Preços

Preços para escalar sem interrupções, da ideia ao nível empresarial

Explore os preços das nossas APIs de modelos e recursos de GPU. Encontre o plano certo para atender às suas necessidades, com tarifas transparentes e opções flexíveis.

A inferência em lote está disponível com um desconto introdutório de 50% nos tokens de entrada e saída para modelos compatíveis. Saiba mais

DeepSeekDeepSeek

Advanced AI models from DeepSeek, offering cutting-edge reasoning capabilities and competitive pricing for enterprise and research applications.

Z.aiZ.ai

GLM series models from Tsinghua University, featuring advanced Chinese language understanding and generation capabilities.

GLM 5.3 Flash

Mais
Contexto
1M
Entrada
$0.15 /Mt· · Leitura de cache $0.03 /Mt
Saída
$0.5 /Mt

GLM 5.3

Mais
Contexto
1M
Entrada
$1.4 /Mt· · Leitura de cache $0.26 /Mt
Saída
$4.4 /Mt

GLM 5.2

Mais
Contexto
1M
Entrada
$1.4 /Mt· · Leitura de cache $0.26 /Mt
Saída
$4.4 /Mt

GLM 5.1

Mais
Contexto
200K
Entrada
$1.38 /Mt· · Leitura de cache $0.26 /Mt
Saída
$4.4 /Mt

GLM 5

Mais
Contexto
198K
Entrada
$1 /Mt· · Leitura de cache $0.2 /Mt
Saída
$3.2 /Mt

GLM 4.7 Flash

Mais
Contexto
195K
Entrada
$0.07 /Mt· · Leitura de cache $0.01 /Mt
Saída
$0.4 /Mt

GLM 4.7

Mais
Contexto
200K
Entrada
$0.6 /Mt· · Leitura de cache $0.11 /Mt
Saída
$2.2 /Mt

GLM 4.6V

Mais
Contexto
128K
Entrada
$0.3 /Mt· · Leitura de cache $0.055 /Mt
Saída
$0.9 /Mt

GLM 4.6

Mais
Contexto
200K
Entrada
$0.55 /Mt· · Leitura de cache $0.11 /Mt
Saída
$2.2 /Mt

GLM 4.5V

Mais
Contexto
64K
Entrada
$0.6 /Mt· · Leitura de cache $0.11 /Mt
Saída
$1.8 /Mt

GLM 4.5 Air

Mais
Contexto
128K
Entrada
$0.13 /Mt· · Leitura de cache $0.025 /Mt
Saída
$0.85 /Mt
MoonshotAI
Moonshot AI

--

Kimi K3

Mais
Contexto
1M
Entrada
$3 /Mt· · Leitura de cache $0.3 /Mt
Saída
$15 /Mt

Kimi K2.7 Code

Mais
Contexto
256K
Entrada
$0.95 /Mt· · Leitura de cache $0.19 /Mt
Saída
$4 /Mt

Kimi K2.6

Mais
Contexto
256K
Entrada
$0.8 /Mt· · Leitura de cache $0.16 /Mt
Saída
$3.4 /Mt

Kimi K2.5

Mais
Contexto
256K
Entrada
$0.6 /Mt· · Leitura de cache $0.1 /Mt
Saída
$3 /Mt
MetaMeta

Meta's Llama models providing state-of-the-art language understanding with open architecture designed for diverse applications.

QwenQwen

Qwen series models offering efficient language processing with various parameter sizes, from lightweight to enterprise-grade solutions.

Qwen3.8 Flash

Mais
Contexto
977K
Entrada
$0.15 /Mt· · Leitura de cache $0.016 /Mt
Saída
$0.47 /Mt

Qwen3.8 27B

Mais
Contexto
977K
Entrada
$0.42 /Mt· · Leitura de cache $0.085 /Mt
Saída
$3 /Mt

Qwen3.8 Max

Mais
Contexto
977K
Entrada
$2 /Mt· · Leitura de cache $0.25 /Mt
Saída
$6 /Mt

Qwen3.7 Max

Mais
Contexto
977K
Entrada
$1.25 /Mt· · Leitura de cache $0.25 /Mt
Saída
$3.75 /Mt
GoogleGoogle

Google's Gemma models offering high-quality language processing with excellent performance for various NLP tasks.

MicrosoftMicrosoft

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.

ApodexApodex

--

inclusionAIinclusionAI

--

Ling 3.1 Flash

Mais
Contexto
256K
Entrada
$0.3 /Mt· · Leitura de cache $0.06 /Mt
Saída
$0.9 /Mt

Ling 3.0 Flash

Mais
Contexto
256K
Entrada
$0.06 /Mt· · Leitura de cache $0.012 /Mt
Saída
$0.18 /Mt
Mind LabMind Lab

--

Macaron V1 Tall

Mais
Contexto
256K
Entrada
$0.2475 /Mt· · Leitura de cache $0.044 /Mt
Saída
$1.43 /Mt
MiniMaxMiniMax

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 M2.7

Mais
Contexto
200K
Entrada
$0.3 /Mt· · Leitura de cache $0.06 /Mt
Saída
$1.2 /Mt

MiniMax M2.5

Mais
Contexto
200K
Entrada
$0.3 /Mt· · Leitura de cache $0.03 /Mt
Saída
$1.2 /Mt
NVIDIANVIDIA

--

OpenAI
OpenAI

--

StepFunStepFun

--

Step 3.7 Flash

Mais
Contexto
256K
Entrada
$0.2 /Mt· · Leitura de cache $0.04 /Mt
Saída
$1.15 /Mt
Hunyuan
Tencent

--

Hy4 Preview

Mais
Contexto
977K
Entrada
$0.834 /Mt· · Leitura de cache $0.042 /Mt
Saída
$2.501 /Mt

Hy3

Mais
Contexto
256K
Entrada
$0.14 /Mt· · Leitura de cache $0.035 /Mt
Saída
$0.58 /Mt
XiaomiXiaomi

--

MiMo V2.6 Pro

Mais
Contexto
1M
Entrada
$0.435 /Mt· · Leitura de cache $0.0036 /Mt
Saída
$0.87 /Mt
Wenxin
Baidu

Baidu's ERNIE models providing advanced Chinese language understanding and multimodal capabilities, optimized for Chinese applications with competitive pricing.

CoBuddy

Mais
Contexto
128K
Entrada
$0.28 /Mt· · Leitura de cache $0.07 /Mt
Saída
$1.13 /Mt
Sao10KSao10K

Specialized fine-tuned models optimized for creative and roleplay applications with enhanced storytelling capabilities.

Embedding

Model NameContextPrice
Qwen3 Embedding 8B32K$0.07/Mt
BAAI:BGE-M38K$0.01/Mt

AI Search

neuralSearch

API Name
EXA
Pricing
$0.007/request

deepSearch

API Name
EXA
Pricing
$0.012/request

deepReasoningSearch

API Name
EXA
Pricing
$0.015/request

additional_result

API Name
EXA
Pricing
$0.001/result (beyond 10 results)

answer

API Name
EXA
Pricing
$0.005/request

contentText

API Name
EXA
Pricing
$0.001/item

contentHighlight

API Name
EXA
Pricing
$0.001/item

contentSummary

API Name
EXA
Pricing
$0.001/item

basicSearch

API Name
Tavily
Pricing
$0.008/request

advancedSearch

API Name
Tavily
Pricing
$0.016/request

basicExtract

API Name
Tavily
Pricing
$0.0016/url

advancedExtract

API Name
Tavily
Pricing
$0.0032/url

regularMapping

API Name
Tavily
Pricing
$0.0008/page

instructedMapping

API Name
Tavily
Pricing
$0.0016/page

Crawl

API Name
Tavily
Pricing
Extract + Mapping Cost

Tudo o que você precisa para criar IA de produção.

Mais de 200 modelos, GPUs sob demanda e ambientes de execução de agentes seguros — unificados em uma única API. Grátis para começar, escala conforme você cresce.