API 价格查询
主流 LLM 厂商价格一览。支持排序、筛选。费用单位：每 100 万 tokens。
| 模型名称 ▲▼ | 服务商 ▲▼ | 输入单价 / 1M ▲ | 输出单价 / 1M ▲▼ | 上下文 ▲▼ | 最大输出 | 速度 ▲▼ | 质量 ▲▼ | 性价比 ▲▼ |
|---|---|---|---|---|---|---|---|---|
| GPT-OSS 120B | OpenAI | $0.039 | $0.190 | 131K | 33K | -- | -- | -- |
| GPT-5 Nano | OpenAI | $0.050 | $0.400 | 128K | 16K | 144 tok/s | 27 | 536.0 |
| Qwen3.5-9B | Alibaba | $0.050 | $0.150 | 262K | 33K | -- | -- | -- |
| Qwen3.5-Omni Flash | Alibaba | $0.065 | $0.260 | 262K | 33K | -- | -- | -- |
| Hunyuan HY3 Preview | Tencent | $0.066 | $0.260 | 262K | 33K | -- | -- | -- |
| GPT-OSS 20B (Bedrock) | OpenAI | $0.070 | $0.300 | 16K | 16K | -- | -- | -- |
| GLM-4.7-flash | Zhipu | $0.070 | $0.400 | 200K | 8K | -- | -- | -- |
| GPT-OSS 20B | OpenAI | $0.075 | $0.300 | 131K | 33K | -- | -- | -- |
| Gemini 2.0 Flash-Lite | $0.075 | $0.300 | 1.0M | 8K | -- | 15 | 193.3 | |
| Llama 4 Scout | Meta | $0.080 | $0.300 | 1.0M | 16K | 132 tok/s | 14 | 168.8 |
| Qwen3-Next-80B-A3B-Thinking | Alibaba | $0.098 | $0.780 | 262K | 33K | -- | -- | -- |
| GPT-4.1 Nano | OpenAI | $0.100 | $0.400 | 1.0M | 33K | 131 tok/s | 13 | 130.0 |
| Gemini 2.5 Flash-Lite | $0.100 | $0.400 | 1.0M | 66K | 263 tok/s | 13 | 127.0 | |
| Gemini 2.0 Flash | $0.100 | $0.400 | 1.0M | 8K | -- | 19 | 185.0 | |
| Devstral Small | Mistral | $0.100 | $0.300 | 256K | 33K | -- | -- | -- |
| Mistral Small 3.2 | Mistral | $0.100 | $0.300 | 128K | 4K | 139 tok/s | 10 | 102.0 |
| Gemma 4 26B A4B | $0.130 | $0.400 | 262K | 33K | -- | -- | -- | |
| Gemma 4 31B | $0.140 | $0.400 | 262K | 33K | -- | -- | -- | |
| DeepSeek V4-Flash | DeepSeek | $0.140 | $0.280 | 1.0M | 384K | -- | -- | -- |
| GPT-OSS 120B (Bedrock) | OpenAI | $0.150 | $0.600 | 16K | 16K | -- | -- | -- |
| GPT-4o Mini | OpenAI | $0.150 | $0.600 | 128K | 16K | 74 tok/s | 13 | 84.0 |
| Mistral Small 4 | Mistral | $0.150 | $0.600 | 256K | 33K | -- | -- | -- |
| Ministral 3 8B | Mistral | $0.150 | $0.150 | 262K | 33K | -- | -- | -- |
| Pixtral 12B | Mistral | $0.150 | $0.150 | 128K | 4K | -- | -- | -- |
| Command R | Cohere | $0.150 | $0.600 | 128K | 4K | -- | -- | -- |
| Command R 08 2024 | Cohere | $0.150 | $0.600 | 128K | 4K | -- | -- | -- |
| Command R7b 12 2024 | Cohere | $0.150 | $0.038 | 128K | 4K | -- | -- | -- |
| Llama 3.3 70B | Meta | $0.180 | $0.180 | 131K | 4K | -- | -- | -- |
| GPT-5.4 Nano | OpenAI | $0.200 | $1.25 | 400K | 128K | -- | -- | -- |
| Grok 4.1 Fast | xAI | $0.200 | $0.500 | 2.0M | 16K | 77 tok/s | 24 | 118.0 |
| Grok 4.1 Fast Reasoning | xAI | $0.200 | $0.500 | 2.0M | 16K | 96 tok/s | 39 | 193.0 |
| Grok Code Fast | xAI | $0.200 | $1.50 | 256K | 16K | -- | -- | -- |
| Ministral 3 14B | Mistral | $0.200 | $0.200 | 262K | 33K | -- | -- | -- |
| Jamba 1.5 | AI21 | $0.200 | $0.400 | 256K | 256K | -- | -- | -- |
| Jamba 1.5 Mini | AI21 | $0.200 | $0.400 | 256K | 256K | -- | -- | -- |
| Jamba 1.5 Mini@001 | AI21 | $0.200 | $0.400 | 256K | 256K | -- | -- | -- |
| Jamba Mini 1.6 | AI21 | $0.200 | $0.400 | 256K | 256K | -- | -- | -- |
| Jamba Mini 1.7 | AI21 | $0.200 | $0.400 | 256K | 256K | -- | -- | -- |
| GPT-5 Mini | OpenAI | $0.250 | $2.00 | 400K | 16K | 79 tok/s | 41 | 164.8 |
| Gemini 3.1 Flash-Lite | $0.250 | $1.50 | 1.0M | 66K | 339 tok/s | 34 | 134.0 | |
| Claude 3 Haiku 20240307 | Anthropic | $0.250 | $1.25 | 200K | 4K | -- | -- | -- |
| Llama 4 Maverick | Meta | $0.270 | $0.850 | 1.0M | 16K | 118 tok/s | 18 | 68.1 |
| Qwen3.6-Plus | Alibaba | $0.276 | $1.65 | 1.0M | 33K | -- | -- | -- |
| DeepSeek V3.2 (Chat) | DeepSeek | $0.280 | $0.420 | 128K | 8K | -- | 32 | 114.6 |
| DeepSeek V3.2 (Reasoner) | DeepSeek | $0.280 | $0.420 | 128K | 8K | -- | -- | -- |
| DeepSeek Reasoner | DeepSeek | $0.280 | $0.420 | 131K | 66K | -- | -- | -- |
| Gemini 2.5 Flash | $0.300 | $2.50 | 1.0M | 66K | 221 tok/s | 21 | 68.7 | |
| Grok 3 Mini | xAI | $0.300 | $0.500 | 131K | 16K | -- | -- | -- |
| Codestral | Mistral | $0.300 | $0.900 | 256K | 33K | -- | -- | -- |
| Qwen 3.5 27B | Alibaba | $0.300 | $2.40 | 128K | 33K | -- | -- | -- |
| Nova 2.0 Lite | Amazon | $0.300 | $2.50 | 1.0M | 64K | 223 tok/s | 18 | 60.0 |
| Nemotron 3 Super 120B | NVIDIA | $0.300 | $0.800 | 1.0M | 33K | 159 tok/s | 36 | 120.0 |
| MiniMax M2.5 | MiniMax | $0.300 | $1.20 | 128K | 33K | 87 tok/s | 42 | 139.7 |
| Command Light | Cohere | $0.300 | $0.600 | 4K | 4K | -- | -- | -- |
| GPT-4.1 Mini | OpenAI | $0.400 | $1.60 | 1.0M | 33K | 75 tok/s | 23 | 57.2 |
| Mistral Medium | Mistral | $0.400 | $2.00 | 131K | 16K | -- | -- | -- |
| Devstral | Mistral | $0.400 | $2.00 | 256K | 33K | -- | -- | -- |
| Qwen3.5-Omni Plus | Alibaba | $0.400 | $4.80 | 262K | 33K | -- | -- | -- |
| Gemini 3 Flash | $0.500 | $3.00 | 1.0M | 66K | 201 tok/s | 35 | 70.0 | |
| Gemini 3 Flash Reasoning | $0.500 | $3.00 | 1.0M | 66K | 202 tok/s | 46 | 92.8 | |
| Mistral Large 3 | Mistral | $0.500 | $1.50 | 262K | 8K | 52 tok/s | 23 | 45.6 |
| Magistral Small | Mistral | $0.500 | $1.50 | 40K | 16K | -- | -- | -- |
| DeepSeek R1 | DeepSeek | $0.550 | $2.19 | 128K | 33K | -- | 27 | 49.3 |
| Grok 3 Mini Fast | xAI | $0.600 | $4.00 | 131K | 16K | -- | -- | -- |
| Qwen 3.5 397B | Alibaba | $0.600 | $3.60 | 128K | 33K | -- | -- | -- |
| Kimi K2.5 | Moonshot | $0.600 | $3.00 | 262K | 33K | 44 tok/s | 47 | 78.0 |
| Kimi K2 Thinking | Moonshot | $0.600 | $2.50 | 262K | 3 |