为从 OpenRouter 迁移过来的团队准备的、兼容 OpenAI 的大模型 API
按 UberLLM 当前最低价计算，150 个模型中有 150 个比 OpenRouter 便宜，最多便宜 99%（2026年11月2日 核对）。
UberLLM 是兼容 OpenAI 和 Anthropic 的大模型 API，提供 237 个文本模型。请求会通过市场转给第三方提供商，按 token 计费，不额外加费用。从 OpenRouter 迁移，只需改 Base URL 和 API 密钥。
逐个模型比价格
| 模型 | UberLLM 输入 / 输出 | OpenRouter 输入 / 输出 | 在 UberLLM 上 |
|---|---|---|---|
| GLM-5.2 z-ai/glm-5.2 | $0.00056 / $0.0022 | $0.0060 / $6.80 | 便宜 99% |
| GPT-OSS 120B openai/gpt-oss-120b | $0.000069 / $0.00030 | $0.1500 / $0.6000 | 便宜 99% |
| GPT-OSS 20B openai/gpt-oss-20b | $0.000018 / $0.000089 | $0.0300 / $0.1300 | 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% |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0021 / $0.0062 | $2.00 / $6.00 | 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 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% |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0022 / $0.0044 | $1.60 / $3.20 | 便宜 99% |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.00098 / $0.0057 | $0.6000 / $3.50 | 便宜 99% |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0013 / $0.0068 | $0.6500 / $3.41 | 便宜 99% |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.00018 / $0.0014 | $0.0450 / $0.5000 | 便宜 99% |
| GLM 5.3 z-ai/glm-5.3 | $0.00070 / $0.0141 | $0.0800 / $3.60 | 便宜 99% |
| GLM-4.7 z-ai/glm-4.7 | $0.0028 / $0.0102 | $0.6000 / $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% |
| Gemma 3 27B google/gemma-3-27b-it | $0.00079 / $0.0020 | $0.0800 / $0.3500 | 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% |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.0350 / $0.1750 | $5.00 / $25.00 | 便宜 99% |
| GPT-6 Astra openai/gpt-6-astra | $0.0752 / $0.3762 | $10.00 / $50.00 | 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 26B A4B IT google/gemma-4-26b-a4b-it | $0.00045 / $0.0015 | $0.0620 / $0.1860 | 便宜 99% |
显示全部 150 个模型
| 模型 | UberLLM 输入 / 输出 | OpenRouter 输入 / 输出 | 在 UberLLM 上 |
|---|---|---|---|
| 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 | $0.0165 / $0.0496 | $2.00 / $6.00 | 便宜 99% |
| GLM-4.6 z-ai/glm-4.6 | $0.0042 / $0.0170 | $0.5000 / $2.00 | 便宜 99% |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.0012 / $0.0036 | $0.2000 / $0.4000 | 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 minimax/minimax-m2 | $0.0023 / $0.0093 | $0.2550 / $1.02 | 便宜 99% |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0014 / $0.0045 | $0.1500 / $0.4700 | 便宜 99% |
| GLM 4.5 z-ai/glm-4.5 | $0.0059 / $0.0216 | $0.6000 / $2.20 | 便宜 99% |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0027 / $0.0094 | $0.2700 / $0.9500 | 便宜 99% |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.00049 / $0.0015 | $0.0500 / $0.1500 | 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% |
| 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% |
| 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% |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0082 / $0.0412 | $0.8250 / $4.13 | 便宜 99% |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0030 / $0.0250 | $0.3000 / $2.50 | 便宜 99% |
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0050 / $0.0300 | $0.5000 / $3.00 | 便宜 99% |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0150 / $0.0900 | $1.50 / $9.00 | 便宜 99% |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0026 / $0.0039 | $0.2600 / $0.3800 | 便宜 98% |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0050 / $0.0250 | $0.6000 / $2.40 | 便宜 98% |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.0315 / $0.1575 | $3.00 / $15.00 | 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% |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0338 / $0.1063 | $2.80 / $8.80 | 便宜 98% |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 / $0.0030 | $0.0600 / $0.2400 | 便宜 98% |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0045 / $0.0179 | $0.3000 / $1.20 | 便宜 98% |
| OpenAI: GPT-6.1 Terra openai/gpt-6.1-terra | $0.0197 / $0.0983 | $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 | $0.0405 / $0.2025 | $2.00 / $10.00 | 便宜 97% |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0408 / $0.2450 | $2.00 / $12.00 | 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 | $0.0610 / $0.3661 | $2.50 / $15.00 | 便宜 97% |
| Claude Opus 5 anthropic/claude-opus-5 | $0.1250 / $0.6249 | $5.00 / $25.00 | 便宜 97% |
| GPT-5.5 openai/gpt-5.5 | $0.1250 / $0.7500 | $5.00 / $30.00 | 便宜 97% |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.1270 / $0.6349 | $5.00 / $25.00 | 便宜 97% |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.1158 / $0.5792 | $4.00 / $20.00 | 便宜 97% |
| GPT-6 Luna openai/gpt-6-luna | $0.0030 / $0.0149 | $0.1000 / $0.5000 | 便宜 97% |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0035 / $0.1207 | $0.1150 / $4.00 | 便宜 96% |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0650 / $0.3250 | $2.00 / $10.00 | 便宜 96% |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0950 / $0.0950 | $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% |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0077 / $0.0464 | $0.2000 / $1.20 | 便宜 96% |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.1605 / $0.8023 | $4.00 / $20.00 | 便宜 95% |
| Grok 4.7 x-ai/grok-4.7 | $0.0840 / $0.2520 | $2.00 / $6.00 | 便宜 95% |
| MiniMax M3 minimax/minimax-m3 | $0.0127 / $0.0507 | $0.3000 / $1.20 | 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% |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0159 / $0.1323 | $0.4500 / $2.70 | 便宜 95% |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.0997 / $0.4985 | $2.00 / $10.00 | 便宜 95% |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.2535 / $1.27 | $5.00 / $25.00 | 便宜 94% |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0507 / $0.2537 | $1.00 / $5.00 | 便宜 94% |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.1026 / $0.5130 | $2.00 / $10.00 | 便宜 94% |
| Claude Fable 5 anthropic/claude-fable-5 | $0.5136 / $2.57 | $10.00 / $50.00 | 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 | $0.1062 / $0.5310 | $2.00 / $10.00 | 便宜 94% |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.1039 / $0.8312 | $1.75 / $14.00 | 便宜 94% |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0198 / $0.0794 | $0.3000 / $1.20 | 便宜 93% |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0072 / $0.0362 | $0.1000 / $0.5000 | 便宜 92% |
| Tencent HY3 tencent/hy3 | $0.0097 / $0.0389 | $0.1320 / $0.5280 | 便宜 92% |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $0.8160 / $4.08 | $10.00 / $50.00 | 便宜 91% |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0733 / $0.4401 | $0.7500 / $4.50 | 便宜 90% |
| Grok 4.6 x-ai/grok-4.6 | $0.2196 / $0.6587 | $2.00 / $6.00 | 便宜 89% |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.11 / $24.64 | $30.00 / $180.00 | 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 | $0.0210 / $0.0420 | $0.1400 / $0.2800 | 便宜 85% |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $0.5835 / $2.92 | $3.00 / $15.00 | 便宜 80% |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0859 / $0.1717 | $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 | $0.0181 / $0.0363 | $0.0910 / $0.1820 | 便宜 80% |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.1400 / $0.4200 | $0.7000 / $2.10 | 便宜 80% |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.1500 / $0.7500 | $0.7500 / $3.75 | 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 Nano openai/gpt-5-nano | $0.0125 / $0.1000 | $0.0500 / $0.4000 | 便宜 75% |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4375 / $3.50 | $1.75 / $14.00 | 便宜 75% |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.5960 / $2.98 | $2.00 / $10.00 | 便宜 70% |
| GPT-5.5 Pro openai/gpt-5.5-pro | $8.98 / $53.89 | $30.00 / $180.00 | 便宜 70% |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0473 / $0.3151 | $0.1400 / $1.00 | 便宜 68% |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0300 / $0.0900 | $0.1700 / $0.2500 | 便宜 67% |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.6800 / $4.08 | $2.00 / $12.00 | 便宜 65% |
| Aion 2.0 aion-labs/aion-2.0 | $0.2800 / $0.5600 | $0.8000 / $1.60 | 便宜 65% |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0299 / $0.0798 | $0.0750 / $0.2000 | 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% |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.4896 / $1.63 | $1.20 / $4.00 | 便宜 59% |
| 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% |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.1648 / $0.6593 | $0.3200 / $1.28 | 便宜 48% |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.0545 / $0.2724 | $0.1000 / $0.5000 | 便宜 45% |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1525 / $0.5490 | $0.2900 / $1.00 | 便宜 45% |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $1.10 / $5.49 | $2.00 / $10.00 | 便宜 45% |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $1.10 / $5.50 | $2.00 / $10.00 | 便宜 45% |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0305 / $0.2010 | $0.0509 / $0.3350 | 便宜 40% |
| Mercury 2 inception/mercury-2 | $0.1525 / $0.4575 | $0.2500 / $0.7500 | 便宜 38% |
| Mercury 3 inception/mercury-3 | $0.0620 / $0.2170 | $0.1000 / $0.3500 | 便宜 37% |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $2.68 / $13.40 | $4.00 / $20.00 | 便宜 32% |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0840 / $0.3500 | $0.1200 / $0.5000 | 便宜 30% |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.7000 / $1.40 | $1.00 / $2.00 | 便宜 30% |
| Kimi K2 moonshotai/kimi-k2 | $0.3990 / $1.61 | $0.5700 / $2.30 | 便宜 29% |
| 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% |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.1600 / $0.9600 | $0.2000 / $1.20 | 便宜 19% |
| Qwen3.7 Max qwen/qwen3.7-max | $1.35 / $4.03 | $1.48 / $4.42 | 便宜 8% |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0380 / $0.1425 | $0.0400 / $0.1500 | 便宜 4% |
| 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 / $0.7000 | 便宜 0% |
价格为每 100 万输入 / 输出 token 的美元价（$）。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；OpenRouter 的价格来自其公开的模型列表。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。 OpenRouter 是其所有者的商标；两者是相互独立的产品。
迁移示例
python
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1", # was: https://openrouter.ai/api/v1
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}],
)UberLLM 对比 OpenRouter
| 功能 | UberLLM | OpenRouter |
|---|---|---|
| OpenAI Chat Completions API，一个密钥用所有模型 | 是 | 是 |
| Anthropic Messages API（可作为 Claude Code 的后端） | 是，地址为 /v1/messages | 是 |
| 媒体 API | 图片、视频、音乐、文字转语音、语音转文字 | 图片、视频、文字转语音、语音转文字 |
| 请求怎么定价 | 实时市场价，不额外加费用：按 UberLLM 当前最低价计算，150 个模型中有 150 个更便宜，最多便宜 99% | 提供商的标价 |
| 充值时的手续费 | 另加 5.5% + $0.50（充值 $25 实付 $26.88） | Standard 套餐 5.5%，Business 套餐 8% |
| 使用你自己的提供商密钥 | 不收费 | 每月 $25,000（按标价计）以内免费，超出部分收 5% |
| 每个 API 密钥的消费上限 | 有：可按天、按月或总额设置 | 有：每个密钥可设额度上限 |
OpenRouter 的信息来自其公开的价格页面和文档，2026年10月21日 核对。两者是相互独立的产品。OpenRouter 是其所有者的商标。 查看所有对比.
常见问题
UberLLM 能直接替换 OpenRouter 吗？
UberLLM 在其 Base URL 上接收 OpenAI Chat Completions 请求，所以为 OpenRouter 或 OpenAI 写的代码，只需换一个 base_url 和 api_key。Anthropic SDK 的请求在 /v1/messages 接收。
UberLLM 和 OpenRouter 有什么不同？
两者都是一个 API 密钥用多个模型。UberLLM 还接收独立卖家提供的算力，作为报价发布在市场上。每个请求都会发给所选模型的一个可用第三方提供商。如果提供商在开始回答前就出错，请求会自动重试。重试后仍然失败的请求不收费。每个请求的费用就是提供商收的价格，每一笔请求和费用都列在“活动”里。UberLLM 不在提供商价格上加钱；充值时收取 5.5% + $0.50 的银行卡手续费。
UberLLM 支持同样的模型吗？
模型库包括 GPT、Claude、Gemini、DeepSeek、GLM、Qwen、Llama、Mistral 和 Kimi 等模型。模型列表会显示当前可用的模型。
怎么从 OpenRouter 迁移到 UberLLM？
把 base_url 设为 https://api.uberllm.dev/v1，并使用 UberLLM 的 API 密钥。模型 id 采用 provider/model 的格式。请确认你用到的每个模型都在 UberLLM 的模型库里。