Modelos y tarifas
Precios en USD por 1M de tokens. El número tachado es el precio oficial del proveedor; el número destacado es tu precio con descuento.
63 / 63
| Modelo | Servido en | Capacidades | Contexto | Entrada | Salida | Entrada en caché | Salud · 24 h |
|---|---|---|---|---|---|---|---|
GPT-4.1×0.6 gpt-4.1 | OpenAI Microsoft Azure · Foundry | 1.0M | $1.20$2.00 | $4.80$8.00 | $0.3$0.5 | 100% | |
GPT-4.1 Mini×0.6 gpt-4.1-mini | OpenAI Microsoft Azure · Foundry | 1.0M | $0.24$0.4 | $0.96$1.60 | $0.06$0.1 | 100% | |
GPT-4.1 Nano×0.6 gpt-4.1-nano | OpenAI Microsoft Azure · Foundry | 1.0M | $0.06$0.1 | $0.24$0.4 | $0.018$0.03 | 100% | |
GPT-4o×0.6 gpt-4o | OpenAI Microsoft Azure · Foundry | 128K | $1.50$2.50 | $6.00$10.00 | — | 100% | |
GPT-4o-mini×0.6 gpt-4o-mini | OpenAI Microsoft Azure · Foundry | 128K | $0.09$0.15 | $0.36$0.6 | $0.045$0.075 | 100% | |
GPT-5×0.6 gpt-5 | OpenAI Microsoft Azure · Foundry | 400K | $0.75$1.25 | $6.00$10.00 | $0.075$0.125 | 100% | |
GPT-5 Mini×0.6 gpt-5-mini | OpenAI Microsoft Azure · Foundry | 400K | $0.15$0.25 | $1.20$2.00 | $0.018$0.03 | 100% | |
GPT-5 Nano×0.6 gpt-5-nano | OpenAI Microsoft Azure · Foundry | 400K | $0.03$0.05 | $0.24$0.4 | $0.006$0.01 | 100% | |
GPT-5.1×0.6 gpt-5.1 | OpenAI Microsoft Azure · Foundry | 400K | $0.75$1.25 | $6.00$10.00 | $0.078$0.13 | 100% | |
GPT-5.1-Codex×0.6 gpt-5.1-codex | OpenAI Microsoft Azure · Foundry | 400K | $0.75$1.25 | $6.00$10.00 | $0.078$0.13 | 100% | |
GPT-5.2×0.6 gpt-5.2 | OpenAI Microsoft Azure · Foundry | 400K | $1.05$1.75 | $8.40$14.00 | $0.105$0.175 | 100% | |
GPT-5.2-Codex×0.6 gpt-5.2-codex | OpenAI Microsoft Azure · Foundry | 400K | $1.05$1.75 | $8.40$14.00 | $0.105$0.175 | 100% | |
GPT-5.3-Codex×0.6 gpt-5.3-codex | OpenAI Microsoft Azure · Foundry | 400K | $1.05$1.75 | $8.40$14.00 | $0.105$0.175 | 100% | |
GPT-5.4×0.6 gpt-5.4 | OpenAI Microsoft Azure · Foundry | 1.1M | $1.50$2.50 | $9.00$15.00 | $0.15$0.25 | 100% | |
GPT-5.4 Mini×0.6 gpt-5.4-mini | OpenAI Microsoft Azure · Foundry | 400K | $0.45$0.75 | $2.70$4.50 | $0.045$0.075 | 100% | |
GPT-5.4 Nano×0.6 gpt-5.4-nano | OpenAI Microsoft Azure · Foundry | 400K | $0.12$0.2 | $0.75$1.25 | $0.012$0.02 | 100% | |
GPT-5.5×0.6 gpt-5.5 | OpenAI Microsoft Azure · Foundry | 1.1M | $3.00$5.00 | $18.00$30.00 | $0.3$0.5 | 100% | |
GPT-5.6 Luna×0.6 gpt-5.6-luna | OpenAI Microsoft Azure · Foundry | 1.1M | $0.12$0.2 | $0.72$1.20 | $0.012$0.02 | 100% | |
GPT-5.6 Sol×0.6 gpt-5.6-sol | OpenAI Microsoft Azure · Foundry | 1.1M | $3.00$5.00 | $18.00$30.00 | $0.3$0.5 | 100% | |
GPT-5.6 Terra×0.6 gpt-5.6-terra | OpenAI Microsoft Azure · Foundry | 1.1M | $1.20$2.00 | $7.20$12.00 | $0.12$0.2 | 100% | |
gpt-oss-120b×0.6 gpt-oss-120b | OpenAI Google Cloud · Vertex AI | 131K | $0.054$0.09 | $0.216$0.36 | — | 100% | |
gpt-oss-20b×0.6 gpt-oss-20b | OpenAI Google Cloud · Vertex AI | 131K | $0.042$0.07 | $0.15$0.25 | — | 100% | |
Claude 3 Haiku×0.6 claude-3-haiku | Anthropic AWS · Amazon Bedrock | 200K | $0.15$0.25 | $0.75$1.25 | $0.018$0.03 | 100% | |
Claude Fable 5×0.6 claude-fable-5 | Anthropic Google Cloud · Vertex AI | 1M | $6.00$10.00 | $30.00$50.00 | $0.6$1.00 | 100% | |
Claude Fable 5.1×0.6 claude-fable-5.1 | Anthropic Google Cloud · Vertex AI | 1M | $6.00$10.00 | $30.00$50.00 | $0.15$0.25 | 100% | |
Claude Haiku 4.5×0.6 claude-haiku-4.5 | Anthropic AWS · Amazon Bedrock | 200K | $0.6$1.00 | $3.00$5.00 | $0.06$0.1 | 100% | |
Claude Opus 4.1×0.6 claude-opus-4.1 | Anthropic AWS · Amazon Bedrock | 200K | $9.00$15.00 | $45.00$75.00 | $0.9$1.50 | 100% | |
Claude Opus 4.5×0.6 claude-opus-4.5 | Anthropic AWS · Amazon Bedrock | 200K | $3.00$5.00 | $15.00$25.00 | $0.3$0.5 | 100% | |
Claude Opus 4.6×0.6 claude-opus-4.6 | Anthropic AWS · Amazon Bedrock | 1M | $3.00$5.00 | $15.00$25.00 | $0.3$0.5 | 100% | |
Claude Opus 4.7×0.6 claude-opus-4.7 | Anthropic AWS · Amazon Bedrock | 1M | $3.00$5.00 | $15.00$25.00 | $0.3$0.5 | 100% | |
Claude Opus 4.8×0.6 claude-opus-4.8 | Anthropic AWS · Amazon Bedrock | 1M | $3.00$5.00 | $15.00$25.00 | $0.3$0.5 | 100% | |
Claude Opus 5×0.6 claude-opus-5 | Anthropic AWS · Amazon Bedrock | 1M | $3.00$5.00 | $15.00$25.00 | $0.3$0.5 | 100% | |
Claude Sonnet 4×0.6 claude-sonnet-4 | Anthropic AWS · Amazon Bedrock | 200K | $1.80$3.00 | $9.00$15.00 | $0.18$0.3 | 100% | |
Claude Sonnet 4.5×0.6 claude-sonnet-4.5 | Anthropic AWS · Amazon Bedrock | 1M | $1.80$3.00 | $9.00$15.00 | $0.18$0.3 | 100% | |
Claude Sonnet 4.6×0.6 claude-sonnet-4.6 | Anthropic AWS · Amazon Bedrock | 1M | $1.80$3.00 | $9.00$15.00 | $0.18$0.3 | 100% | |
Claude Sonnet 5×0.6 claude-sonnet-5 | Anthropic AWS · Amazon Bedrock | 1M | $1.20$2.00 | $6.00$10.00 | $0.12$0.2 | 100% | |
Gemini 2.5 Flash×0.6 gemini-2.5-flash | Google Google Cloud · Vertex AI | 1.0M | $0.18$0.3 | $1.50$2.50 | $0.018$0.03 | 100% | |
Gemini 2.5 Flash Lite×0.6 gemini-2.5-flash-lite | Google Google Cloud · Vertex AI | 1.0M | $0.06$0.1 | $0.24$0.4 | $0.006$0.01 | 100% | |
Gemini 3.1 Flash Lite×0.6 gemini-3.1-flash-lite | Google Google Cloud · Vertex AI | 1.0M | $0.15$0.25 | $0.9$1.50 | $0.015$0.025 | 100% | |
Gemini 3.1 Pro Preview×0.6 gemini-3.1-pro | Google Google Cloud · Vertex AI | 1.0M | $1.20$2.00 | $7.20$12.00 | $0.12$0.2 | 100% | |
Gemini 3.5 Flash×0.6 gemini-3.5-flash | Google Google Cloud · Vertex AI | 1.0M | $0.9$1.50 | $5.40$9.00 | $0.09$0.15 | 100% | |
Gemini 3.5 Flash Lite×0.6 gemini-3.5-flash-lite | Google Google Cloud · Vertex AI | 1.0M | $0.18$0.3 | $1.50$2.50 | $0.018$0.03 | 100% | |
Gemini 3.6 Flash×0.6 gemini-3.6-flash | Google Google Cloud · Vertex AI | 1.0M | $0.45$0.75 | $2.25$3.75 | $0.045$0.075 | 100% | |
Gemini 3.7 Flash×0.6 gemini-3.7-flash | Google Google Cloud · Vertex AI | 1.0M | $0.45$0.75 | $2.25$3.75 | $0.045$0.075 | 100% | |
Gemini 3.8 Flash×0.6 gemini-3.8-flash | Google Google Cloud · Vertex AI | 1.0M | $0.45$0.75 | $2.25$3.75 | $0.045$0.075 | 100% | |
Gemma 4 26B A4B ×0.6 gemma-4-26b | Google Google Cloud · Vertex AI | 262K | $0.09$0.15 | $0.36$0.6 | — | 100% | |
DeepSeek V4 Flash 0423×0.6 deepseek-v4-flash | DeepSeek Microsoft Azure · Foundry | 1.0M | $0.126$0.21 | $0.336$0.56 | $0.0186$0.031 | 100% | |
Qwen3 235B A22B Instruct 2507×0.6 qwen3-235b | Alibaba Google Cloud · Vertex AI | 262K | $0.132$0.22 | $0.528$0.88 | — | 100% | |
Qwen3 Coder 480B A35B×0.6 qwen3-coder | Alibaba Google Cloud · Vertex AI | 262K | $0.132$0.22 | $1.08$1.80 | — | 100% | |
Qwen3 Next 80B A3B Instruct×0.6 qwen3-next-80b | Alibaba Google Cloud · Vertex AI | 262K | $0.09$0.15 | $0.72$1.20 | — | 100% | |
Qwen3 Next 80B A3B Thinking×0.6 qwen3-next-80b-thinking | Alibaba Google Cloud · Vertex AI | 262K | $0.09$0.15 | $0.72$1.20 | — | 100% | |
GLM 4.7×0.6 glm-4.7 | Zhipu Google Cloud · Vertex AI | 200K | $0.36$0.6 | $1.32$2.20 | — | 100% | |
GLM 5×0.6 glm-5 | Zhipu AWS · Amazon Bedrock | 203K | $0.6$1.00 | $1.92$3.20 | — | 100% | |
Kimi K2 Thinking×0.6 kimi-k2-thinking | Moonshot Google Cloud · Vertex AI | 262K | $0.36$0.6 | $1.50$2.50 | — | 100% | |
Kimi K2.5×0.6 kimi-k2.5 | Moonshot AWS · Amazon Bedrock | 262K | $0.36$0.6 | $1.80$3.00 | — | 100% | |
Llama 3.1 70B Instruct×0.6 llama-3.1-70b | Meta AWS · Amazon Bedrock | 131K | $0.432$0.72 | $0.432$0.72 | — | 100% | |
MiniMax M2×0.6 minimax-m2 | MiniMax Google Cloud · Vertex AI | 197K | $0.18$0.3 | $0.72$1.20 | — | 100% | |
Grok 4.6×0.6 grok-4.6 | xAI AWS · Amazon Bedrock | 500K | $1.32$2.20 | $3.96$6.60 | $0.33$0.55 | 100% | |
Nova 2 Lite×0.6 nova-2-lite | Amazon AWS · Amazon Bedrock | 1M | $0.18$0.3 | $1.50$2.50 | — | 100% | |
Nova Lite 1.0×0.6 nova-lite | Amazon AWS · Amazon Bedrock | 300K | $0.036$0.06 | $0.144$0.24 | — | 100% | |
Nova Micro 1.0×0.6 nova-micro | Amazon AWS · Amazon Bedrock | 128K | $0.021$0.035 | $0.084$0.14 | — | 100% | |
Nova Pro 1.0×0.6 nova-pro | Amazon AWS · Amazon Bedrock | 300K | $0.48$0.8 | $1.92$3.20 | — | 100% | |
Palmyra X5×0.6 palmyra-x5 | Writer AWS · Amazon Bedrock | 1.0M | $0.36$0.6 | $3.60$6.00 | — | 100% |
La salud se mide con tráfico real de clientes: cada barra es una hora, verde ≥ 99 % de éxito, ámbar ≥ 90 %, rojo por debajo. Las horas sin solicitudes se muestran como saludables.
Cómo se mide
El uso se mide por solicitud. Las solicitudes fallidas (no 2xx) nunca se cobran.
Cada modelo muestra el precio oficial del proveedor y tu precio con descuento; el multiplicador junto al nombre es el que se aplica a ese modelo.
Cada respuesta devuelve el objeto usage estándar de OpenAI; el panel muestra el coste de cada solicitud.