- Contexto
- 1M
- Entrada
- $0.3 /Mt· · Leitura de cache $0.006 /Mt
- Saída
- $1.2 /Mt
A inferência em lote está disponível com um desconto introdutório de 50% nos tokens de entrada e saída para modelos compatíveis. Saiba mais
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 1M | $0.3 /Mt· · Leitura de cache $0.006 /Mt | $1.2 /Mt | Mais |
| DeepSeek V4.1 Flash | 1M | $0.3 /Mt· · Leitura de cache $0.006 /Mt | $1.2 /Mt | Mais |
| DeepSeek V4 Pro 0813 | 1M | $1.32 /Mt· · Leitura de cache $0.044 /Mt | $3.96 /Mt | Mais |
| DeepSeek V4 Flash 0731 | 1M | $0.44 /Mt· · Leitura de cache $0.028 /Mt | $1.32 /Mt | Mais |
| DeepSeek V4 Pro | 1M | $1.6 /Mt· · Leitura de cache $0.135 /Mt | $3.2 /Mt | Mais |
| DeepSeek OCR 2 | 8K | $0.03 /Mt | $0.03 /Mt | Mais |
| DeepSeek R1 0528 | 160K | $0.7 /Mt· · Leitura de cache $0.35 /Mt | $2.5 /Mt | Mais |
| DeepSeek R1 Turbo | 63K | $0.7 /Mt | $2.5 /Mt | Mais |
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Llama 3.1 8B Instruct | 16K | $0.02 /Mt | $0.05 /Mt | Mais |
| Llama 3.3 70B Instruct | 12K | $0.135 /Mt | $0.4 /Mt | Mais |
| Llama 4 Maverick Instruct | 1M | $0.27 /Mt | $0.85 /Mt | Mais |
| Llama 4 Scout Instruct | 128K | $0.18 /Mt | $0.59 /Mt | Mais |
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Qwen3.8 Flash | 977K | $0.15 /Mt· · Leitura de cache $0.016 /Mt· Gravação de cache (5m)$0.2 /Mt | $0.47 /Mt | Mais |
| Qwen3.8 27B | 977K | $0.42 /Mt· · Leitura de cache $0.085 /Mt | $3 /Mt | Mais |
| Qwen3.8 2.4T A95B | 977K | $2 /Mt· · Leitura de cache $0.25 /Mt | $6 /Mt | Mais |
| Qwen3.8 Max | 977K | $2 /Mt· · Leitura de cache $0.25 /Mt· Gravação de cache (5m)$2.5 /Mt | $6 /Mt | Mais |
| Qwen3.7 Max | 977K | $1.25 /Mt· · Leitura de cache $0.25 /Mt | $3.75 /Mt | Mais |
| Qwen3.6 27B | 256K | $0.6 /Mt | $3.6 /Mt | Mais |
| Qwen3.5 27B | 256K | $0.3 /Mt | $2.4 /Mt | Mais |
| Qwen3.5 122B A10B | 256K | $0.4 /Mt | $3.2 /Mt | Mais |
| Qwen3.5 35B A3B | 256K | $0.25 /Mt | $2 /Mt | Mais |
| Qwen3.5 397B A17B | 256K | $0.6 /Mt | $3.6 /Mt | Mais |
| Qwen3.6 35B A3B | 256K | $0.248 /Mt | $1.485 /Mt | Mais |
| Qwen3 VL 30B A3B Instruct | 128K | $0.2 /Mt | $0.7 /Mt | Mais |
| Qwen3 Omni 30B A3B Thinking | 64K | - | Mais | |
| Qwen MT Plus | 16K | $0.25 /Mt | $0.75 /Mt | Mais |
Baidu's ERNIE models providing advanced Chinese language understanding and multimodal capabilities, optimized for Chinese applications with competitive pricing.
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Gemma 4 26B A4B | 256K | $0.13 /Mt | $0.4 /Mt | Mais |
| Gemma 4 31B | 256K | $0.14 /Mt | $0.4 /Mt | Mais |
| Gemma 3 27B | 96K | $0.119 /Mt | $0.2 /Mt | Mais |
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| GLM 5.3 Flash | 1M | $0.15 /Mt· · Leitura de cache $0.03 /Mt | $0.5 /Mt | Mais |
| GLM 5.3 | 1M | $1.4 /Mt· · Leitura de cache $0.26 /Mt | $4.4 /Mt | Mais |
| GLM 5.2 | 1M | $1.4 /Mt· · Leitura de cache $0.26 /Mt | $4.4 /Mt | Mais |
| GLM 5.1 | 200K | $1.38 /Mt· · Leitura de cache $0.26 /Mt | $4.4 /Mt | Mais |
| GLM 5 | 198K | $1 /Mt· · Leitura de cache $0.2 /Mt | $3.2 /Mt | Mais |
| GLM 4.7 Flash | 195K | $0.07 /Mt· · Leitura de cache $0.01 /Mt | $0.4 /Mt | Mais |
| GLM 4.7 | 200K | $0.6 /Mt· · Leitura de cache $0.11 /Mt | $2.2 /Mt | Mais |
| AutoGLM Phone 9B Multilingual | 64K | $0.035 /Mt | $0.138 /Mt | Mais |
| GLM 4.6V | 128K | $0.3 /Mt· · Leitura de cache $0.055 /Mt | $0.9 /Mt | Mais |
| GLM 4.6 | 200K | $0.55 /Mt· · Leitura de cache $0.11 /Mt | $2.2 /Mt | Mais |
| GLM 4.5V | 64K | $0.6 /Mt· · Leitura de cache $0.11 /Mt | $1.8 /Mt | Mais |
| GLM 4.5 Air | 128K | $0.13 /Mt· · Leitura de cache $0.025 /Mt | $0.85 /Mt | Mais |
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Llama 3 8B Stheno V3.2 | 8K | $0.05 /Mt | $0.05 /Mt | Mais |
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| WizardLM 2 8x22B | 64K | $0.62 /Mt | $0.62 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Apodex 1.1 Mini | 256K | Gratuito | Gratuito | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Ling 3.1 Flash 1019 | 977K | $0.3 /Mt· · Leitura de cache $0.06 /Mt | $0.9 /Mt | Mais |
| Ling 3.0 Flash Fin | 256K | $0.075 /Mt· · Leitura de cache $0.015 /Mt | $0.22 /Mt | Mais |
| Ling 3.0 Flash | 256K | $0.06 /Mt· · Leitura de cache $0.012 /Mt | $0.18 /Mt | Mais |
| Ling 3.0 Flash VL | 256K | $0.075 /Mt· · Leitura de cache $0.015 /Mt | $0.22 /Mt | Mais |
| Ling 3.0 Flash Sante | 256K | $0.075 /Mt· · Leitura de cache $0.015 /Mt | $0.22 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Macaron V1 Venti | 1M | $0.825 /Mt· · Leitura de cache $0.165 /Mt | $2.475 /Mt | Mais |
| Macaron V1 Tall | 256K | $0.2475 /Mt· · Leitura de cache $0.044 /Mt | $1.43 /Mt | Mais |
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.
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| MiniMax M3.1 Flash | 977K | $0.15 /Mt· · Leitura de cache $0.015 /Mt | $0.6 /Mt | Mais |
| MiniMax M3 | 977K | - | Mais | |
| MiniMax M2.7 | 200K | $0.3 /Mt· · Leitura de cache $0.06 /Mt | $1.2 /Mt | Mais |
| MiniMax M2.5 | 200K | $0.3 /Mt· · Leitura de cache $0.03 /Mt | $1.2 /Mt | Mais |
| MiniMax M1 | 977K | $0.55 /Mt | $2.2 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Kimi K3.1 Pro Highspeed | 1M | $4 /Mt· · Leitura de cache $0.2 /Mt· Gravação de cache (5m)$4 /Mt· Gravação de cache (1h)$8 /Mt | $20 /Mt | Mais |
| Kimi K3.1 Pro | 1M | $2 /Mt· · Leitura de cache $0.2 /Mt· Gravação de cache (5m)$2 /Mt· Gravação de cache (1h)$4 /Mt | $10 /Mt | Mais |
| Kimi K3 | 1M | $3 /Mt· · Leitura de cache $0.3 /Mt· Gravação de cache (5m)$3 /Mt· Gravação de cache (1h)$6 /Mt | $15 /Mt | Mais |
| Kimi K2.7 Code | 256K | $0.95 /Mt· · Leitura de cache $0.19 /Mt | $4 /Mt | Mais |
| Kimi K2.6 | 256K | $0.8 /Mt· · Leitura de cache $0.16 /Mt | $3.4 /Mt | Mais |
| Kimi K2.5 | 256K | $0.6 /Mt· · Leitura de cache $0.1 /Mt | $3 /Mt | Mais |
| Kimi K2 Thinking | 256K | $0.6 /Mt· · Leitura de cache $0.15 /Mt | $2.5 /Mt | Mais |
| Kimi K2 Instruct 0905 | 256K | $0.6 /Mt | $2.5 /Mt | Mais |
| Kimi K2 Instruct | 128K | $0.57 /Mt | $2.3 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| NVIDIA Nemotron 3 Nano 30B A3B | 256K | $0.05 /Mt | $0.2 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| OpenAI GPT OSS 120B | 128K | $0.05 /Mt | $0.25 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Step 5 Preview | 977K | $1 /Mt· · Leitura de cache $0.1 /Mt | $2.7 /Mt | Mais |
| Step 3.7 Flash | 256K | $0.2 /Mt· · Leitura de cache $0.04 /Mt | $1.15 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| Hy4 Preview | 977K | $0.834 /Mt· · Leitura de cache $0.042 /Mt | $2.501 /Mt | Mais |
| Hy3 | 256K | $0.14 /Mt· · Leitura de cache $0.035 /Mt | $0.58 /Mt | Mais |
--
--
| Nome do modelo | Contexto | Entrada | Saída | Ações |
|---|---|---|---|---|
| MiMo V2.6 Flash | 1M | $0.14 /Mt· · Leitura de cache $0.0028 /Mt | $0.28 /Mt | Mais |
| MiMo V2.6 Pro | 1M | $0.435 /Mt· · Leitura de cache $0.0036 /Mt | $0.87 /Mt | Mais |
| Model Name | Context | Price |
|---|---|---|
| Qwen3 Embedding 8B | 32K | $0.07/Mt |
| BAAI:BGE-M3 | 8K | $0.01/Mt |
| 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 |