UberLLM 对比 LiteLLM
LiteLLM 是您自行托管并连接到您已付费的提供商的软件；UberLLM 是一个托管市场，一个预付费 key 即可访问聊天、图像、视频、音乐和语音模型，每个请求都会发送给最便宜且健康的卖家，您无需管理服务器或提供商账户。
UberLLM 目前提供 484 个模型，其中 237 个用于图片、视频、音乐和语音。
UberLLM 与 LiteLLM 并排对比
| UberLLM | LiteLLM | |
|---|---|---|
| 如何开始 | 最低充值 $5，无需订阅 | 免费、开源（自托管） |
| 免费试用 | 无，需预付充值 | 免费开源版本 |
| 模型价格之外的费用 | 请求不收费；充值时收取 5.5% + $0.50 银行卡手续费 | 开源版本不提供；企业版定价未公开 |
| 支持 OpenAI SDK | 是 | 是 |
| 支持 Claude Code 和 Anthropic SDK | 是 | 是 |
| 聊天和文本模型 | 是 | 是 |
| 图片模型 | 是 | 是 |
| 视频模型 | 是 | 是 |
| 音乐模型 | 是 | 否 |
| 同一个模型有多个卖家 | 是 | 是 |
| 生成失败不收费 | 是 | 未说明 |
| 无需写代码的应用 | 否 | 否 |
| 可以部署在自己的服务器上 | 否 | 是 |
LiteLLM 的信息来自其官网，截至 2026年10月28日（其价格页面）。“未说明”表示 LiteLLM 没有公开这项信息。两家公司相互独立；LiteLLM 是其所有者的商标。UberLLM 的实时价格见模型价格榜。
逐个模型比价格
按 UberLLM 当前最低价计算，219 个模型中有 216 个比 各提供商自己的价格 便宜，最多便宜 99%（2026年11月2日 核对）。
| 模型 | UberLLM 输入 / 输出 | 提供商价格 输入 / 输出 | 在 UberLLM 上 |
|---|---|---|---|
| GLM-5.2 z-ai/glm-5.2 | $0.00056 / $0.0022 | $0.0060 / $4.40 | 便宜 99% |
| GPT-OSS 20B openai/gpt-oss-20b | $0.000018 / $0.000089 | $0.0300 / $0.1300 | 便宜 99% |
| GPT-OSS 120B openai/gpt-oss-120b | $0.000069 / $0.00030 | $0.0700 / $0.3000 | 便宜 99% |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | $0.000074 / $0.00030 | $0.0750 / $0.3000 | 便宜 99% |
| GLM 4.5 Air z-ai/glm-4.5-air | $0.00013 / $0.00084 | $0.1300 / $0.8500 | 便宜 99% |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0016 / $0.0032 | $1.60 / $3.20 | 便宜 99% |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0021 / $0.0063 | $2.00 / $6.00 | 便宜 99% |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0022 / $0.0065 | $2.00 / $6.00 | 便宜 99% |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.00018 / $0.00056 | $0.1500 / $0.4700 | 便宜 99% |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.00036 / $0.0014 | $0.3000 / $1.20 | 便宜 99% |
| Qwen 3.8 27B qwen/qwen-3-8-27b | $0.00020 / $0.0025 | $0.1500 / $1.88 | 便宜 99% |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.00097 / $0.0056 | $0.6000 / $3.50 | 便宜 99% |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0013 / $0.0067 | $0.6500 / $3.41 | 便宜 99% |
| NVIDIA Nemotron 3 Super 120B nvidia/nemotron-3-super-120b | $0.00077 / $0.0062 | $0.3000 / $2.40 | 便宜 99% |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.00018 / $0.0014 | $0.0450 / $0.5000 | 便宜 99% |
| GLM-4.7 z-ai/glm-4.7 | $0.0028 / $0.0102 | $0.5500 / $2.20 | 便宜 99% |
| GLM 4.7 Flash z-ai/glm-4.7-flash | $0.00031 / $0.0020 | $0.0605 / $0.4000 | 便宜 99% |
| Kimi K3 moonshotai/kimi-k3 | $0.0010 / $0.0788 | $0.1920 / $15.00 | 便宜 99% |
| GLM-5 z-ai/glm-5 | $0.0054 / $0.0174 | $1.00 / $3.20 | 便宜 99% |
| Meta: Muse Spark 1.2 meta-llama/muse-spark-1.2 | $0.0078 / $0.0267 | $1.25 / $4.25 | 便宜 99% |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.00046 / $0.00058 | $0.0500 / $0.1000 | 便宜 99% |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.00057 / $0.0035 | $0.0900 / $0.5500 | 便宜 99% |
| Meta: Muse Spark 1.1 meta-llama/muse-spark-1.1 | $0.0079 / $0.0268 | $1.25 / $4.25 | 便宜 99% |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.00045 / $0.0015 | $0.0675 / $0.2250 | 便宜 99% |
| Meta: Muse Spark 1.2 Contributor meta-llama/muse-spark-1.2-contributor | $0.00069 / $0.0014 | $0.1000 / $0.2000 | 便宜 99% |
显示全部 219 个模型
| 模型 | UberLLM 输入 / 输出 | 提供商价格 输入 / 输出 | 在 UberLLM 上 |
|---|---|---|---|
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0036 / $0.0216 | $0.5000 / $3.00 | 便宜 99% |
| Meta: Muse Spark 1.3 meta-llama/muse-spark-1.3 | $0.0091 / $0.0311 | $1.25 / $4.25 | 便宜 99% |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.00090 / $0.0018 | $0.1190 / $0.2380 | 便宜 99% |
| Gemma 4 31B google/gemma-4-31b | $0.00091 / $0.0027 | $0.1200 / $0.3600 | 便宜 99% |
| GPT-6 Astra openai/gpt-6-astra | $0.0799 / $0.3993 | $10.00 / $50.00 | 便宜 99% |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.0400 / $0.2000 | $5.00 / $25.00 | 便宜 99% |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0050 / $0.0250 | $0.6250 / $3.13 | 便宜 99% |
| Kimi K2.5 moonshotai/kimi-k2.5 | $0.0041 / $0.0205 | $0.5000 / $2.50 | 便宜 99% |
| Grok 4.5 x-ai/grok-4.5 | $0.0168 / $0.0505 | $2.00 / $6.00 | 便宜 99% |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.00086 / $0.0095 | $0.0900 / $1.10 | 便宜 99% |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0024 / $0.0086 | $0.2700 / $0.9500 | 便宜 99% |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0074 / $0.0372 | $0.8250 / $4.13 | 便宜 99% |
| MiniMax M2 minimax/minimax-m2 | $0.0023 / $0.0093 | $0.2550 / $1.02 | 便宜 99% |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.00090 / $0.0034 | $0.1200 / $0.3600 | 便宜 99% |
| Meta: Muse Spark 1.3 Contributor meta-llama/muse-spark-1.3-contributor | $0.00094 / $0.0019 | $0.1000 / $0.2000 | 便宜 99% |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.0285 / $0.1425 | $3.00 / $15.00 | 便宜 99% |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0014 / $0.0045 | $0.1500 / $0.4700 | 便宜 99% |
| GLM-4.6 z-ai/glm-4.6 | $0.0042 / $0.0170 | $0.4300 / $1.75 | 便宜 99% |
| GLM 4.5 z-ai/glm-4.5 | $0.0059 / $0.0216 | $0.6000 / $2.20 | 便宜 99% |
| Thinking Machines: Inkling thinking-machines/inkling | $0.0094 / $0.0401 | $1.00 / $4.05 | 便宜 99% |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.00049 / $0.0015 | $0.0500 / $0.1500 | 便宜 99% |
| Gemma 3 27B google/gemma-3-27b-it | $0.00079 / $0.0020 | $0.0800 / $0.2000 | 便宜 99% |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.00069 / $0.0028 | $0.0700 / $0.2800 | 便宜 99% |
| Qwen3 32B qwen/qwen3-32b | $0.00079 / $0.0028 | $0.0800 / $0.2800 | 便宜 99% |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0012 / $0.0079 | $0.1200 / $0.8000 | 便宜 99% |
| DeepSeek V3.1 deepseek/deepseek-v3.1 | $0.0025 / $0.0094 | $0.2500 / $0.9500 | 便宜 99% |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0030 / $0.0099 | $0.3000 / $1.00 | 便宜 99% |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0025 / $0.0149 | $0.2500 / $1.50 | 便宜 99% |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0021 / $0.0188 | $0.2100 / $1.90 | 便宜 99% |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0030 / $0.0248 | $0.3000 / $2.50 | 便宜 99% |
| Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.0059 / $0.0248 | $0.6000 / $2.50 | 便宜 99% |
| Grok 4.3 x-ai/grok-4.3 | $0.0124 / $0.0248 | $1.25 / $2.50 | 便宜 99% |
| GLM-5 Turbo z-ai/glm-5-turbo | $0.0119 / $0.0396 | $1.20 / $4.00 | 便宜 99% |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 / $0.0030 | $0.0750 / $0.3000 | 便宜 99% |
| Ministral 3B mistralai/ministral-3-3b-instruct | $0.0010 / $0.0010 | $0.1000 / $0.1000 | 便宜 99% |
| Ministral 14B 3.0 mistralai/ministral-3-14b-instruct | $0.0020 / $0.0020 | $0.2000 / $0.2000 | 便宜 99% |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.0075 / $0.0375 | $0.7500 / $3.75 | 便宜 99% |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0150 / $0.0900 | $1.50 / $9.00 | 便宜 99% |
| Meta: Muse Wonder meta-llama/muse-wonder | $0.0400 / $0.2000 | $4.00 / $20.00 | 便宜 99% |
| GLM 5.3 z-ai/glm-5.3 | $0.00070 / $0.0141 | $0.0699 / $1.40 | 便宜 98% |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0020 / $0.0121 | $0.2000 / $1.20 | 便宜 98% |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0026 / $0.0039 | $0.2600 / $0.3800 | 便宜 98% |
| NVIDIA Nemotron Nano 12B v2 VL BF16 nvidia/nemotron-nano-12b-v2 | $0.0022 / $0.0065 | $0.2000 / $0.6000 | 便宜 98% |
| GLM 5.1 z-ai/glm-5.1 | $0.0152 / $0.0479 | $1.40 / $4.40 | 便宜 98% |
| GLM 5.3 Flash z-ai/glm-5.3-flash | $0.00033 / $0.0011 | $0.0285 / $0.0923 | 便宜 98% |
| Ministral 3 8B mistralai/ministral-3-8b-instruct | $0.0017 / $0.0017 | $0.1500 / $0.1500 | 便宜 98% |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0338 / $0.1063 | $2.80 / $8.80 | 便宜 98% |
| Magistral Small 2509 mistralai/magistral-small-2509 | $0.0069 / $0.0208 | $0.5000 / $1.50 | 便宜 98% |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.0641 / $0.3205 | $4.00 / $20.00 | 便宜 98% |
| GPT OSS Safeguard 120B openai/gpt-oss-safeguard-120b | $0.0024 / $0.0096 | $0.1500 / $0.6000 | 便宜 98% |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.0889 / $0.4444 | $5.00 / $25.00 | 便宜 98% |
| Claude Opus 5 anthropic/claude-opus-5 | $0.0900 / $0.4500 | $5.00 / $25.00 | 便宜 98% |
| NVIDIA Nemotron Nano 9B v2 nvidia/nemotron-nano-9b-v2 | $0.0011 / $0.0043 | $0.0600 / $0.2300 | 便宜 98% |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0378 / $0.2267 | $2.00 / $12.00 | 便宜 98% |
| Devstral 2 123B mistralai/devstral-2-123b | $0.0077 / $0.0384 | $0.4000 / $2.00 | 便宜 98% |
| OpenAI: GPT-6.1 Terra openai/gpt-6.1-terra | $0.0196 / $0.0982 | $1.00 / $5.00 | 便宜 98% |
| Claude Opus 4.5 anthropic/claude-opus-4.5 | $0.0985 / $0.4925 | $5.00 / $25.00 | 便宜 98% |
| GPT-6 Sol openai/gpt-6-sol | $0.0403 / $0.2013 | $2.00 / $10.00 | 便宜 97% |
| Palmyra Vision 7B writer/palmyra-vision-7b | $0.0034 / $0.0134 | $0.1500 / $0.6000 | 便宜 97% |
| GPT-4o Mini openai/gpt-4o-mini | $0.0035 / $0.0138 | $0.1500 / $0.6000 | 便宜 97% |
| GPT-4o openai/gpt-4o | $0.0589 / $0.2355 | $2.50 / $10.00 | 便宜 97% |
| GPT-5.4 openai/gpt-5.4 | $0.0608 / $0.3648 | $2.50 / $15.00 | 便宜 97% |
| GPT-5.5 openai/gpt-5.5 | $0.1250 / $0.7500 | $5.00 / $30.00 | 便宜 97% |
| GPT-6 Luna openai/gpt-6-luna | $0.0030 / $0.0149 | $0.1000 / $0.5000 | 便宜 97% |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0045 / $0.0180 | $0.1500 / $0.6000 | 便宜 97% |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0035 / $0.1206 | $0.1150 / $4.00 | 便宜 96% |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0910 / $0.0910 | $0.4500 / $3.50 | 便宜 96% |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0179 / $0.1289 | $0.5000 / $3.60 | 便宜 96% |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.1579 / $0.7897 | $4.00 / $20.00 | 便宜 96% |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0819 / $0.4094 | $2.00 / $10.00 | 便宜 95% |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.0904 / $0.4520 | $2.00 / $10.00 | 便宜 95% |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0014 / $0.0060 | $0.0300 / $0.1300 | 便宜 95% |
| Mistral Large mistralai/mistral-large | $0.0928 / $0.2784 | $2.00 / $6.00 | 便宜 95% |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.0839 / $0.6711 | $1.75 / $14.00 | 便宜 95% |
| Claude Fable 5 anthropic/claude-fable-5 | $0.4800 / $2.40 | $10.00 / $50.00 | 便宜 95% |
| Qwen 3.6 35B A3B qwen/qwen3-6-35b-a3b | $0.0049 / $0.0485 | $0.1000 / $1.00 | 便宜 95% |
| Qwen 3.8 Max qwen/qwen-3-8-max | $0.1212 / $0.3638 | $2.50 / $7.50 | 便宜 95% |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0159 / $0.1323 | $0.3250 / $2.70 | 便宜 95% |
| Gemma 4 E2B google/gemma-4-e2b | $0.0020 / $0.0040 | $0.0400 / $0.0800 | 便宜 95% |
| Mistral Large 3 mistralai/mistral-large-3 | $0.0248 / $0.0742 | $0.5000 / $1.50 | 便宜 95% |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.0999 / $0.4995 | $2.00 / $10.00 | 便宜 95% |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.2592 / $1.30 | $5.00 / $25.00 | 便宜 94% |
| GPT-5.2 openai/gpt-5.2 | $0.0927 / $0.7420 | $1.75 / $14.00 | 便宜 94% |
| Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | $0.1099 / $0.5495 | $2.00 / $10.00 | 便宜 94% |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0581 / $0.2907 | $1.00 / $5.00 | 便宜 94% |
| MiniMax M3 minimax/minimax-m3 | $0.0180 / $0.0719 | $0.3000 / $1.20 | 便宜 94% |
| Grok 4.7 x-ai/grok-4.7 | $0.1200 / $0.3600 | $2.00 / $6.00 | 便宜 94% |
| Gemini 3.1 Pro google/gemini-3.1-pro | $0.1200 / $0.7200 | $2.00 / $12.00 | 便宜 94% |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0192 / $0.0769 | $0.3000 / $1.20 | 便宜 93% |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0071 / $0.0355 | $0.1000 / $0.5000 | 便宜 92% |
| Tencent HY3 tencent/hy3 | $0.0095 / $0.0380 | $0.1320 / $0.5280 | 便宜 92% |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $0.7868 / $3.93 | $10.00 / $50.00 | 便宜 92% |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.1593 / $0.7963 | $2.00 / $10.00 | 便宜 92% |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0733 / $0.4401 | $0.7500 / $4.50 | 便宜 90% |
| GPT 5 Nano openai/gpt-5-nano | $0.0059 / $0.0471 | $0.0500 / $0.4000 | 便宜 88% |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.11 / $24.64 | $30.00 / $180.00 | 便宜 86% |
| Grok 4.20 Multi-Agent Beta x-ai/grok-4.20-multi-agent-beta | $0.1750 / $0.3500 | $1.25 / $2.50 | 便宜 86% |
| Grok 4.20 Beta x-ai/grok-4.20-beta | $0.1750 / $0.3500 | $1.25 / $2.50 | 便宜 86% |
| Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.0145 / $0.0465 | $0.1000 / $0.3200 | 便宜 85% |
| MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.0208 / $0.0416 | $0.1400 / $0.2800 | 便宜 85% |
| MiniMax M3.1 Flash minimax/minimax-m3-1-flash | $0.0225 / $0.0900 | $0.1500 / $0.6000 | 便宜 85% |
| Grok 4.6 x-ai/grok-4.6 | $0.3564 / $1.07 | $2.00 / $6.00 | 便宜 82% |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $0.5505 / $2.75 | $3.00 / $15.00 | 便宜 81% |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0851 / $0.1701 | $0.4350 / $0.8700 | 便宜 80% |
| GPT 5.4 Nano openai/gpt-5.4-nano | $0.0396 / $0.2475 | $0.2000 / $1.25 | 便宜 80% |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0182 / $0.0364 | $0.0910 / $0.1820 | 便宜 80% |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3000 / $2.40 | $1.25 / $10.00 | 便宜 76% |
| GPT 5 Mini openai/gpt-5-mini | $0.0612 / $0.4900 | $0.2500 / $2.00 | 便宜 75% |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4375 / $3.50 | $1.75 / $14.00 | 便宜 75% |
| Gemma 4 26B A4B Uncensored (E2EE) google/e2ee-gemma-4-26b-a4b-uncensored-p | $0.0565 / $0.2618 | $0.1900 / $0.8800 | 便宜 70% |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.0599 / $0.3593 | $0.2000 / $1.20 | 便宜 70% |
| Gemini 3.6 Flash google/gemini-3-6-flash | $0.2249 / $1.12 | $0.7500 / $3.75 | 便宜 70% |
| Gemini 3.5 Flash Lite google/gemini-3-5-flash-lite | $0.0900 / $0.7500 | $0.3000 / $2.50 | 便宜 70% |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.6000 / $3.60 | $2.00 / $12.00 | 便宜 70% |
| GPT-5.5 Pro openai/gpt-5.5-pro | $9.00 / $54.00 | $30.00 / $180.00 | 便宜 70% |
| Qwen 3.6 35B A3B (E2EE) qwen/e2ee-qwen3-6-35b-a3b | $0.0553 / $0.3587 | $0.1820 / $1.18 | 便宜 69% |
| Qwen3 VL 235B qwen/qwen3-vl-235b-a22b-thinking | $0.0638 / $0.5775 | $0.2100 / $1.90 | 便宜 69% |
| Mistral Small 4 mistralai/mistral-small-4 | $0.0469 / $0.1875 | $0.1500 / $0.6000 | 便宜 68% |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0473 / $0.3151 | $0.1500 / $1.00 | 便宜 68% |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0300 / $0.0900 | $0.1700 / $0.2500 | 便宜 67% |
| GPT OSS 120B openai/e2ee-gpt-oss-120b-p | $0.0427 / $0.2136 | $0.1300 / $0.6500 | 便宜 67% |
| Venice Uncensored 1.2 venice/uncensored-1.2 | $0.0659 / $0.2967 | $0.2000 / $0.9000 | 便宜 67% |
| Venice Role Play Uncensored venice/uncensored-role-play | $0.1648 / $0.6593 | $0.5000 / $2.00 | 便宜 67% |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.1648 / $0.6593 | $0.5000 / $2.00 | 便宜 67% |
| Aion 3.0 aion-labs/aion-3-0 | $1.05 / $2.10 | $3.00 / $6.00 | 便宜 65% |
| Aion 2.0 aion-labs/aion-2.0 | $0.2800 / $0.5600 | $0.8000 / $1.60 | 便宜 65% |
| Aion 3.5 aion-labs/aion-3-5 | $1.31 / $2.63 | $3.75 / $7.50 | 便宜 65% |
| Aion 3.0 Mini aion-labs/aion-3-0-mini | $0.2450 / $0.4900 | $0.7000 / $1.40 | 便宜 64% |
| Aion 3.5 Mini aion-labs/aion-3-5-mini | $0.3063 / $0.6125 | $0.8750 / $1.75 | 便宜 64% |
| GLM 5.1 E2EE z-ai/e2ee-glm-5.1 | $0.4400 / $1.66 | $1.40 / $4.40 | 便宜 62% |
| Seed 2.1 Turbo bytedance/seed-2-1-turbo | $0.1976 / $0.9881 | $0.5000 / $2.50 | 便宜 60% |
| Claude Opus 5 (Fast) anthropic/claude-opus-5-fast | $3.98 / $19.90 | $10.00 / $50.00 | 便宜 60% |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0299 / $0.0798 | $0.0750 / $0.2000 | 便宜 60% |
| GLM 4.7 Flash Heretic z-ai/glm-4.7-flash-heretic | $0.0279 / $0.1597 | $0.0700 / $0.4000 | 便宜 60% |
| Z.ai: GLM 5.3 FlashX z-ai/glm-5.3-flashx | $0.1480 / $0.5000 | $0.3700 / $1.25 | 便宜 60% |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $0.8000 / $4.00 | $2.00 / $10.00 | 便宜 60% |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $0.8000 / $4.00 | $2.00 / $10.00 | 便宜 60% |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.0400 / $0.2000 | $0.1000 / $0.5000 | 便宜 59% |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.4896 / $1.63 | $1.20 / $4.00 | 便宜 59% |
| GLM 5.2 E2EE z-ai/e2ee-glm-5-2-p | $0.7851 / $2.58 | $1.75 / $5.75 | 便宜 55% |
| Hermes 3 Llama 3.1 405b nousresearch/hermes-3-llama-3.1-405b | $0.4496 / $0.4496 | $1.00 / $1.00 | 便宜 55% |
| inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.0338 / $0.1013 | $0.0750 / $0.2250 | 便宜 55% |
| MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.2160 / $0.8100 | $0.4800 / $1.80 | 便宜 55% |
| Sakana: Fugu Max sakana/fugu-max | $0.9200 / $2.76 | $2.00 / $6.00 | 便宜 54% |
| Sakana: Fugu Ultra v2 sakana/fugu-ultra-v2 | $2.30 / $13.80 | $5.00 / $30.00 | 便宜 54% |
| Claude Opus 4.8 Fast anthropic/claude-opus-4.8-fast | $4.67 / $23.34 | $10.00 / $50.00 | 便宜 53% |
| Gemma 4 Uncensored google/gemma-4-uncensored | $0.0780 / $0.2399 | $0.1625 / $0.5000 | 便宜 52% |
| Qwen 3 Coder 480B Turbo qwen/qwen3-coder-turbo | $0.2100 / $0.9000 | $0.3500 / $1.50 | 便宜 39% |
| MiMo-V2.5 xiaomi/mimo-v2-5 | $0.2440 / $1.22 | $0.4000 / $2.00 | 便宜 39% |
| Mercury 2 inception/mercury-2 | $0.1525 / $0.4575 | $0.2500 / $0.7500 | 便宜 38% |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1525 / $0.5490 | $0.2500 / $0.9000 | 便宜 38% |
| Abliterated Large Flash abliteration-ai/abliteration-abliterated-model-large-flash | $0.7875 / $1.57 | $1.25 / $2.50 | 便宜 37% |
| DeepSeek V4 Flash E2EE deepseek/e2ee-deepseek-v4-flash | $0.1147 / $0.2350 | $0.1820 / $0.3730 | 便宜 37% |
| DeepSeek V4 Flash 0731 Fast deepseek/deepseek-v4-flash-0731-fast | $0.2205 / $0.4410 | $0.3500 / $0.7000 | 便宜 37% |
| Meta: Muse Spark Open meta-llama/muse-spark-open | $0.8000 / $2.72 | $1.25 / $4.25 | 便宜 36% |
| Qwen 2.5 7B qwen/e2ee-qwen-2-5-7b-p | $0.0325 / $0.0845 | $0.0500 / $0.1300 | 便宜 35% |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $2.68 / $13.40 | $4.00 / $20.00 | 便宜 32% |
| Venice Uncensored 1.1 venice/uncensored | $0.1344 / $0.6048 | $0.2000 / $0.9000 | 便宜 32% |
| Abliterated Large V2 abliteration-ai/abliteration-abliterated-model-large-v2 | $2.07 / $3.45 | $3.00 / $5.00 | 便宜 31% |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.6965 / $1.39 | $1.00 / $2.00 | 便宜 30% |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0840 / $0.3500 | $0.1200 / $0.5000 | 便宜 30% |
| Kimi K3 Fast moonshotai/kimi-k3-fast-api | $3.15 / $15.75 | $4.50 / $22.50 | 便宜 30% |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0350 / $0.2310 | $0.0500 / $0.3300 | 便宜 29% |
| MiniMax M3 Preview minimax/minimax-m3-preview | $0.2100 / $0.8400 | $0.3000 / $1.20 | 便宜 29% |
| Kimi K2 moonshotai/kimi-k2 | $0.3990 / $1.61 | $0.5700 / $2.30 | 便宜 29% |
| Qwen3.7 Max qwen/qwen3.7-max | $1.89 / $5.63 | $2.70 / $8.05 | 便宜 29% |
| Qwen 3.6 Plus Uncensored qwen/qwen3.6-plus-uncensored | $0.4625 / $2.77 | $0.6250 / $3.75 | 便宜 26% |
| GLM 4.7 Thinking (Morpheus Web) z-ai/glm-4.7-thinking:web | $0.3375 / $1.50 | $0.4500 / $2.00 | 便宜 25% |
| OpenAI GPT OSS 120B (Morpheus Web) openai/gpt-oss-120b:web | $0.0525 / $0.2250 | $0.0700 / $0.3000 | 便宜 24% |
| GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.58 / $9.49 | $2.00 / $12.00 | 便宜 20% |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | $0.1725 / $0.5174 | $0.2156 / $0.6468 | 便宜 20% |
| Mercury 3 inception/mercury-3 | $0.0800 / $0.2800 | $0.1000 / $0.3500 | 便宜 19% |
| NVIDIA Nemotron 3.5 Lightning 30B nvidia/nemotron-3-5-lightning-30b-a3b | $0.0640 / $0.1600 | $0.0700 / $0.2000 | 便宜 18% |
| Trinity Large Thinking arcee-ai/trinity-large-thinking | $0.2344 / $0.8438 | $0.3000 / $1.00 | 便宜 16% |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0380 / $0.1425 | $0.0400 / $0.1500 | 便宜 4% |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.6930 / $2.08 | $0.7000 / $2.10 | 便宜 1% |
| ByteDance Seed: Seed-2.0-Code bytedance/seed-2.0-code | $0.4950 / $2.97 | $0.5000 / $3.00 | 便宜 1% |
| Fireworks: Ember-1 fireworks/ember-1 | $2.97 / $14.85 | $3.00 / $15.00 | 便宜 1% |
| Particle AI: Particle-1 particle-ai/particle-1 | $0.0495 / $0.4950 | $0.0500 / $0.5000 | 便宜 1% |
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.1485 / $0.4950 | $0.1500 / $0.5000 | 便宜 1% |
| Reflection: Beam 1.0 501B A23B reflection/beam-1.0-501b-a23b | $0.2475 / $0.9900 | $0.2500 / $1.00 | 便宜 1% |
| Cohere: Command A+ cohere/command-a-plus | $0.2970 / $1.49 | $0.3000 / $1.50 | 便宜 1% |
| Elorian: Glimpse elorian/glimpse | $0.5940 / $2.97 | $0.6000 / $3.00 | 便宜 1% |
| Pareto 26.9 unbiased/pareto-26.9 | $2.48 / $7.42 | $2.50 / $7.50 | 便宜 1% |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $3.96 / $11.88 | $4.00 / $12.00 | 便宜 1% |
| Moondream: Moondream 3.1 moondream/moondream3.1-9b-a2b | $0.2970 / $2.48 | $0.3000 / $2.50 | 便宜 0% |
| Moondream: Moondream 3 Preview moondream/moondream3-preview | $0.2970 / $2.48 | $0.3000 / $2.50 | 便宜 0% |
| OpenAI: GPT-6.1 Terra Pro openai/gpt-6.1-terra-pro | $0.9900 / $4.95 | $1.00 / $5.00 | 便宜 0% |
| MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | $4.31 / $8.61 | $4.35 / $8.70 | 便宜 0% |
| LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b | $0.0495 / $0.6930 | $0.0500 / $0.7000 | 便宜 0% |
| Meta: Muse Glimmer 30B meta-llama/muse-glimmer-30b | $0.2970 / $1.19 | $0.3000 / $1.20 | 便宜 0% |
| GLM 4.7 Thinking z-ai/glm-4.7-thinking | $0.4500 / $2.00 | $0.4500 / $2.00 | 相同 |
| DeepSeek V4.1 Flash Uncensored deepseek/deepseek-v4.1-flash-uncensored | $0.0900 / $1.00 | $0.0450 / $0.5000 | 贵 100% |
| GLM-5.3 Flash Uncensored z-ai/glm-5.3-flash-uncensored | $0.1500 / $0.5000 | $0.0285 / $0.0923 | 贵 440% |
价格为每 100 万输入 / 输出 token 的美元价（$）。比较时输入与输出按 1:3 加权。UberLLM 的价格是当前市场上的最低价；提供商价格是每个模型的官方标价，也就是你通过 LiteLLM 付给提供商的价格。两边价格均于 2026年11月2日 核对。双方都在卖的模型全部列出，包括这里价格相同或更贵的模型。
LiteLLM 是什么
一个开源的 AI 网关（代理服务器和 Python SDK），您可以自行运行，通过一个 OpenAI 风格的 API 和您自己的提供商 key 调用多个模型提供商。它增加了虚拟 key、预算、支出跟踪、负载均衡和故障转移。
怎么付费
开源网关是免费的；您在自己的服务器上运行它，并直接向每个模型提供商付费。企业版通过销售提供 SSO、审计日志和支持，价格定制。
UberLLM 是什么
一个 AI 模型的 API 市场。每个请求都会发给该模型最便宜且正常工作的卖家，只需一个兼容 OpenAI 和 Anthropic 的密钥。
怎么付费
按用量付费，价格就是每个模型标出的价格，每个请求不额外加钱。只有充值时才收取 5.5% + $0.50 的银行卡手续费。生成失败不收费。
选 UberLLM，如果
想用一个密钥、以实时最低价调用聊天、图片、视频和音乐模型，并继续使用现有 OpenAI 或 Anthropic SDK 的开发者。
选 LiteLLM，如果
希望在自己的云端（甚至气隙环境）运行自己的网关、保留其现有的提供商合同和 key，并自行控制 key、预算和路由的工程团队。
LiteLLM 能做而 UberLLM 不能做的
- 自托管，包括气隙环境设置
- 使用您自己的提供商 key 和合同
- 您控制的虚拟 key、团队预算和速率限制
- 企业版 SSO、审计日志和定制 SLA
改一行就能切换
把你正在用的 SDK 指向 UberLLM 就行。同一个密钥就能用聊天、图片、视频、音乐和语音。
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",
)常见问题
UberLLM 是 LiteLLM 的替代品吗？
部分是。两者都为您提供一个跨多个模型的、与 OpenAI 兼容和与 Anthropic 兼容的 API。LiteLLM 是一个您自行托管并连接到您自己的提供商账户的网关；UberLLM 是一个按使用量付费的托管服务，因此您无需运行服务器或持有提供商 key。
UberLLM 与 LiteLLM 有何不同？
使用 LiteLLM，您运行代理并直接向每个提供商付费。使用 UberLLM，您充值预付费额度（最低 $5，仅在充值时收取 5.5% + $0.50 的银行卡手续费），按每个模型显示的价格付费，不收取每请求费用，并且每个请求都会发送给最便宜且健康的卖家。失败的生成不收取任何费用，并且您可以为每个请求设置价格上限。UberLLM 没有自托管版本。
我可以同时使用 LiteLLM 和 UberLLM 吗？
由于 UberLLM 暴露了与 OpenAI 兼容的 endpoint，它可以作为与 OpenAI 兼容的 endpoint 添加到 LiteLLM 这样的网关后面。请查阅 LiteLLM 的文档，了解如何添加自定义的与 OpenAI 兼容的提供商。