Mt· · Lecture du cache $0.3 /Mt | $15 /Mt | Plus |
| Kimi K2.7 Code | 256K | $0.95 /Mt· · Lecture du cache $0.19 /Mt | $4 /Mt | Plus |
| Kimi K2.6 | 256K | $0.8 /Mt· · Lecture du cache $0.16 /Mt | $3.4 /Mt | Plus |
| Kimi K2.5 | 256K | $0.6 /Mt· · Lecture du cache $0.1 /Mt | $3 /Mt | Plus |
| Kimi K2 Thinking | 256K | $0.6 /Mt· · Lecture du cache $0.15 /Mt | $2.5 /Mt | Plus |
| Kimi K2 Instruct 0905 | 256K | $0.6 /Mt | $2.5 /Mt | Plus |
| Kimi K2 Instruct | 128K | $0.57 /Mt | $2.3 /Mt | Plus |
Meta's Llama models providing state-of-the-art language understanding with open architecture designed for diverse applications.
Meta's Llama models providing state-of-the-art language understanding with open architecture designed for diverse applications.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Llama 3.1 8B Instruct | 16K | $0.02 /Mt | $0.05 /Mt | Plus |
| Llama 3.3 70B Instruct | 12K | $0.135 /Mt | $0.4 /Mt | Plus |
| Llama 4 Maverick Instruct | 1M | $0.27 /Mt | $0.85 /Mt | Plus |
| Llama 4 Scout Instruct | 128K | $0.18 /Mt | $0.59 /Mt | Plus |
Qwen series models offering efficient language processing with various parameter sizes, from lightweight to enterprise-grade solutions.
Qwen series models offering efficient language processing with various parameter sizes, from lightweight to enterprise-grade solutions.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Qwen3.8 Flash | 977K | $0.15 /Mt· · Lecture du cache $0.016 /Mt | $0.47 /Mt | Plus |
| Qwen3.8 27B | 977K | $0.42 /Mt· · Lecture du cache $0.085 /Mt | $3 /Mt | Plus |
| Qwen3.8 2.4T A95B | 977K | $2 /Mt· · Lecture du cache $0.25 /Mt | $6 /Mt | Plus |
| Qwen3.8 Max | 977K | $2 /Mt· · Lecture du cache $0.25 /Mt | $6 /Mt | Plus |
| Qwen3.7 Max | 977K | $1.25 /Mt· · Lecture du cache $0.25 /Mt | $3.75 /Mt | Plus |
| Qwen3.6 27B | 256K | $0.6 /Mt | $3.6 /Mt | Plus |
| Qwen3.5 27B | 256K | $0.3 /Mt | $2.4 /Mt | Plus |
| Qwen3.5 122B A10B | 256K | $0.4 /Mt | $3.2 /Mt | Plus |
| Qwen3.5 35B A3B | 256K | $0.25 /Mt | $2 /Mt | Plus |
| Qwen3.5 397B A17B | 256K | $0.6 /Mt | $3.6 /Mt | Plus |
| Qwen3 Coder Next | 256K | $0.2 /Mt | $1.5 /Mt | Plus |
| Qwen3 VL 235B A22B Thinking | 128K | $0.98 /Mt | $3.95 /Mt | Plus |
| Qwen3.6 35B A3B | 256K | $0.248 /Mt | $1.485 /Mt | Plus |
| Qwen3 Next 80B A3B Instruct | 128K | $0.15 /Mt | $1.5 /Mt | Plus |
| Qwen3 VL 235B A22B Instruct | 128K | $0.3 /Mt | $1.5 /Mt | Plus |
| Qwen3 Max | 256K | - | Plus | |
| Qwen3 Coder 480B A35B Instruct | 256K | $0.38 /Mt | $1.55 /Mt | Plus |
| Qwen3 Coder 30B A3B Instruct | 156K | $0.07 /Mt | $0.27 /Mt | Plus |
| Qwen3 235B A22B Thinking 2507 | 128K | $0.3 /Mt | $3 /Mt | Plus |
| Qwen3 235B A22B Instruct 2507 | 128K | $0.09 /Mt | $0.58 /Mt | Plus |
| Qwen2.5 72B Instruct | 31K | $0.38 /Mt | $0.4 /Mt | Plus |
| Qwen3 235B A22B | 40K | $0.2 /Mt | $0.8 /Mt | Plus |
| Qwen3 VL 30B A3B Instruct | 128K | $0.2 /Mt | $0.7 /Mt | Plus |
| Qwen3 Omni 30B A3B Thinking | 64K | - | Plus | |
| Qwen3 Omni 30B A3B Instruct | 64K | - | Plus | |
| Qwen MT Plus | 16K | $0.25 /Mt | $0.75 /Mt | Plus |
Google's Gemma models offering high-quality language processing with excellent performance for various NLP tasks.
Google's Gemma models offering high-quality language processing with excellent performance for various NLP tasks.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Gemma 4 26B A4B | 256K | $0.13 /Mt | $0.4 /Mt | Plus |
| Gemma 4 31B | 256K | $0.14 /Mt | $0.4 /Mt | Plus |
| Gemma 3 27B | 96K | $0.119 /Mt | $0.2 /Mt | Plus |
Efficient and powerful language models from Mistral AI, designed for both commercial and open-source applications.
Efficient and powerful language models from Mistral AI, designed for both commercial and open-source applications.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Mistral Nemo | 59K | $0.04 /Mt | $0.17 /Mt | Plus |
Microsoft's models deliver state-of-the-art multilingual capabilities with enterprise-grade security, seamlessly integrated into the Azure cloud ecosystem. Optimized for cross-platform collaboration and business intelligence, these models excel in document understanding and generation—key strengths for Microsoft 365 workflows.
Microsoft's models deliver state-of-the-art multilingual capabilities with enterprise-grade security, seamlessly integrated into the Azure cloud ecosystem. Optimized for cross-platform collaboration and business intelligence, these models excel in document understanding and generation—key strengths for Microsoft 365 workflows.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| WizardLM 2 8x22B | 64K | $0.62 /Mt | $0.62 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Ling 3.1 Flash | 256K | Gratuit | Gratuit | Plus |
| Ling 3.0 Flash Sante | 256K | Gratuit | Gratuit | Plus |
| Ling 3.0 Flash Fin | 256K | $0.075 /Mt· · Lecture du cache $0.015 /Mt | $0.22 /Mt | Plus |
| Ling 3.0 Flash | 256K | $0.06 /Mt· · Lecture du cache $0.012 /Mt | $0.18 /Mt | Plus |
| Ling 3.0 Flash VL | 256K | $0.075 /Mt· · Lecture du cache $0.015 /Mt | $0.22 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Macaron V1 Venti | 1M | $0.825 /Mt· · Lecture du cache $0.165 /Mt | $2.475 /Mt | Plus |
| Macaron V1 Tall | 256K | $0.2475 /Mt· · Lecture du cache $0.044 /Mt | $1.43 /Mt | Plus |
Minimax AI's advanced language models delivering robust conversational AI capabilities with optimized performance for customer service, content generation, and creative applications, featuring strong multilingual support and enterprise-ready scalability.
Minimax AI's advanced language models delivering robust conversational AI capabilities with optimized performance for customer service, content generation, and creative applications, featuring strong multilingual support and enterprise-ready scalability.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| MiniMax M3 | 977K | - | Plus | |
| MiniMax M2.7 | 200K | $0.3 /Mt· · Lecture du cache $0.06 /Mt | $1.2 /Mt | Plus |
| MiniMax M2.5 Highspeed | 200K | $0.6 /Mt· · Lecture du cache $0.03 /Mt | $2.4 /Mt | Plus |
| MiniMax M2.5 | 200K | $0.3 /Mt· · Lecture du cache $0.03 /Mt | $1.2 /Mt | Plus |
| MiniMax M2.1 | 200K | $0.3 /Mt· · Lecture du cache $0.03 /Mt | $1.2 /Mt | Plus |
| MiniMax M2 | 200K | $0.3 /Mt· · Lecture du cache $0.03 /Mt | $1.2 /Mt | Plus |
| MiniMax M1 | 977K | $0.55 /Mt | $2.2 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| NVIDIA Nemotron 3 Nano 30B A3B | 256K | $0.05 /Mt | $0.2 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| OpenAI GPT OSS 120B | 128K | $0.05 /Mt | $0.25 /Mt | Plus |
| OpenAI GPT OSS 20B | 128K | $0.04 /Mt | $0.15 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Step 3.7 Flash | 256K | $0.2 /Mt· · Lecture du cache $0.04 /Mt | $1.15 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Hy4 Preview | 977K | $0.834 /Mt· · Lecture du cache $0.042 /Mt | $2.501 /Mt | Plus |
| Hy3 | 256K | $0.14 /Mt· · Lecture du cache $0.035 /Mt | $0.58 /Mt | Plus |
--
--
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| MiMo V2.6 Flash | 1M | $0.14 /Mt· · Lecture du cache $0.0028 /Mt | $0.28 /Mt | Plus |
| MiMo V2.6 Pro | 1M | $0.435 /Mt· · Lecture du cache $0.0036 /Mt | $0.87 /Mt | Plus |
Baidu's ERNIE models providing advanced Chinese language understanding and multimodal capabilities, optimized for Chinese applications with competitive pricing.
Baidu's ERNIE models providing advanced Chinese language understanding and multimodal capabilities, optimized for Chinese applications with competitive pricing.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| CoBuddy | 128K | $0.28 /Mt· · Lecture du cache $0.07 /Mt | $1.13 /Mt | Plus |
| ERNIE 4.5 VL 424B A47B | 120K | $0.42 /Mt | $1.25 /Mt | Plus |
| ERNIE 4.5 21B A3B | 117K | $0.07 /Mt | $0.28 /Mt | Plus |
Specialized fine-tuned models optimized for creative and roleplay applications with enhanced storytelling capabilities.
Specialized fine-tuned models optimized for creative and roleplay applications with enhanced storytelling capabilities.
| Nom du modèle | Contexte | Entrée | Sortie | Actions |
|---|---|---|---|---|
| Llama 3 8B Lunaris | 8K | $0.05 /Mt | $0.05 /Mt | Plus |
| Llama 3 8B Stheno V3.2 | 8K | $0.05 /Mt | $0.05 /Mt | Plus |
| Llama 3.1 70B Euryale V2.2 | 8K | $1.48 /Mt | $1.48 /Mt | Plus |
| Nom du modèle | Contexte | Entrée |
|---|---|---|
qwen/qwen3-embedding-0.6b | 32K | $0.07 /Mt |
Qwen3 Embedding 8B | 32K | $0.07 /Mt |
BAAI:BGE-M3 | 8K | $0.01 /Mt |
Pricing may vary based on image dimensions, inference steps, and upscaling factors. Use theCalculateur de tarifsfor an estimate.
| Nom de l’API | Mode | Largeur&Hauteur | Tarifs |
|---|---|---|---|
Qwen-Image Edit | - | - | $0.02 /image |
Qwen-Image Text to Image | - | - | $0.02 /image |
ming image 0.1 design | Input | - | $0/Mt$1/Mt |
| Output | - | $0/Mt$1/Mt | |
ming image 0.1 design layer | Input | - | $0/Mt$1/Mt |
| Output | - | $0/Mt$1/Mt |
Pricing may vary based on the number of frames, chosen model, and inference steps. Use theCalculateur de tarifsfor an estimate.
| Nom de l’API | Mode | Durée | Résolution | Tarifs |
|---|---|---|---|---|
Kling v3.0 Pro Image-to-Video | No Audio | - | $0.112 /s | |
| Audio | - | $0.168 /s | ||
Kling v3.0 Pro Text-to-Video | No Audio | - | $0.112 /s | |
| Audio | - | $0.168 /s | ||
Kling v3.0 Standard Image-to-Video | No Audio | - | $0.084 /s | |
| Audio | - | $0.126 /s | ||
Kling v3.0 Standard Text-to-Video | No Audio | - | $0.084 /s | |
| Audio | - | $0.126 /s | ||
Minimax Hailuo 2.3 Fast Image to Video | - | 6s | 768P | $0.19 /video |
| - | 10s | 768P | $0.32 /video | |
| - | 6s | 1080P | $0.33 /video | |
Minimax Hailuo 2.3 Image to Video | - | 6s | 768P | $0.28 /video |
| - | 10s | 768P | $0.56 /video | |
| - | 6s | 1080P | $0.49 /video | |
Minimax Hailuo 2.3 Text to Video | - | 6s | 768P | $0.28 /video |
| - | 10s | 768P | $0.56 /video | |
| - | 6s | 1080P | $0.49 /video | |
Wan 2.5 Image to Video | - | 5s | 480P | $0.25 /video |
| - | 10s | 480P | $0.50 /video | |
| - | 5s | 720P | $0.50 /video | |
| - | 10s | 720P | $1.00 /video | |
| - | 5s | 1080P | $0.75 /video | |
| - | 10s | 1080P | $1.50 /video | |
Wan 2.5 Text to Video | - | 5s | 480P | $0.25 /video |
| - | 10s | 480P | $0.50 /video | |
| - | 5s | 720P | $0.50 /video | |
| - | 10s | 720P | $1.00 /video | |
| - | 5s | 1080P | $0.75 /video | |
| - | 10s | 1080P | $1.50 /video | |
Wan 2.6 Image to Video | - | 5s | 720P | $0.50 /video |
| - | 10s | 720P | $1.00 /video | |
| - | 15s | 720P | $1.50 /video | |
| - | 5s | 1080P | $0.75 /video | |
| - | 10s | 1080P | $1.50 /video | |
| - | 15s | 1080P | $2.25 /video | |
Wan 2.6 Reference to Video | - | 5s | 720P | $0.50 /video |
| - | 10s | 720P | $1.00 /video | |
| - | 5s | 1080P | $0.75 /video | |
| - | 10s | 1080P | $1.50 /video | |
Wan 2.6 Text to Video | - | 5s | 720P | $0.50 /video |
| - | 10s | 720P | $1.00 /video | |
| - | 15s | 720P | $1.50 /video | |
| - | 5s | 1080P | $0.75 /video | |
| - | 10s | 1080P | $1.50 /video | |
| - | 15s | 1080P | $2.25 /video |
| Nom de l’API | Modèle | Étapes | Tarifs |
|---|---|---|---|
Image to Video | SVD-XT | 20 | $0.024 /video |
| SVD | 20 | $0.0134 /video |
| Nom de l’API | Mode | Tarifs |
|---|---|---|
Fish Audio Text to Speech | - | $15 /1M characters |
Fish Audio Voice Cloning | - | $0.1 /voice |
MiniMax Voice-Cloning | - | $1.5 /voice |
Text to Speech | - | $15 /1M characters |
| API Name | Mode | Pricing |
|---|---|---|
| EXA | neuralSearch | $0.007/request |
| deepSearch | $0.012/request | |
| deepReasoningSearch | $0.015/request | |
| additional_result | $0.001/result (beyond 10 results) | |
| answer | $0.005/request | |
| contentText | $0.001/item | |
| contentHighlight | $0.001/item | |
| contentSummary | $0.001/item | |
| Tavily | basicSearch | $0.008/request |
| advancedSearch | $0.016/request | |
| basicExtract | $0.0016/url | |
| advancedExtract | $0.0032/url | |
| regularMapping | $0.0008/page | |
| instructedMapping | $0.0016/page | |
| Crawl | Extract + Mapping Cost |
Plus de 200 modèles, des GPUs à la demande et des environnements d’exécution d’agents sécurisés — unifiés sous une seule API. Gratuit pour commencer, évolutif à mesure que vous grandissez.