Precios simples y transparentes

Paga solo por lo que uses. Sin suscripciones ni cargos ocultos.

Perfecto para probar

$10 pago único

Popular

Para uso regular

$100 pago único

Para uso intensivo

$1000 pago único

¿Necesitas un monto personalizado?

Precios de model

1 credit = $1 USD. Todos los precios incluyen las tarifas de la plataforma.

Model	Input	5m Cache Writes	1h Cache Writes	Cache Hits & Refreshes	Output
GPT-5.6 Sol `openai/gpt-5.6-sol`	Tokens de entrada: [0, 270k]5 / M	30 / M
GPT-5.6 Sol `openai/gpt-5.6-sol`	Tokens de entrada: (270k, 1000k]10 / M	45 / M
GPT-5.6 Terra `openai/gpt-5.6-terra`	Tokens de entrada: [0, 270k]2.5 / M	15 / M
GPT-5.6 Terra `openai/gpt-5.6-terra`	Tokens de entrada: (270k, 1000k]5 / M	22.5 / M
GPT-5.6 Luna `openai/gpt-5.6-luna`	Tokens de entrada: [0, 270k]1 / M	6 / M
GPT-5.6 Luna `openai/gpt-5.6-luna`	Tokens de entrada: (270k, 1000k]2 / M	9 / M
GPT-5.5 `openai/gpt-5.5`	Tokens de entrada: [0, 270k]5 / M	30 / M
GPT-5.5 `openai/gpt-5.5`	Tokens de entrada: (270k, 1000k]10 / M	45 / M
GPT-5.4 `openai/gpt-5.4`	Tokens de entrada: [0, 270k]2.5 / M	15 / M
GPT-5.4 `openai/gpt-5.4`	Tokens de entrada: (270k, 1000k]5 / M	22.5 / M
GPT-5.4-Pro `openai/gpt-5.4-pro`	Tokens de entrada: [0, 270k]30 / M	180 / M
GPT-5.4-Pro `openai/gpt-5.4-pro`	Tokens de entrada: (270k, 1000k]60 / M	270 / M
GPT-5.4-Mini `openai/gpt-5.4-mini`	0.75 / M	—	—	0.075 / M	4.5 / M
GPT-5.4-Nano `openai/gpt-5.4-nano`	0.2 / M	—	—	0.02 / M	1.25 / M
GPT-5.3-Codex `openai/gpt-5.3-codex`	1.75 / M	—	—	0.17 / M	14 / M

Model	Input	5m Cache Writes	1h Cache Writes	Cache Hits & Refreshes	Output
Claude Fable 5 `anthropic/claude-fable-5`	10 / M	12.5 / M	20 / M	1 / M	50 / M
Claude Opus 4.8 `anthropic/claude-opus-4-8`	5 / M	6.25 / M	10 / M	0.5 / M	25 / M
Claude Sonnet 4.6 `anthropic/claude-sonnet-4-6`	3 / M	3.75 / M	6 / M	0.3 / M	15 / M
Claude Opus 4.6 `anthropic/claude-opus-4-6`	5 / M	6.25 / M	10 / M	0.5 / M	25 / M
Claude Opus 4.7 `anthropic/claude-opus-4-7`	5 / M	6.25 / M	10 / M	0.5 / M	25 / M
Claude Haiku 4.5 `anthropic/claude-haiku-4-5`	1 / M	1.25 / M	2 / M	0.1 / M	5 / M

Model	Input	Cached input	Output
Gemini 3.5 Flash `google/gemini-3.5-flash`	1.5 / M	0.15 / M	9 / M
Gemini 3.1 Pro `google/gemini-3.1-pro-preview`	2 / M	0.2 / M	12 / M
Gemini 3.1 Flash Lite `google/gemini-3.1-flash-lite-preview`	0.25 / M	—	1.5 / M
Gemini 3.1 Flash Image `google/gemini-3.1-flash-image-preview`	0.15 / M	—	30 / M
Gemini 3 Pro Image `google/gemini-3-pro-image-preview`	2 / M	—	12 / M
Gemini 3 Flash `google/gemini-3-flash-preview`	0.5 / M	0.05 / M	3 / M

Model	Input	Cached input	Output
Grok 4.20 Reasoning `xai/grok-4.20-reasoning`	1.25 / M	0.2 / M	2.5 / M
Grok 4.20 Fast `xai/grok-4.20-non-reasoning`	1.25 / M	0.2 / M	2.5 / M
Grok Code Fast `xai/grok-code-fast-1`	0.2 / M	0.02 / M	1.5 / M

Model	Input	Output
DeepSeek-V4-Pro `deepseek/deepseek-v4-pro`	0.43 / M	0.87 / M
DeepSeek-V4-Flash `deepseek/deepseek-v4-flash`	0.14 / M	0.28 / M
DeepSeek-V3.2 `deepseek/deepseek-v3.2`	Tokens de entrada: [0, 32k]0.27 / M	0.4 / M
DeepSeek-V3.2 `deepseek/deepseek-v3.2`	Tokens de entrada: (32k, 128k]0.54 / M	0.8 / M
DeepSeek-V3.1 `deepseek/deepseek-v3.1`	0.27 / M	1.1 / M
DeepSeek-V3.2-Think `deepseek/deepseek-v3.2-think`	0.55 / M	2.19 / M
DeepSeek-R1-0528 `deepseek/deepseek-r1-0528`	0.7 / M	2.5 / M

Model	Input	Output
Qwen-Max `alibaba/qwen-max`	0.34 / M	1.38 / M
Qwen-Plus `alibaba/qwen-plus`	0.12 / M	0.29 / M
Qwen-Turbo `alibaba/qwen-turbo`	0.044 / M	0.087 / M
Qwen3.5-397B `alibaba/qwen3.5-397b-a17b`	0.6 / M	3.6 / M
Qwen3-VL-235B `alibaba/qwen3-vl-235b-a22b-instruct`	0.3 / M	1.5 / M
Qwen3-Coder-480B `alibaba/qwen3-coder-480b-a35b-instruct`	0.33 / M	1.65 / M

Model	Input	Cached input	Output
GLM-5.1 `zhipu/glm-5.1`	1.4 / M	0.26 / M	4.4 / M
GLM-5-Turbo `zhipu/glm-5-turbo`	1.2 / M	0.24 / M	4 / M
GLM-5 `zhipu/glm-5`	1 / M	0.2 / M	3.2 / M

Model	Input	Cached input	Output
MiniMax-M2.7 `minimax/minimax-m2.7`	0.28 / M	0.055 / M	1.2 / M
MiniMax-M2.5 `minimax/minimax-m2.5`	0.15 / M	0.03 / M	1.08 / M

Model	Input	Output
MiMo-V2-Pro `xiaomi/mimo-v2-pro`	1 / M	3 / M
MiMo-V2-Omni `xiaomi/mimo-v2-omni`	0.4 / M	2 / M

Model	Input	Cached input	Output
Kimi-K2.6 `kimi/kimi-k2.6`	0.95 / M	0.16 / M	4 / M
Kimi-K2.5 `kimi/kimi-k2.5`	0.6 / M	0.1 / M	3 / M