Giá API LLM: so sánh 252 model
Rẻ hơn OpenRouter ở 134 trên 150 model, rẻ hơn tới 99%, theo giá tốt nhất hiện tại của UberLLM (kiểm tra ngày 5 tháng 11, 2026).
Giá API trực tiếp theo từng model cho GPT, Claude, Gemini, DeepSeek, GLM, Qwen, Llama, Mistral, Kimi và các model khác, tính cho 1M token input và output. Tất cả model đều dùng chung một API key, và UberLLM không cộng thêm phí vào các mức giá này.
Một tháng của bạn sẽ tốn bao nhiêu?
Trên UberLLM
$13.47
OpenRouter: $400.00Giá chính thức: $400.00Bạn tiết kiệm $386.53 mỗi tháng
UberLLM vs OpenRouter, từng model một
| Model | UberLLM vào / ra | OpenRouter vào / ra | Trên UberLLM |
|---|---|---|---|
| GLM-5.2 z-ai/glm-5.2 | $0.00052 / $0.0035 | $0.0060 / $6.80 | rẻ hơn 99% |
| GPT-OSS 20B openai/gpt-oss-20b | $0.000018 / $0.000089 | $0.0300 / $0.1300 | rẻ hơn 99% |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | $0.000074 / $0.00030 | $0.0750 / $0.3000 | rẻ hơn 99% |
| GLM 4.5 Air z-ai/glm-4.5-air | $0.00013 / $0.00084 | $0.1300 / $0.8500 | rẻ hơn 99% |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0021 / $0.0063 | $2.00 / $6.00 | rẻ hơn 99% |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.00036 / $0.0014 | $0.3000 / $1.20 | rẻ hơn 99% |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.00018 / $0.00056 | $0.1500 / $0.4700 | rẻ hơn 99% |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0068 / $0.0136 | $1.60 / $3.20 | rẻ hơn 99% |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.00057 / $0.0035 | $0.1400 / $0.8000 | rẻ hơn 99% |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.00069 / $0.0028 | $0.1500 / $0.6000 | rẻ hơn 99% |
| GLM-4.7 z-ai/glm-4.7 | $0.0028 / $0.0102 | $0.6000 / $2.20 | rẻ hơn 99% |
| Kimi K3 moonshotai/kimi-k3 | $0.0017 / $0.0781 | $0.1920 / $16.00 | rẻ hơn 99% |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.00022 / $0.0025 | $0.0450 / $0.5000 | rẻ hơn 99% |
| GLM 4.7 Flash z-ai/glm-4.7-flash | $0.00031 / $0.0020 | $0.0605 / $0.4000 | rẻ hơn 99% |
| GLM-5 z-ai/glm-5 | $0.0053 / $0.0168 | $1.00 / $3.20 | rẻ hơn 99% |
| Gemma 3 27B google/gemma-3-27b-it | $0.00079 / $0.0020 | $0.0800 / $0.3500 | rẻ hơn 99% |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.00046 / $0.00058 | $0.0500 / $0.1000 | rẻ hơn 99% |
| GPT-OSS 120B openai/gpt-oss-120b | $0.000069 / $0.00030 | $0.0120 / $0.0460 | rẻ hơn 99% |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.00090 / $0.0018 | $0.0590 / $0.3000 | rẻ hơn 99% |
| Kimi K2.5 moonshotai/kimi-k2.5 | $0.0040 / $0.0203 | $0.5000 / $2.50 | rẻ hơn 99% |
| GLM-4.6 z-ai/glm-4.6 | $0.0042 / $0.0170 | $0.5000 / $2.00 | rẻ hơn 99% |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.0012 / $0.0036 | $0.2000 / $0.4000 | rẻ hơn 99% |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.00086 / $0.0095 | $0.1000 / $1.10 | rẻ hơn 99% |
| MiniMax M2 minimax/minimax-m2 | $0.0023 / $0.0093 | $0.2550 / $1.02 | rẻ hơn 99% |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0014 / $0.0045 | $0.1500 / $0.4700 | rẻ hơn 99% |
Hiện tất cả 150 model
| Model | UberLLM vào / ra | OpenRouter vào / ra | Trên UberLLM |
|---|---|---|---|
| GLM 4.5 z-ai/glm-4.5 | $0.0059 / $0.0216 | $0.6000 / $2.20 | rẻ hơn 99% |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0027 / $0.0094 | $0.2700 / $0.9500 | rẻ hơn 99% |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.00049 / $0.0015 | $0.0500 / $0.1500 | rẻ hơn 99% |
| Qwen3 32B qwen/qwen3-32b | $0.00079 / $0.0028 | $0.0800 / $0.2800 | rẻ hơn 99% |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0012 / $0.0079 | $0.1200 / $0.8000 | rẻ hơn 99% |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0030 / $0.0099 | $0.3000 / $1.00 | rẻ hơn 99% |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0025 / $0.0149 | $0.2500 / $1.50 | rẻ hơn 99% |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0021 / $0.0188 | $0.2100 / $1.90 | rẻ hơn 99% |
| Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.0059 / $0.0248 | $0.6000 / $2.50 | rẻ hơn 99% |
| Grok 4.3 x-ai/grok-4.3 | $0.0124 / $0.0248 | $1.25 / $2.50 | rẻ hơn 99% |
| GLM-5 Turbo z-ai/glm-5-turbo | $0.0119 / $0.0396 | $1.20 / $4.00 | rẻ hơn 99% |
| GLM 5.3 Flash z-ai/glm-5.3-flash | $0.0015 / $0.0050 | $0.1500 / $0.5000 | rẻ hơn 99% |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0030 / $0.0250 | $0.3000 / $2.50 | rẻ hơn 99% |
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0050 / $0.0300 | $0.5000 / $3.00 | rẻ hơn 99% |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0150 / $0.0900 | $1.50 / $9.00 | rẻ hơn 99% |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0026 / $0.0039 | $0.2600 / $0.3800 | rẻ hơn 98% |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0050 / $0.0250 | $0.6000 / $2.40 | rẻ hơn 98% |
| GLM 5.1 z-ai/glm-5.1 | $0.0145 / $0.0455 | $1.40 / $4.40 | rẻ hơn 98% |
| GPT-6 Astra openai/gpt-6-astra | $0.1072 / $0.5360 | $10.00 / $50.00 | rẻ hơn 98% |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0223 / $0.1341 | $2.00 / $12.00 | rẻ hơn 98% |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0333 / $0.1047 | $2.80 / $8.80 | rẻ hơn 98% |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 / $0.0030 | $0.0600 / $0.2400 | rẻ hơn 98% |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0114 / $0.0568 | $0.8250 / $4.13 | rẻ hơn 98% |
| GLM 5.3 z-ai/glm-5.3 | $0.00052 / $0.0234 | $0.0699 / $1.40 | rẻ hơn 98% |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.0671 / $0.3354 | $4.00 / $20.00 | rẻ hơn 98% |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.00045 / $0.0015 | $0.0270 / $0.0810 | rẻ hơn 98% |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.0110 / $0.0643 | $0.6000 / $3.50 | rẻ hơn 98% |
| GPT-6 Luna openai/gpt-6-luna | $0.0020 / $0.0102 | $0.1000 / $0.5000 | rẻ hơn 97% |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0041 / $0.0247 | $0.2000 / $1.20 | rẻ hơn 97% |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0310 / $0.0931 | $0.1070 / $4.28 | rẻ hơn 97% |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0485 / $0.2426 | $2.00 / $10.00 | rẻ hơn 97% |
| GPT-5.4 openai/gpt-5.4 | $0.0610 / $0.3661 | $2.50 / $15.00 | rẻ hơn 97% |
| GPT-5.5 openai/gpt-5.5 | $0.1250 / $0.7500 | $5.00 / $30.00 | rẻ hơn 97% |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0750 / $0.0750 | $0.4500 / $3.50 | rẻ hơn 97% |
| GPT-4o Mini openai/gpt-4o-mini | $0.0045 / $0.0180 | $0.1500 / $0.6000 | rẻ hơn 97% |
| OpenAI: GPT-6.1 Terra openai/gpt-6.1-terra | $0.0311 / $0.1553 | $1.00 / $5.00 | rẻ hơn 96% |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0203 / $0.1066 | $0.6500 / $3.41 | rẻ hơn 96% |
| GPT-6 Sol openai/gpt-6-sol | $0.0670 / $0.3352 | $2.00 / $10.00 | rẻ hơn 96% |
| Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | $0.0674 / $0.3369 | $2.00 / $10.00 | rẻ hơn 96% |
| Claude Opus 5 anthropic/claude-opus-5 | $0.1750 / $0.8749 | $5.00 / $25.00 | rẻ hơn 96% |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0177 / $0.1278 | $0.5000 / $3.60 | rẻ hơn 96% |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.1965 / $0.9827 | $5.00 / $25.00 | rẻ hơn 96% |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.1970 / $0.9850 | $5.00 / $25.00 | rẻ hơn 96% |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0060 / $0.0239 | $0.1500 / $0.6000 | rẻ hơn 96% |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.1200 / $0.6000 | $3.00 / $15.00 | rẻ hơn 96% |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0807 / $0.2422 | $2.00 / $6.00 | rẻ hơn 95% |
| Grok 4.7 x-ai/grok-4.7 | $0.0909 / $0.2728 | $2.00 / $6.00 | rẻ hơn 95% |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0014 / $0.0059 | $0.0300 / $0.1300 | rẻ hơn 95% |
| Grok 4.5 x-ai/grok-4.5 | $0.0915 / $0.2746 | $2.00 / $6.00 | rẻ hơn 95% |
| Mistral Large mistralai/mistral-large | $0.0928 / $0.2784 | $2.00 / $6.00 | rẻ hơn 95% |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.1997 / $0.9983 | $4.00 / $20.00 | rẻ hơn 95% |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.2498 / $1.25 | $5.00 / $25.00 | rẻ hơn 95% |
| Claude Fable 5 anthropic/claude-fable-5 | $0.5005 / $2.50 | $10.00 / $50.00 | rẻ hơn 94% |
| GPT-5.2 openai/gpt-5.2 | $0.0925 / $0.7401 | $1.75 / $14.00 | rẻ hơn 94% |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $0.5386 / $2.69 | $10.00 / $50.00 | rẻ hơn 94% |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0541 / $0.2707 | $1.00 / $5.00 | rẻ hơn 94% |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.1095 / $0.5474 | $2.00 / $10.00 | rẻ hơn 94% |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0182 / $0.1512 | $0.4500 / $2.70 | rẻ hơn 94% |
| MiniMax M3 minimax/minimax-m3 | $0.0173 / $0.0694 | $0.3000 / $1.20 | rẻ hơn 94% |
| Claude Opus 4.5 anthropic/claude-opus-4.5 | $0.2916 / $1.46 | $5.00 / $25.00 | rẻ hơn 94% |
| GPT-4o openai/gpt-4o | $0.1489 / $0.5955 | $2.50 / $10.00 | rẻ hơn 94% |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.1216 / $0.6080 | $2.00 / $10.00 | rẻ hơn 93% |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0183 / $0.0730 | $0.3000 / $1.20 | rẻ hơn 93% |
| Tencent HY3 tencent/hy3 | $0.0092 / $0.0366 | $0.1320 / $0.5280 | rẻ hơn 93% |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0071 / $0.0356 | $0.1000 / $0.5000 | rẻ hơn 92% |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.1442 / $0.7208 | $2.00 / $10.00 | rẻ hơn 92% |
| Grok 4.6 x-ai/grok-4.6 | $0.1527 / $0.4581 | $2.00 / $6.00 | rẻ hơn 92% |
| Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.0145 / $0.0465 | $0.2000 / $0.5200 | rẻ hơn 91% |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.1570 / $1.26 | $1.75 / $14.00 | rẻ hơn 91% |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0729 / $0.4372 | $0.7500 / $4.50 | rẻ hơn 90% |
| GPT 5 Nano openai/gpt-5-nano | $0.0059 / $0.0471 | $0.0500 / $0.4000 | rẻ hơn 88% |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.10 / $24.58 | $30.00 / $180.00 | rẻ hơn 86% |
| MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.0228 / $0.0456 | $0.1400 / $0.2800 | rẻ hơn 83% |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.1326 / $0.3980 | $0.7000 / $2.10 | rẻ hơn 81% |
| GPT 5.4 Nano openai/gpt-5.4-nano | $0.0387 / $0.2419 | $0.2000 / $1.25 | rẻ hơn 80% |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0858 / $0.1716 | $0.4350 / $0.8700 | rẻ hơn 80% |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.1500 / $0.7500 | $0.7500 / $3.75 | rẻ hơn 80% |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3000 / $2.40 | $1.25 / $10.00 | rẻ hơn 76% |
| GPT 5 Mini openai/gpt-5-mini | $0.0616 / $0.4926 | $0.2500 / $2.00 | rẻ hơn 75% |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0225 / $0.0450 | $0.0910 / $0.1820 | rẻ hơn 75% |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | $0.0539 / $0.1617 | $0.2156 / $0.6468 | rẻ hơn 75% |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4375 / $3.50 | $1.75 / $14.00 | rẻ hơn 75% |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0500 / $0.0750 | $0.1700 / $0.2500 | rẻ hơn 70% |
| GPT-5.5 Pro openai/gpt-5.5-pro | $8.98 / $53.87 | $30.00 / $180.00 | rẻ hơn 70% |
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.0450 / $0.1500 | $0.1500 / $0.5000 | rẻ hơn 70% |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $0.9000 / $4.50 | $3.00 / $15.00 | rẻ hơn 70% |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $1.58 / $7.90 | $4.00 / $20.00 | rẻ hơn 60% |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.7920 / $4.75 | $2.00 / $12.00 | rẻ hơn 60% |
| Z.ai: GLM 5.3 FlashX z-ai/glm-5.3-flashx | $0.1480 / $0.5000 | $0.3700 / $1.25 | rẻ hơn 60% |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1000 / $0.4500 | $0.2900 / $1.00 | rẻ hơn 55% |
| MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.2160 / $0.8100 | $0.4800 / $1.80 | rẻ hơn 55% |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0250 / $0.1650 | $0.0509 / $0.3350 | rẻ hơn 50% |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0781 / $0.5210 | $0.1400 / $1.00 | rẻ hơn 47% |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.1099 / $0.6593 | $0.2000 / $1.20 | rẻ hơn 45% |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.6816 / $2.27 | $1.20 / $4.00 | rẻ hơn 43% |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0430 / $0.1146 | $0.0750 / $0.2000 | rẻ hơn 42% |
| GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.15 / $6.90 | $2.00 / $12.00 | rẻ hơn 42% |
| Mercury 2 inception/mercury-2 | $0.1447 / $0.4342 | $0.2500 / $0.7500 | rẻ hơn 42% |
| Mercury 3 inception/mercury-3 | $0.0590 / $0.2065 | $0.1000 / $0.3500 | rẻ hơn 41% |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.5900 / $1.18 | $1.00 / $2.00 | rẻ hơn 41% |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0840 / $0.3500 | $0.1200 / $0.5000 | rẻ hơn 30% |
| Kimi K2 moonshotai/kimi-k2 | $0.3990 / $1.61 | $0.5700 / $2.30 | rẻ hơn 29% |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.2395 / $0.9581 | $0.3200 / $1.28 | rẻ hơn 25% |
| Aion 2.0 aion-labs/aion-2.0 | $0.6800 / $1.36 | $0.8000 / $1.60 | rẻ hơn 15% |
| Qwen3.7 Max qwen/qwen3.7-max | $1.30 / $3.90 | $1.48 / $4.42 | rẻ hơn 11% |
| Particle AI: Particle-1 particle-ai/particle-1 | $0.0450 / $0.4500 | $0.0500 / $0.5000 | rẻ hơn 9% |
| Z.ai: GLM 5.3 FlashX Legal z-ai/glm-5.3-flashx-legal | $0.3330 / $1.13 | $0.3700 / $1.25 | rẻ hơn 9% |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $1.90 / $9.50 | $2.00 / $10.00 | rẻ hơn 5% |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $1.90 / $9.50 | $2.00 / $10.00 | rẻ hơn 5% |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0400 / $0.1500 | $0.0400 / $0.1500 | Bằng nhau |
| OpenAI: GPT-6.1 Terra Pro openai/gpt-6.1-terra-pro | $1.00 / $5.00 | $1.00 / $5.00 | Bằng nhau |
| MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | $4.35 / $8.70 | $4.35 / $8.70 | Bằng nhau |
| inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.0788 / $0.2362 | $0.0750 / $0.2250 | đắt hơn 5% |
| Cohere: Command A+ cohere/command-a-plus | $0.3150 / $1.57 | $0.3000 / $1.50 | đắt hơn 5% |
| Moondream: Moondream 3.1 moondream/moondream3.1-9b-a2b | $0.3150 / $2.63 | $0.3000 / $2.50 | đắt hơn 5% |
| Moondream: Moondream 3 Preview moondream/moondream3-preview | $0.3150 / $2.63 | $0.3000 / $2.50 | đắt hơn 5% |
| Elorian: Glimpse elorian/glimpse | $0.6300 / $3.15 | $0.6000 / $3.00 | đắt hơn 5% |
| Sakana: Fugu Max sakana/fugu-max | $2.10 / $6.30 | $2.00 / $6.00 | đắt hơn 5% |
| Pareto 26.9 unbiased/pareto-26.9 | $2.63 / $7.88 | $2.50 / $7.50 | đắt hơn 5% |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $4.20 / $12.60 | $4.00 / $12.00 | đắt hơn 5% |
| Fireworks: Ember-1 fireworks/ember-1 | $3.15 / $15.75 | $3.00 / $15.00 | đắt hơn 5% |
| Sakana: Fugu Ultra v2 sakana/fugu-ultra-v2 | $5.25 / $31.50 | $5.00 / $30.00 | đắt hơn 5% |
| Reflection: Beam 1.0 501B A23B reflection/beam-1.0-501b-a23b | $0.2625 / $1.05 | $0.2500 / $1.00 | đắt hơn 5% |
| LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b | $0.0525 / $0.7350 | $0.0500 / $0.7000 | đắt hơn 5% |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.1150 / $0.5750 | $0.1000 / $0.5000 | đắt hơn 14% |
$ cho mỗi 1M token input / output. Phép so sánh tính input và output theo tỉ lệ 1:3. Giá UberLLM là giá tốt nhất trên chợ ngay lúc này; Giá OpenRouter lấy từ danh sách model công khai của họ. Cả hai được kiểm tra ngày 5 tháng 11, 2026. Mọi model mà cả hai bên cùng bán đều được liệt kê, kể cả những model ở đây có giá bằng hoặc đắt hơn. OpenRouter là thương hiệu của chủ sở hữu; hai bên là sản phẩm độc lập.
Mọi model chat, rẻ nhất trước
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| GPT-OSS 20B openai/gpt-oss-20b | $0.000018 | $0.000089 | 128K |
| GPT-OSS 120B openai/gpt-oss-120b | $0.000069 | $0.00030 | 128K |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | $0.000074 | $0.00030 | 128K |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.00018 | $0.00056 | 1000K |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.00046 | $0.00058 | 128K |
| GLM 4.5 Air z-ai/glm-4.5-air | $0.00013 | $0.00084 | 128K |
| Ministral 3B mistralai/ministral-3-3b-instruct | $0.0010 | $0.0010 | 128K |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.00036 | $0.0014 | 198K |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.00045 | $0.0015 | 262K |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.00049 | $0.0015 | 128K |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.00090 | $0.0018 | 1049K |
| GLM 4.7 Flash z-ai/glm-4.7-flash | $0.00031 | $0.0020 | 198K |
| Gemma 3 27B google/gemma-3-27b-it | $0.00079 | $0.0020 | 40K |
| Ministral 3 8B mistralai/ministral-3-8b-instruct | $0.0017 | $0.0017 | 128K |
| Qwen 3.8 27B qwen/qwen-3-8-27b | $0.00020 | $0.0025 | 262K |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.00022 | $0.0025 | 1049K |
| Ministral 14B 3.0 mistralai/ministral-3-14b-instruct | $0.0020 | $0.0020 | 128K |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.00069 | $0.0028 | 256K |
| Qwen3 32B qwen/qwen3-32b | $0.00079 | $0.0028 | 32K |
| Gemma 4 31B google/gemma-4-31b | $0.00091 | $0.0027 | 256K |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 | $0.0030 | 128K |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.00057 | $0.0035 | 128K |
| GLM-5.2 z-ai/glm-5.2 | $0.00052 | $0.0035 | 1049K |
| Gemma 4 E2B google/gemma-4-e2b | $0.0016 | $0.0032 | 128K |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.0012 | $0.0036 | 262K |
| NVIDIA Nemotron Nano 9B v2 nvidia/nemotron-nano-9b-v2 | $0.0011 | $0.0043 | 128K |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0026 | $0.0039 | 160K |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0014 | $0.0045 | 1000K |
| GLM 5.3 Flash z-ai/glm-5.3-flash | $0.0015 | $0.0050 | 1049K |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0014 | $0.0059 | 1000K |
| NVIDIA Nemotron 3 Super 120B nvidia/nemotron-3-super-120b | $0.00077 | $0.0062 | 256K |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0021 | $0.0063 | 1000K |
| NVIDIA Nemotron Nano 12B v2 VL BF16 nvidia/nemotron-nano-12b-v2 | $0.0022 | $0.0065 | 128K |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0012 | $0.0079 | 256K |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.00086 | $0.0095 | 256K |
| MiniMax M2 minimax/minimax-m2 | $0.0023 | $0.0093 | 1000K |
| DeepSeek V3.1 deepseek/deepseek-v3.1 | $0.0025 | $0.0094 | 128K |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0027 | $0.0094 | 198K |
| GPT OSS Safeguard 120B openai/gpt-oss-safeguard-120b | $0.0024 | $0.0096 | 128K |
| GPT-6 Luna openai/gpt-6-luna | $0.0020 | $0.0102 | 1050K |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0030 | $0.0099 | 256K |
| GLM-4.7 z-ai/glm-4.7 | $0.0028 | $0.0102 | 128K |
| Palmyra Vision 7B writer/palmyra-vision-7b | $0.0034 | $0.0134 | 4K |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0025 | $0.0149 | 1049K |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0068 | $0.0136 | 1000K |
| GLM-4.6 z-ai/glm-4.6 | $0.0042 | $0.0170 | 198K |
| GLM-5 z-ai/glm-5 | $0.0053 | $0.0168 | 198K |
| GPT-4o Mini openai/gpt-4o-mini | $0.0045 | $0.0180 | 128K |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0021 | $0.0188 | 256K |
| Kimi K2.5 moonshotai/kimi-k2.5 | $0.0040 | $0.0203 | 256K |
| Magistral Small 2509 mistralai/magistral-small-2509 | $0.0069 | $0.0208 | 128K |
| GLM 4.5 z-ai/glm-4.5 | $0.0059 | $0.0216 | 128K |
| GLM 5.3 z-ai/glm-5.3 | $0.00052 | $0.0234 | 1000K |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0060 | $0.0239 | 1049K |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0030 | $0.0250 | 1049K |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0041 | $0.0247 | 1050K |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0050 | $0.0250 | 1000K |
| Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.0059 | $0.0248 | 256K |
| Grok 4.3 x-ai/grok-4.3 | $0.0124 | $0.0248 | 1000K |
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0050 | $0.0300 | 256K |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0071 | $0.0356 | 1000K |
| Tencent HY3 tencent/hy3 | $0.0092 | $0.0366 | 262K |
| Devstral 2 123B mistralai/devstral-2-123b | $0.0077 | $0.0384 | 256K |
| Thinking Machines: Inkling thinking-machines/inkling | $0.0094 | $0.0401 | 1049K |
| GLM-5 Turbo z-ai/glm-5-turbo | $0.0119 | $0.0396 | 200K |
| MiniMax M3.1 Flash minimax/minimax-m3-1-flash | $0.0102 | $0.0410 | 1000K |
| Meta: Muse Spark 1.3 Contributor meta-llama/muse-spark-1.3-contributor | $0.0200 | $0.0400 | 1049K |
| GPT 5 Nano openai/gpt-5-nano | $0.0059 | $0.0471 | 400K |
| Qwen 3.6 35B A3B qwen/qwen3-6-35b-a3b | $0.0049 | $0.0485 | 262K |
| GLM 5.1 z-ai/glm-5.1 | $0.0145 | $0.0455 | 200K |
| Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.0145 | $0.0465 | 128K |
| GPT OSS 20B openai/e2ee-gpt-oss-20b-p | $0.0125 | $0.0475 | 128K |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0225 | $0.0450 | 1000K |
| MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.0228 | $0.0456 | 1049K |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0114 | $0.0568 | 1049K |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.0110 | $0.0643 | 262K |
| Qwen 2.5 7B qwen/e2ee-qwen-2-5-7b-p | $0.0237 | $0.0616 | 32K |
| Meta: Muse Spark 1.2 Contributor meta-llama/muse-spark-1.2-contributor | $0.0300 | $0.0600 | 1049K |
| MiniMax M3 minimax/minimax-m3 | $0.0173 | $0.0694 | 200K |
| Kimi K3 moonshotai/kimi-k3 | $0.0017 | $0.0781 | 1000K |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0183 | $0.0730 | 198K |
| Mistral Large 3 mistralai/mistral-large-3 | $0.0248 | $0.0742 | 256K |
| Aion 3.5 aion-labs/aion-3-5 | $0.0375 | $0.0750 | 262K |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0500 | $0.0750 | 256K |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0150 | $0.0900 | 1000K |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0750 | $0.0750 | 128K |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0310 | $0.0931 | 1049K |
| Qwen3.5 Flash qwen/qwen3.5-flash | $0.0250 | $0.1000 | 1000K |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0203 | $0.1066 | 256K |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0333 | $0.1047 | 1000K |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0430 | $0.1146 | 256K |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0177 | $0.1278 | 128K |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0223 | $0.1341 | 1050K |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0182 | $0.1512 | 256K |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0400 | $0.1500 | 260K |
| MiMo-V2.5 xiaomi/mimo-v2-5 | $0.0700 | $0.1400 | 1000K |
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.0450 | $0.1500 | 262K |
| OpenAI: GPT-6.1 Terra openai/gpt-6.1-terra | $0.0311 | $0.1553 | 1050K |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0250 | $0.1650 | 128K |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | $0.0539 | $0.1617 | 1049K |
| NVIDIA Nemotron 3.5 Lightning 30B nvidia/nemotron-3-5-lightning-30b-a3b | $0.0640 | $0.1600 | 1000K |
| Mistral Small 3.2 24B Instruct (Morpheus Web) mistralai/mistral-small-3.2-24b-instruct:web | $0.0628 | $0.1675 | 256K |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0858 | $0.1716 | 1049K |
| Mistral Small 4 mistralai/mistral-small-4 | $0.0469 | $0.1875 | 256K |
| GLM 4.7 Flash Heretic z-ai/glm-4.7-flash-heretic | $0.0349 | $0.1994 | 200K |
| OpenAI GPT OSS 120B (Morpheus Web) openai/gpt-oss-120b:web | $0.0469 | $0.2010 | 128K |
| Gemma 3 27B E2EE google/e2ee-gemma-3-27b | $0.0560 | $0.2000 | 40K |
| Mercury 3 inception/mercury-3 | $0.0590 | $0.2065 | 1000K |
| GPT 5.4 Nano openai/gpt-5.4-nano | $0.0387 | $0.2419 | 400K |
| DeepSeek V4 Flash E2EE deepseek/e2ee-deepseek-v4-flash | $0.1074 | $0.2201 | 1000K |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0485 | $0.2426 | 1050K |
| inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.0788 | $0.2362 | 262K |
| Claude Haiku 5.5 (batch) anthropic/claude-haiku-5.5:batch | $0.0500 | $0.2500 | 1000K |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0807 | $0.2422 | 1000K |
| DeepSeek V4 Flash (Morpheus Web) deepseek/deepseek-v4-flash:web | $0.1139 | $0.2345 | 1000K |
| Gemma 4 Uncensored google/gemma-4-uncensored | $0.0813 | $0.2500 | 256K |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0541 | $0.2707 | 200K |
| Grok 4.7 x-ai/grok-4.7 | $0.0909 | $0.2728 | 500K |
| Grok 4.5 x-ai/grok-4.5 | $0.0915 | $0.2746 | 500K |
| GPT OSS 120B openai/e2ee-gpt-oss-120b-p | $0.0579 | $0.2897 | 128K |
| Mistral Large mistralai/mistral-large | $0.0928 | $0.2784 | 128K |
| Gemma 4 31B (E2EE) google/e2ee-gemma-4-31b | $0.1000 | $0.3000 | 262K |
| GPT-6 Sol openai/gpt-6-sol | $0.0670 | $0.3352 | 1050K |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.0671 | $0.3354 | 1050K |
| Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | $0.0674 | $0.3369 | 1000K |
| Gemma 4 26B A4B IT (Morpheus Web) google/gemma-4-26b-a4b-it:web | $0.1089 | $0.3350 | 262K |
| Gemma 4 31B IT (Morpheus Web) google/gemma-4-31b-it:web | $0.1172 | $0.3350 | 262K |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0840 | $0.3500 | 256K |
| GPT-5.4 openai/gpt-5.4 | $0.0610 | $0.3661 | 1000K |
| MiniMax M2.7 Highspeed minimax/minimax-m2.7-highspeed | $0.0900 | $0.3600 | 205K |
| Qwen 3.8 Max qwen/qwen-3-8-max | $0.1212 | $0.3638 | 1000K |
| Grok 4.20 Multi-Agent Beta x-ai/grok-4.20-multi-agent-beta | $0.1750 | $0.3500 | 2000K |
| Grok 4.20 Beta x-ai/grok-4.20-beta | $0.1750 | $0.3500 | 2000K |
| Qwen3.5 Plus qwen/qwen3.5-plus | $0.0650 | $0.3900 | 1000K |
| Llama 3.2 3B (Morpheus Web) meta-llama/llama-3.2-3b-instruct:web | $0.1005 | $0.4020 | 128K |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.1326 | $0.3980 | 524K |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0729 | $0.4372 | 400K |
| Venice Uncensored 1.2 venice/uncensored-1.2 | $0.0959 | $0.4316 | 128K |
| Particle AI: Particle-1 particle-ai/particle-1 | $0.0450 | $0.4500 | 1049K |
| Meta: Muse Spark 1.3 meta-llama/muse-spark-1.3 | $0.1250 | $0.4250 | 1049K |
| Gemma 4 26B A4B Uncensored (E2EE) google/e2ee-gemma-4-26b-a4b-uncensored-p | $0.0949 | $0.4396 | 262K |
| DeepSeek V4 Flash 0731 Fast deepseek/deepseek-v4-flash-0731-fast | $0.2065 | $0.4130 | 1000K |
| Mercury 2 inception/mercury-2 | $0.1447 | $0.4342 | 128K |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1000 | $0.4500 | 128K |
| Grok 4.6 x-ai/grok-4.6 | $0.1527 | $0.4581 | 500K |
| GPT 5 Mini openai/gpt-5-mini | $0.0616 | $0.4926 | 400K |
| Qwen 3 235B A22B Instruct 2507 (Morpheus Web) qwen/qwen3-235b-a22b-2507:web | $0.1005 | $0.5025 | 128K |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0781 | $0.5210 | 256K |
| Z.ai: GLM 5.3 FlashX z-ai/glm-5.3-flashx | $0.1480 | $0.5000 | 1049K |
| GPT-6 Astra openai/gpt-6-astra | $0.1072 | $0.5360 | 1050K |
| Qwen 3.6 35B A3B (E2EE) qwen/e2ee-qwen3-6-35b-a3b | $0.0847 | $0.5490 | 128K |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.1095 | $0.5474 | 1000K |
| Venice Uncensored 1.1 venice/uncensored | $0.1249 | $0.5621 | 32K |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.1150 | $0.5750 | 1050K |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.1200 | $0.6000 | 1000K |
| GPT-4o openai/gpt-4o | $0.1489 | $0.5955 | 128K |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.1216 | $0.6080 | 1049K |
| MiniMax M3 Preview minimax/minimax-m3-preview | $0.1500 | $0.6000 | 524K |
| DeepSeek V4.1 Flash Uncensored deepseek/deepseek-v4.1-flash-uncensored | $0.1500 | $0.6000 | 1049K |
| Qwen 3.6 35B A3B Uncensored (E2EE) qwen/e2ee-qwen3-6-35b-a3b-uncensored-p | $0.2000 | $0.6000 | 128K |
| Hermes 3 Llama 3.1 405b nousresearch/hermes-3-llama-3.1-405b | $0.5000 | $0.5000 | 128K |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.1099 | $0.6593 | 1050K |
| Trinity Large Thinking arcee-ai/trinity-large-thinking | $0.1975 | $0.6320 | 256K |
| LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b | $0.0525 | $0.7350 | 128K |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.1442 | $0.7208 | 1049K |
| GPT-5.2 openai/gpt-5.2 | $0.0925 | $0.7401 | 256K |
| GPT-5.5 openai/gpt-5.5 | $0.1250 | $0.7500 | 1000K |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.1500 | $0.7500 | 1049K |
| MiniMax M2.5 (Morpheus Web) minimax/minimax-m2.5:web | $0.2278 | $0.7973 | 198K |
| MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.2160 | $0.8100 | 1050K |
| Claude Opus 5 anthropic/claude-opus-5 | $0.1750 | $0.8749 | 1000K |
| Qwen 3 Coder 480B Turbo qwen/qwen3-coder-turbo | $0.2065 | $0.8850 | 256K |
| Aion 3.0 Mini aion-labs/aion-3-0-mini | $0.4130 | $0.8260 | 128K |
| Qwen3 VL 235B qwen/qwen3-vl-235b-a22b-thinking | $0.1048 | $0.9481 | 256K |
| Venice Role Play Uncensored venice/uncensored-role-play | $0.2395 | $0.9581 | 128K |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.2395 | $0.9581 | 256K |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.1965 | $0.9827 | 1000K |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.1970 | $0.9850 | 1000K |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.1997 | $0.9983 | 1000K |
| Reflection: Beam 1.0 501B A23B reflection/beam-1.0-501b-a23b | $0.2625 | $1.05 | 1049K |
| Aion 3.5 Mini aion-labs/aion-3-5-mini | $0.5162 | $1.03 | 262K |
| Z.ai: GLM 5.3 FlashX Legal z-ai/glm-5.3-flashx-legal | $0.3330 | $1.13 | 1049K |
| Gemini 3.5 Flash Lite google/gemini-3-5-flash-lite | $0.1470 | $1.23 | 1000K |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.1570 | $1.26 | 400K |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.2498 | $1.25 | 1000K |
| Seed 2.1 Turbo bytedance/seed-2-1-turbo | $0.2500 | $1.25 | 256K |
| Qwen 3 Next 80b (Morpheus Web) qwen/qwen3-next-80b-a3b-instruct:web | $0.2345 | $1.27 | 256K |
| Meta: Muse Glimmer 30B meta-llama/muse-glimmer-30b | $0.3150 | $1.26 | 131K |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.5900 | $1.18 | 256K |
| Gemini 3.1 Pro google/gemini-3.1-pro | $0.2196 | $1.32 | 1049K |
| Meta: Muse Spark 1.2 meta-llama/muse-spark-1.2 | $0.3750 | $1.27 | 1049K |
| Abliterated Large V2 abliteration-ai/abliteration-abliterated-model-large-v2 | $0.7500 | $1.25 | 1000K |
| Claude Opus 4.5 anthropic/claude-opus-4.5 | $0.2916 | $1.46 | 198K |
| Aion 2.0 aion-labs/aion-2.0 | $0.6800 | $1.36 | 128K |
| Cohere: Command A+ cohere/command-a-plus | $0.3150 | $1.57 | 192K |
| Abliterated Large Flash abliteration-ai/abliteration-abliterated-model-large-flash | $0.7375 | $1.48 | 1000K |
| Kimi K2 moonshotai/kimi-k2 | $0.3990 | $1.61 | 256K |
| GLM 5.1 E2EE z-ai/e2ee-glm-5.1 | $0.4400 | $1.66 | 200K |
| OrcaCyber: MiniMax M3.1 Flash Abliterated / Uncensored orcacyber/orcacyber-minimax-m3.1-flash | $0.8000 | $1.60 | 262K |
| OrcaCyber: Qwen3.8 Flash Next Abliterated / Uncensored orcacyber/orcacyber-qwen3.8-flash-next | $0.8000 | $1.60 | 262K |
| Qwen 3.6 Plus Uncensored qwen/qwen3.6-plus-uncensored | $0.3063 | $1.84 | 1000K |
| Gemini 3.6 Flash google/gemini-3-6-flash | $0.3675 | $1.84 | 1000K |
| Llama 3.3 70B (Morpheus Web) meta-llama/llama-3.3-70b-instruct:web | $0.4690 | $1.88 | 128K |
| Meta: Muse Wonder meta-llama/muse-wonder | $0.4000 | $2.00 | 1049K |
| GLM 4.7 Thinking z-ai/glm-4.7-thinking | $0.4500 | $2.00 | 128K |
| Hermes 3 Llama 3.1 405b (Morpheus Web) meta-llama/hermes-3-llama-3.1-405b:web | $0.7370 | $2.01 | 128K |
| Kimi K2.7 Code (Morpheus Web) moonshotai/kimi-k2.7-code:web | $0.4556 | $2.28 | 262K |
| Kimi K2.5 (Morpheus Web) moonshotai/kimi-k2.5:web | $0.3752 | $2.35 | 256K |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.6816 | $2.27 | 200K |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3000 | $2.40 | 1049K |
| OpenAI: GPT-6.1 Terra Pro (batch) openai/gpt-6.1-terra-pro:batch | $0.5000 | $2.50 | 1050K |
| OpenAI: GPT-6.1 Terra (batch) openai/gpt-6.1-terra:batch | $0.5000 | $2.50 | 1050K |
| Claude Fable 5 anthropic/claude-fable-5 | $0.5005 | $2.50 | 1000K |
| Meta: Muse Spark 1.1 meta-llama/muse-spark-1.1 | $0.7199 | $2.45 | 1049K |
| Moondream: Moondream 3.1 moondream/moondream3.1-9b-a2b | $0.3150 | $2.63 | 32K |
| Moondream: Moondream 3 Preview moondream/moondream3-preview | $0.3150 | $2.63 | 32K |
| Meta: Muse Spark Open meta-llama/muse-spark-open | $0.7375 | $2.51 | 1049K |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $0.5386 | $2.69 | 1000K |
| DeepSeek V4 Pro (Morpheus Web) deepseek/deepseek-v4-pro:web | $1.16 | $2.54 | 1000K |
| GLM 5.2 (Morpheus Web) z-ai/glm-5.2:web | $0.8040 | $2.75 | 1049K |
| GLM 5 (Morpheus Web) z-ai/glm-5:web | $0.7370 | $2.78 | 198K |
| GLM 5.2 E2EE z-ai/e2ee-glm-5-2-p | $0.8654 | $2.84 | 524K |
| Kimi K2.6 (Morpheus Web) moonshotai/kimi-k2.6:web | $0.5695 | $3.12 | 256K |
| ByteDance Seed: Seed-2.0-Code bytedance/seed-2.0-code | $0.5250 | $3.15 | 262K |
| Elorian: Glimpse elorian/glimpse | $0.6300 | $3.15 | 262K |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4375 | $3.50 | 256K |
| GLM 5.1 Non-thinking (Morpheus Web) z-ai/glm-5.1-non-thinking:web | $1.00 | $3.35 | 200K |
| GLM 5.1 Non-thinking z-ai/glm-5.1-non-thinking | $1.00 | $3.35 | 200K |
| GLM 5.1 (Morpheus Web) z-ai/glm-5.1:web | $1.17 | $3.69 | 200K |
| Aion 3.0 aion-labs/aion-3-0 | $1.75 | $3.50 | 128K |
| Qwen3.7 Max qwen/qwen3.7-max | $1.30 | $3.90 | 256K |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $0.9000 | $4.50 | 198K |
| GLM 5.3 Uncensored z-ai/glm-5.3-uncensored | $1.40 | $4.40 | 1049K |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.7920 | $4.75 | 1000K |
| OpenAI: GPT-6.1 Terra Pro openai/gpt-6.1-terra-pro | $1.00 | $5.00 | 1050K |
| Sakana: Fugu Max sakana/fugu-max | $2.10 | $6.30 | 1000K |
| GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.15 | $6.90 | 1050K |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $1.58 | $7.90 | 1050K |
| Pareto 26.9 unbiased/pareto-26.9 | $2.63 | $7.88 | 262K |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $1.90 | $9.50 | 1050K |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $1.90 | $9.50 | 1050K |
| MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | $4.35 | $8.70 | 1049K |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $4.20 | $12.60 | 1000K |
| Kimi K3 Fast moonshotai/kimi-k3-fast-api | $2.65 | $13.28 | 1000K |
| Fireworks: Ember-1 fireworks/ember-1 | $3.15 | $15.75 | 1049K |
| Claude Opus 4.8 Fast anthropic/claude-opus-4.8-fast | $4.67 | $23.34 | 1000K |
| Claude Opus 5 (Fast) anthropic/claude-opus-5-fast | $4.72 | $23.59 | 1000K |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.10 | $24.58 | 1000K |
| Sakana: Fugu Ultra v2 sakana/fugu-ultra-v2 | $5.25 | $31.50 | 1000K |
| GPT-5.5 Pro openai/gpt-5.5-pro | $8.98 | $53.87 | 1000K |
| Claude Opus 4.6 Fast anthropic/claude-opus-4.6-fast | $27.00 | $135.00 | 1000K |
| Claude Opus 4.7 Fast anthropic/claude-opus-4.7-fast | $27.00 | $135.00 | 1000K |
Câu hỏi thường gặp về giá API LLM
Request được định tuyến và tính tiền thế nào?
Mỗi request được gửi tới một nhà cung cấp bên thứ ba đang sẵn sàng cho model được yêu cầu. Nếu nhà cung cấp lỗi trước khi bắt đầu trả lời, request sẽ được thử lại. Request vẫn lỗi thì không bị tính tiền. Một request tốn đúng số tiền nhà cung cấp của nó đã tính, UberLLM không cộng phí, và mọi request đều được liệt kê kèm chi phí trong mục Hoạt động.
Giá API LLM được đo thế nào?
Giá được báo theo 1 triệu token, tách thành token input (prompt) và output (completion). Mỗi giá UberLLM là giá trực tiếp tốt nhất trên thị trường UberLLM, còn cột OpenRouter được đọc từ danh sách model công khai của OpenRouter trong cùng ngày. Các bảng được sắp xếp theo giá gộp, với tỷ trọng input và output là 1:3. UberLLM không cộng phí vào giá của nhà cung cấp. Phí thẻ 5.5% + $0.50 được tính khi bạn nạp credit; số credit bạn nhận đúng bằng số tiền bạn chọn.
Hỗ trợ những SDK và endpoint nào?
Mọi model trong danh sách này đều dùng được với một API key tại https://api.uberllm.dev/v1. API nhận request dạng OpenAI Chat Completions và Anthropic Messages, nên SDK chính thức của OpenAI và Anthropic đều chạy được sau khi bạn đặt base URL.