UberLLM vs LiteLLM
LiteLLM es un software que tú alojas y conectas a proveedores a los que ya pagas; UberLLM es un marketplace alojado donde una clave prepagada llega a modelos de chat, imagen, video, música y voz, cada solicitud va al vendedor saludable más barato, y no tienes servidores ni cuentas de proveedor que gestionar.
Ahora mismo UberLLM da acceso a 484 modelos, 237 de ellos para imágenes, vídeo, música y voz.
UberLLM vs LiteLLM, frente a frente
| UberLLM | LiteLLM | |
|---|---|---|
| Cómo empiezas | Recarga mínima de 5 $, sin suscripción | Gratuito, código abierto (autoalojado) |
| Prueba gratis | No, crédito prepago | Versión gratuita de código abierto |
| Comisión sobre el precio de los modelos | Ninguna por solicitud; comisión de tarjeta de 5,5 % + 0,50 $ al añadir crédito | Ninguno en la versión de código abierto; precios de Enterprise no publicados |
| Funciona con el SDK de OpenAI | Sí | Sí |
| Funciona con Claude Code y el SDK de Anthropic | Sí | Sí |
| Modelos de chat y texto | Sí | Sí |
| Modelos de imagen | Sí | Sí |
| Modelos de vídeo | Sí | Sí |
| Modelos de música | Sí | No |
| El mismo modelo de muchos vendedores | Sí | Sí |
| Las generaciones fallidas son gratis | Sí | No lo indica |
| App sin código (sin programar) | No | No |
| Puedes ejecutarlo en tus propios servidores | No | Sí |
Los datos de LiteLLM salen de su propia web a fecha de 28 de octubre de 2026 (su página de precios). «No lo indica» significa que LiteLLM no lo publica. Las dos empresas son independientes; LiteLLM es una marca registrada de su propietario. Los precios de UberLLM están en directo en el panel de modelos.
Precio, modelo a modelo
Más barato que el precio propio de cada proveedor en 216 de 219 modelos, hasta un 99% menos, con el mejor precio de UberLLM en este momento (revisado el 2 de noviembre de 2026).
| Modelo | UberLLM entrada / salida | Precio del proveedor entrada / salida | En UberLLM |
|---|---|---|---|
| GLM-5.2 z-ai/glm-5.2 | $0.00056 / $0.0022 | $0.0060 / $4.40 | 99% menos |
| GPT-OSS 20B openai/gpt-oss-20b | $0.000018 / $0.000089 | $0.0300 / $0.1300 | 99% menos |
| GPT-OSS 120B openai/gpt-oss-120b | $0.000069 / $0.00030 | $0.0700 / $0.3000 | 99% menos |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | $0.000074 / $0.00030 | $0.0750 / $0.3000 | 99% menos |
| GLM 4.5 Air z-ai/glm-4.5-air | $0.00013 / $0.00084 | $0.1300 / $0.8500 | 99% menos |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0016 / $0.0032 | $1.60 / $3.20 | 99% menos |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0021 / $0.0063 | $2.00 / $6.00 | 99% menos |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0022 / $0.0065 | $2.00 / $6.00 | 99% menos |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.00018 / $0.00056 | $0.1500 / $0.4700 | 99% menos |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.00036 / $0.0014 | $0.3000 / $1.20 | 99% menos |
| Qwen 3.8 27B qwen/qwen-3-8-27b | $0.00020 / $0.0025 | $0.1500 / $1.88 | 99% menos |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.00097 / $0.0056 | $0.6000 / $3.50 | 99% menos |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0013 / $0.0067 | $0.6500 / $3.41 | 99% menos |
| NVIDIA Nemotron 3 Super 120B nvidia/nemotron-3-super-120b | $0.00077 / $0.0062 | $0.3000 / $2.40 | 99% menos |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.00018 / $0.0014 | $0.0450 / $0.5000 | 99% menos |
| GLM-4.7 z-ai/glm-4.7 | $0.0028 / $0.0102 | $0.5500 / $2.20 | 99% menos |
| GLM 4.7 Flash z-ai/glm-4.7-flash | $0.00031 / $0.0020 | $0.0605 / $0.4000 | 99% menos |
| Kimi K3 moonshotai/kimi-k3 | $0.0010 / $0.0788 | $0.1920 / $15.00 | 99% menos |
| GLM-5 z-ai/glm-5 | $0.0054 / $0.0174 | $1.00 / $3.20 | 99% menos |
| Meta: Muse Spark 1.2 meta-llama/muse-spark-1.2 | $0.0078 / $0.0267 | $1.25 / $4.25 | 99% menos |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.00046 / $0.00058 | $0.0500 / $0.1000 | 99% menos |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.00057 / $0.0035 | $0.0900 / $0.5500 | 99% menos |
| Meta: Muse Spark 1.1 meta-llama/muse-spark-1.1 | $0.0079 / $0.0268 | $1.25 / $4.25 | 99% menos |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.00045 / $0.0015 | $0.0675 / $0.2250 | 99% menos |
| Meta: Muse Spark 1.2 Contributor meta-llama/muse-spark-1.2-contributor | $0.00069 / $0.0014 | $0.1000 / $0.2000 | 99% menos |
Ver los 219 modelos
| Modelo | UberLLM entrada / salida | Precio del proveedor entrada / salida | En UberLLM |
|---|---|---|---|
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0036 / $0.0216 | $0.5000 / $3.00 | 99% menos |
| Meta: Muse Spark 1.3 meta-llama/muse-spark-1.3 | $0.0091 / $0.0311 | $1.25 / $4.25 | 99% menos |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.00090 / $0.0018 | $0.1190 / $0.2380 | 99% menos |
| Gemma 4 31B google/gemma-4-31b | $0.00091 / $0.0027 | $0.1200 / $0.3600 | 99% menos |
| GPT-6 Astra openai/gpt-6-astra | $0.0799 / $0.3993 | $10.00 / $50.00 | 99% menos |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.0400 / $0.2000 | $5.00 / $25.00 | 99% menos |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0050 / $0.0250 | $0.6250 / $3.13 | 99% menos |
| Kimi K2.5 moonshotai/kimi-k2.5 | $0.0041 / $0.0205 | $0.5000 / $2.50 | 99% menos |
| Grok 4.5 x-ai/grok-4.5 | $0.0168 / $0.0505 | $2.00 / $6.00 | 99% menos |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.00086 / $0.0095 | $0.0900 / $1.10 | 99% menos |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0024 / $0.0086 | $0.2700 / $0.9500 | 99% menos |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0074 / $0.0372 | $0.8250 / $4.13 | 99% menos |
| MiniMax M2 minimax/minimax-m2 | $0.0023 / $0.0093 | $0.2550 / $1.02 | 99% menos |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.00090 / $0.0034 | $0.1200 / $0.3600 | 99% menos |
| Meta: Muse Spark 1.3 Contributor meta-llama/muse-spark-1.3-contributor | $0.00094 / $0.0019 | $0.1000 / $0.2000 | 99% menos |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.0285 / $0.1425 | $3.00 / $15.00 | 99% menos |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0014 / $0.0045 | $0.1500 / $0.4700 | 99% menos |
| GLM-4.6 z-ai/glm-4.6 | $0.0042 / $0.0170 | $0.4300 / $1.75 | 99% menos |
| GLM 4.5 z-ai/glm-4.5 | $0.0059 / $0.0216 | $0.6000 / $2.20 | 99% menos |
| Thinking Machines: Inkling thinking-machines/inkling | $0.0094 / $0.0401 | $1.00 / $4.05 | 99% menos |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.00049 / $0.0015 | $0.0500 / $0.1500 | 99% menos |
| Gemma 3 27B google/gemma-3-27b-it | $0.00079 / $0.0020 | $0.0800 / $0.2000 | 99% menos |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.00069 / $0.0028 | $0.0700 / $0.2800 | 99% menos |
| Qwen3 32B qwen/qwen3-32b | $0.00079 / $0.0028 | $0.0800 / $0.2800 | 99% menos |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0012 / $0.0079 | $0.1200 / $0.8000 | 99% menos |
| DeepSeek V3.1 deepseek/deepseek-v3.1 | $0.0025 / $0.0094 | $0.2500 / $0.9500 | 99% menos |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0030 / $0.0099 | $0.3000 / $1.00 | 99% menos |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0025 / $0.0149 | $0.2500 / $1.50 | 99% menos |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0021 / $0.0188 | $0.2100 / $1.90 | 99% menos |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0030 / $0.0248 | $0.3000 / $2.50 | 99% menos |
| Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.0059 / $0.0248 | $0.6000 / $2.50 | 99% menos |
| Grok 4.3 x-ai/grok-4.3 | $0.0124 / $0.0248 | $1.25 / $2.50 | 99% menos |
| GLM-5 Turbo z-ai/glm-5-turbo | $0.0119 / $0.0396 | $1.20 / $4.00 | 99% menos |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 / $0.0030 | $0.0750 / $0.3000 | 99% menos |
| Ministral 3B mistralai/ministral-3-3b-instruct | $0.0010 / $0.0010 | $0.1000 / $0.1000 | 99% menos |
| Ministral 14B 3.0 mistralai/ministral-3-14b-instruct | $0.0020 / $0.0020 | $0.2000 / $0.2000 | 99% menos |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.0075 / $0.0375 | $0.7500 / $3.75 | 99% menos |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0150 / $0.0900 | $1.50 / $9.00 | 99% menos |
| Meta: Muse Wonder meta-llama/muse-wonder | $0.0400 / $0.2000 | $4.00 / $20.00 | 99% menos |
| GLM 5.3 z-ai/glm-5.3 | $0.00070 / $0.0141 | $0.0699 / $1.40 | 98% menos |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0020 / $0.0121 | $0.2000 / $1.20 | 98% menos |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0026 / $0.0039 | $0.2600 / $0.3800 | 98% menos |
| NVIDIA Nemotron Nano 12B v2 VL BF16 nvidia/nemotron-nano-12b-v2 | $0.0022 / $0.0065 | $0.2000 / $0.6000 | 98% menos |
| GLM 5.1 z-ai/glm-5.1 | $0.0152 / $0.0479 | $1.40 / $4.40 | 98% menos |
| GLM 5.3 Flash z-ai/glm-5.3-flash | $0.00033 / $0.0011 | $0.0285 / $0.0923 | 98% menos |
| Ministral 3 8B mistralai/ministral-3-8b-instruct | $0.0017 / $0.0017 | $0.1500 / $0.1500 | 98% menos |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0338 / $0.1063 | $2.80 / $8.80 | 98% menos |
| Magistral Small 2509 mistralai/magistral-small-2509 | $0.0069 / $0.0208 | $0.5000 / $1.50 | 98% menos |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.0641 / $0.3205 | $4.00 / $20.00 | 98% menos |
| GPT OSS Safeguard 120B openai/gpt-oss-safeguard-120b | $0.0024 / $0.0096 | $0.1500 / $0.6000 | 98% menos |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.0889 / $0.4444 | $5.00 / $25.00 | 98% menos |
| Claude Opus 5 anthropic/claude-opus-5 | $0.0900 / $0.4500 | $5.00 / $25.00 | 98% menos |
| NVIDIA Nemotron Nano 9B v2 nvidia/nemotron-nano-9b-v2 | $0.0011 / $0.0043 | $0.0600 / $0.2300 | 98% menos |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0378 / $0.2267 | $2.00 / $12.00 | 98% menos |
| Devstral 2 123B mistralai/devstral-2-123b | $0.0077 / $0.0384 | $0.4000 / $2.00 | 98% menos |
| OpenAI: GPT-6.1 Terra openai/gpt-6.1-terra | $0.0196 / $0.0982 | $1.00 / $5.00 | 98% menos |
| Claude Opus 4.5 anthropic/claude-opus-4.5 | $0.0985 / $0.4925 | $5.00 / $25.00 | 98% menos |
| GPT-6 Sol openai/gpt-6-sol | $0.0403 / $0.2013 | $2.00 / $10.00 | 97% menos |
| Palmyra Vision 7B writer/palmyra-vision-7b | $0.0034 / $0.0134 | $0.1500 / $0.6000 | 97% menos |
| GPT-4o Mini openai/gpt-4o-mini | $0.0035 / $0.0138 | $0.1500 / $0.6000 | 97% menos |
| GPT-4o openai/gpt-4o | $0.0589 / $0.2355 | $2.50 / $10.00 | 97% menos |
| GPT-5.4 openai/gpt-5.4 | $0.0608 / $0.3648 | $2.50 / $15.00 | 97% menos |
| GPT-5.5 openai/gpt-5.5 | $0.1250 / $0.7500 | $5.00 / $30.00 | 97% menos |
| GPT-6 Luna openai/gpt-6-luna | $0.0030 / $0.0149 | $0.1000 / $0.5000 | 97% menos |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0045 / $0.0180 | $0.1500 / $0.6000 | 97% menos |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0035 / $0.1206 | $0.1150 / $4.00 | 96% menos |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0910 / $0.0910 | $0.4500 / $3.50 | 96% menos |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0179 / $0.1289 | $0.5000 / $3.60 | 96% menos |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.1579 / $0.7897 | $4.00 / $20.00 | 96% menos |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0819 / $0.4094 | $2.00 / $10.00 | 95% menos |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.0904 / $0.4520 | $2.00 / $10.00 | 95% menos |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0014 / $0.0060 | $0.0300 / $0.1300 | 95% menos |
| Mistral Large mistralai/mistral-large | $0.0928 / $0.2784 | $2.00 / $6.00 | 95% menos |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.0839 / $0.6711 | $1.75 / $14.00 | 95% menos |
| Claude Fable 5 anthropic/claude-fable-5 | $0.4800 / $2.40 | $10.00 / $50.00 | 95% menos |
| Qwen 3.6 35B A3B qwen/qwen3-6-35b-a3b | $0.0049 / $0.0485 | $0.1000 / $1.00 | 95% menos |
| Qwen 3.8 Max qwen/qwen-3-8-max | $0.1212 / $0.3638 | $2.50 / $7.50 | 95% menos |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0159 / $0.1323 | $0.3250 / $2.70 | 95% menos |
| Gemma 4 E2B google/gemma-4-e2b | $0.0020 / $0.0040 | $0.0400 / $0.0800 | 95% menos |
| Mistral Large 3 mistralai/mistral-large-3 | $0.0248 / $0.0742 | $0.5000 / $1.50 | 95% menos |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.0999 / $0.4995 | $2.00 / $10.00 | 95% menos |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.2592 / $1.30 | $5.00 / $25.00 | 94% menos |
| GPT-5.2 openai/gpt-5.2 | $0.0927 / $0.7420 | $1.75 / $14.00 | 94% menos |
| Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | $0.1099 / $0.5495 | $2.00 / $10.00 | 94% menos |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0581 / $0.2907 | $1.00 / $5.00 | 94% menos |
| MiniMax M3 minimax/minimax-m3 | $0.0180 / $0.0719 | $0.3000 / $1.20 | 94% menos |
| Grok 4.7 x-ai/grok-4.7 | $0.1200 / $0.3600 | $2.00 / $6.00 | 94% menos |
| Gemini 3.1 Pro google/gemini-3.1-pro | $0.1200 / $0.7200 | $2.00 / $12.00 | 94% menos |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0192 / $0.0769 | $0.3000 / $1.20 | 93% menos |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0071 / $0.0355 | $0.1000 / $0.5000 | 92% menos |
| Tencent HY3 tencent/hy3 | $0.0095 / $0.0380 | $0.1320 / $0.5280 | 92% menos |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $0.7868 / $3.93 | $10.00 / $50.00 | 92% menos |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.1593 / $0.7963 | $2.00 / $10.00 | 92% menos |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0733 / $0.4401 | $0.7500 / $4.50 | 90% menos |
| GPT 5 Nano openai/gpt-5-nano | $0.0059 / $0.0471 | $0.0500 / $0.4000 | 88% menos |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.11 / $24.64 | $30.00 / $180.00 | 86% menos |
| Grok 4.20 Multi-Agent Beta x-ai/grok-4.20-multi-agent-beta | $0.1750 / $0.3500 | $1.25 / $2.50 | 86% menos |
| Grok 4.20 Beta x-ai/grok-4.20-beta | $0.1750 / $0.3500 | $1.25 / $2.50 | 86% menos |
| Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.0145 / $0.0465 | $0.1000 / $0.3200 | 85% menos |
| MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.0208 / $0.0416 | $0.1400 / $0.2800 | 85% menos |
| MiniMax M3.1 Flash minimax/minimax-m3-1-flash | $0.0225 / $0.0900 | $0.1500 / $0.6000 | 85% menos |
| Grok 4.6 x-ai/grok-4.6 | $0.3564 / $1.07 | $2.00 / $6.00 | 82% menos |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $0.5505 / $2.75 | $3.00 / $15.00 | 81% menos |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0851 / $0.1701 | $0.4350 / $0.8700 | 80% menos |
| GPT 5.4 Nano openai/gpt-5.4-nano | $0.0396 / $0.2475 | $0.2000 / $1.25 | 80% menos |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0182 / $0.0364 | $0.0910 / $0.1820 | 80% menos |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3000 / $2.40 | $1.25 / $10.00 | 76% menos |
| GPT 5 Mini openai/gpt-5-mini | $0.0612 / $0.4900 | $0.2500 / $2.00 | 75% menos |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4375 / $3.50 | $1.75 / $14.00 | 75% menos |
| Gemma 4 26B A4B Uncensored (E2EE) google/e2ee-gemma-4-26b-a4b-uncensored-p | $0.0565 / $0.2618 | $0.1900 / $0.8800 | 70% menos |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.0599 / $0.3593 | $0.2000 / $1.20 | 70% menos |
| Gemini 3.6 Flash google/gemini-3-6-flash | $0.2249 / $1.12 | $0.7500 / $3.75 | 70% menos |
| Gemini 3.5 Flash Lite google/gemini-3-5-flash-lite | $0.0900 / $0.7500 | $0.3000 / $2.50 | 70% menos |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.6000 / $3.60 | $2.00 / $12.00 | 70% menos |
| GPT-5.5 Pro openai/gpt-5.5-pro | $9.00 / $54.00 | $30.00 / $180.00 | 70% menos |
| Qwen 3.6 35B A3B (E2EE) qwen/e2ee-qwen3-6-35b-a3b | $0.0553 / $0.3587 | $0.1820 / $1.18 | 69% menos |
| Qwen3 VL 235B qwen/qwen3-vl-235b-a22b-thinking | $0.0638 / $0.5775 | $0.2100 / $1.90 | 69% menos |
| Mistral Small 4 mistralai/mistral-small-4 | $0.0469 / $0.1875 | $0.1500 / $0.6000 | 68% menos |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0473 / $0.3151 | $0.1500 / $1.00 | 68% menos |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0300 / $0.0900 | $0.1700 / $0.2500 | 67% menos |
| GPT OSS 120B openai/e2ee-gpt-oss-120b-p | $0.0427 / $0.2136 | $0.1300 / $0.6500 | 67% menos |
| Venice Uncensored 1.2 venice/uncensored-1.2 | $0.0659 / $0.2967 | $0.2000 / $0.9000 | 67% menos |
| Venice Role Play Uncensored venice/uncensored-role-play | $0.1648 / $0.6593 | $0.5000 / $2.00 | 67% menos |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.1648 / $0.6593 | $0.5000 / $2.00 | 67% menos |
| Aion 3.0 aion-labs/aion-3-0 | $1.05 / $2.10 | $3.00 / $6.00 | 65% menos |
| Aion 2.0 aion-labs/aion-2.0 | $0.2800 / $0.5600 | $0.8000 / $1.60 | 65% menos |
| Aion 3.5 aion-labs/aion-3-5 | $1.31 / $2.63 | $3.75 / $7.50 | 65% menos |
| Aion 3.0 Mini aion-labs/aion-3-0-mini | $0.2450 / $0.4900 | $0.7000 / $1.40 | 64% menos |
| Aion 3.5 Mini aion-labs/aion-3-5-mini | $0.3063 / $0.6125 | $0.8750 / $1.75 | 64% menos |
| GLM 5.1 E2EE z-ai/e2ee-glm-5.1 | $0.4400 / $1.66 | $1.40 / $4.40 | 62% menos |
| Seed 2.1 Turbo bytedance/seed-2-1-turbo | $0.1976 / $0.9881 | $0.5000 / $2.50 | 60% menos |
| Claude Opus 5 (Fast) anthropic/claude-opus-5-fast | $3.98 / $19.90 | $10.00 / $50.00 | 60% menos |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0299 / $0.0798 | $0.0750 / $0.2000 | 60% menos |
| GLM 4.7 Flash Heretic z-ai/glm-4.7-flash-heretic | $0.0279 / $0.1597 | $0.0700 / $0.4000 | 60% menos |
| Z.ai: GLM 5.3 FlashX z-ai/glm-5.3-flashx | $0.1480 / $0.5000 | $0.3700 / $1.25 | 60% menos |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $0.8000 / $4.00 | $2.00 / $10.00 | 60% menos |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $0.8000 / $4.00 | $2.00 / $10.00 | 60% menos |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.0400 / $0.2000 | $0.1000 / $0.5000 | 59% menos |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.4896 / $1.63 | $1.20 / $4.00 | 59% menos |
| GLM 5.2 E2EE z-ai/e2ee-glm-5-2-p | $0.7851 / $2.58 | $1.75 / $5.75 | 55% menos |
| Hermes 3 Llama 3.1 405b nousresearch/hermes-3-llama-3.1-405b | $0.4496 / $0.4496 | $1.00 / $1.00 | 55% menos |
| inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.0338 / $0.1013 | $0.0750 / $0.2250 | 55% menos |
| MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.2160 / $0.8100 | $0.4800 / $1.80 | 55% menos |
| Sakana: Fugu Max sakana/fugu-max | $0.9200 / $2.76 | $2.00 / $6.00 | 54% menos |
| Sakana: Fugu Ultra v2 sakana/fugu-ultra-v2 | $2.30 / $13.80 | $5.00 / $30.00 | 54% menos |
| Claude Opus 4.8 Fast anthropic/claude-opus-4.8-fast | $4.67 / $23.34 | $10.00 / $50.00 | 53% menos |
| Gemma 4 Uncensored google/gemma-4-uncensored | $0.0780 / $0.2399 | $0.1625 / $0.5000 | 52% menos |
| Qwen 3 Coder 480B Turbo qwen/qwen3-coder-turbo | $0.2100 / $0.9000 | $0.3500 / $1.50 | 39% menos |
| MiMo-V2.5 xiaomi/mimo-v2-5 | $0.2440 / $1.22 | $0.4000 / $2.00 | 39% menos |
| Mercury 2 inception/mercury-2 | $0.1525 / $0.4575 | $0.2500 / $0.7500 | 38% menos |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1525 / $0.5490 | $0.2500 / $0.9000 | 38% menos |
| Abliterated Large Flash abliteration-ai/abliteration-abliterated-model-large-flash | $0.7875 / $1.57 | $1.25 / $2.50 | 37% menos |
| DeepSeek V4 Flash E2EE deepseek/e2ee-deepseek-v4-flash | $0.1147 / $0.2350 | $0.1820 / $0.3730 | 37% menos |
| DeepSeek V4 Flash 0731 Fast deepseek/deepseek-v4-flash-0731-fast | $0.2205 / $0.4410 | $0.3500 / $0.7000 | 37% menos |
| Meta: Muse Spark Open meta-llama/muse-spark-open | $0.8000 / $2.72 | $1.25 / $4.25 | 36% menos |
| Qwen 2.5 7B qwen/e2ee-qwen-2-5-7b-p | $0.0325 / $0.0845 | $0.0500 / $0.1300 | 35% menos |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $2.68 / $13.40 | $4.00 / $20.00 | 32% menos |
| Venice Uncensored 1.1 venice/uncensored | $0.1344 / $0.6048 | $0.2000 / $0.9000 | 32% menos |
| Abliterated Large V2 abliteration-ai/abliteration-abliterated-model-large-v2 | $2.07 / $3.45 | $3.00 / $5.00 | 31% menos |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.6965 / $1.39 | $1.00 / $2.00 | 30% menos |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0840 / $0.3500 | $0.1200 / $0.5000 | 30% menos |
| Kimi K3 Fast moonshotai/kimi-k3-fast-api | $3.15 / $15.75 | $4.50 / $22.50 | 30% menos |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0350 / $0.2310 | $0.0500 / $0.3300 | 29% menos |
| MiniMax M3 Preview minimax/minimax-m3-preview | $0.2100 / $0.8400 | $0.3000 / $1.20 | 29% menos |
| Kimi K2 moonshotai/kimi-k2 | $0.3990 / $1.61 | $0.5700 / $2.30 | 29% menos |
| Qwen3.7 Max qwen/qwen3.7-max | $1.89 / $5.63 | $2.70 / $8.05 | 29% menos |
| Qwen 3.6 Plus Uncensored qwen/qwen3.6-plus-uncensored | $0.4625 / $2.77 | $0.6250 / $3.75 | 26% menos |
| GLM 4.7 Thinking (Morpheus Web) z-ai/glm-4.7-thinking:web | $0.3375 / $1.50 | $0.4500 / $2.00 | 25% menos |
| OpenAI GPT OSS 120B (Morpheus Web) openai/gpt-oss-120b:web | $0.0525 / $0.2250 | $0.0700 / $0.3000 | 24% menos |
| GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.58 / $9.49 | $2.00 / $12.00 | 20% menos |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | $0.1725 / $0.5174 | $0.2156 / $0.6468 | 20% menos |
| Mercury 3 inception/mercury-3 | $0.0800 / $0.2800 | $0.1000 / $0.3500 | 19% menos |
| NVIDIA Nemotron 3.5 Lightning 30B nvidia/nemotron-3-5-lightning-30b-a3b | $0.0640 / $0.1600 | $0.0700 / $0.2000 | 18% menos |
| Trinity Large Thinking arcee-ai/trinity-large-thinking | $0.2344 / $0.8438 | $0.3000 / $1.00 | 16% menos |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0380 / $0.1425 | $0.0400 / $0.1500 | 4% menos |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.6930 / $2.08 | $0.7000 / $2.10 | 1% menos |
| ByteDance Seed: Seed-2.0-Code bytedance/seed-2.0-code | $0.4950 / $2.97 | $0.5000 / $3.00 | 1% menos |
| Fireworks: Ember-1 fireworks/ember-1 | $2.97 / $14.85 | $3.00 / $15.00 | 1% menos |
| Particle AI: Particle-1 particle-ai/particle-1 | $0.0495 / $0.4950 | $0.0500 / $0.5000 | 1% menos |
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.1485 / $0.4950 | $0.1500 / $0.5000 | 1% menos |
| Reflection: Beam 1.0 501B A23B reflection/beam-1.0-501b-a23b | $0.2475 / $0.9900 | $0.2500 / $1.00 | 1% menos |
| Cohere: Command A+ cohere/command-a-plus | $0.2970 / $1.49 | $0.3000 / $1.50 | 1% menos |
| Elorian: Glimpse elorian/glimpse | $0.5940 / $2.97 | $0.6000 / $3.00 | 1% menos |
| Pareto 26.9 unbiased/pareto-26.9 | $2.48 / $7.42 | $2.50 / $7.50 | 1% menos |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $3.96 / $11.88 | $4.00 / $12.00 | 1% menos |
| Moondream: Moondream 3.1 moondream/moondream3.1-9b-a2b | $0.2970 / $2.48 | $0.3000 / $2.50 | 0% menos |
| Moondream: Moondream 3 Preview moondream/moondream3-preview | $0.2970 / $2.48 | $0.3000 / $2.50 | 0% menos |
| OpenAI: GPT-6.1 Terra Pro openai/gpt-6.1-terra-pro | $0.9900 / $4.95 | $1.00 / $5.00 | 0% menos |
| MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | $4.31 / $8.61 | $4.35 / $8.70 | 0% menos |
| LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b | $0.0495 / $0.6930 | $0.0500 / $0.7000 | 0% menos |
| Meta: Muse Glimmer 30B meta-llama/muse-glimmer-30b | $0.2970 / $1.19 | $0.3000 / $1.20 | 0% menos |
| GLM 4.7 Thinking z-ai/glm-4.7-thinking | $0.4500 / $2.00 | $0.4500 / $2.00 | Igual |
| DeepSeek V4.1 Flash Uncensored deepseek/deepseek-v4.1-flash-uncensored | $0.0900 / $1.00 | $0.0450 / $0.5000 | 100% más |
| GLM-5.3 Flash Uncensored z-ai/glm-5.3-flash-uncensored | $0.1500 / $0.5000 | $0.0285 / $0.0923 | 440% más |
$ por cada millón de tokens de entrada / salida. La comparación pondera entrada y salida en proporción 1:3. Los precios de UberLLM son el mejor precio del mercado en este momento; Los precios de los proveedores son el precio de lista oficial de cada modelo, que es lo que pagas a un proveedor a través de LiteLLM. Ambos revisados el 2 de noviembre de 2026. Aparecen todos los modelos que venden los dos, incluidos los que aquí cuestan lo mismo o más.
Qué es LiteLLM
Un gateway de IA de código abierto (servidor proxy y SDK de Python) que tú mismo ejecutas para llamar a muchos proveedores de modelos a través de una API estilo OpenAI con tus propias API keys de proveedor. Añade claves virtuales, presupuestos, seguimiento de gastos, balanceo de carga y mecanismos de fallback.
Cómo pagas
El gateway de código abierto es gratuito; lo ejecutas en tus propios servidores y pagas a cada proveedor de modelos directamente. La versión Enterprise añade SSO, registros de auditoría y soporte con precios personalizados a través de ventas.
Qué es UberLLM
Un mercado de APIs de modelos de IA. Cada solicitud va al vendedor más barato que funcione bien para ese modelo, con una sola clave compatible con OpenAI y Anthropic.
Cómo pagas
Pagas por uso, al precio que ves en cada modelo, sin nada añadido por solicitud. Solo se suma una comisión de tarjeta de 5,5 % + 0,50 $ cuando añades crédito. Una generación que falla no cuesta nada.
Elige UberLLM si
Desarrolladores que quieren el precio más bajo del momento en modelos de chat, imagen, vídeo y música con una sola clave, usando el SDK de OpenAI o Anthropic que ya tienen.
Elige LiteLLM si
Equipos de ingeniería que quieren ejecutar su propio gateway en su propia nube (incluso en entornos air-gapped), mantener sus contratos y API keys de proveedor existentes, y controlar ellos mismos las API keys, los presupuestos y el enrutamiento.
Lo que LiteLLM hace y UberLLM no
- Autoalojamiento, incluyendo configuraciones air-gapped
- Usa tus propias API keys y contratos de proveedor
- Claves virtuales, presupuestos de equipo y límites de tasa que tú controlas
- SSO Enterprise, registros de auditoría y SLAs personalizados
Cámbiate con una sola línea
Apunta a UberLLM el SDK que ya usas. La misma clave sirve para chat, imágenes, vídeo, música y voz.
python
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1", # the only line that changes
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
# the same key makes images (and video, music, speech)
img = client.images.generate(
model="venice/nano-banana-pro",
prompt="a red apple on a white table",
)Preguntas frecuentes
¿Es UberLLM una alternativa a LiteLLM?
En parte. Ambos te ofrecen una API compatible con OpenAI y Anthropic para muchos modelos. LiteLLM es un gateway que tú alojas y conectas a tus propias cuentas de proveedor; UberLLM es un servicio alojado que pagas por uso, por lo que no ejecutas servidores ni tienes API keys de proveedor.
¿En qué se diferencia UberLLM de LiteLLM?
Con LiteLLM ejecutas el proxy y pagas a cada proveedor directamente. Con UberLLM añades crédito prepagado (mínimo $5, tarifa de tarjeta de 5.5% + $0.50 solo cuando añades crédito), pagas el precio mostrado por modelo sin tarifa por solicitud, y cada solicitud va al vendedor saludable más barato. Las generaciones fallidas no cuestan nada, y puedes limitar el precio por solicitud. UberLLM no tiene una versión autoalojada.
¿Puedo usar LiteLLM y UberLLM juntos?
Dado que UberLLM expone endpoints compatibles con OpenAI, puede añadirse como un endpoint compatible con OpenAI detrás de un gateway como LiteLLM. Consulta la documentación de LiteLLM para saber cómo añadir un proveedor personalizado compatible con OpenAI.