跳转至

其他服务商

注意

此页含开源模型,无统一价格,所有信息仅供参考,具体价格自行调整。
国产模型使用$1:¥1的比例设置倍率,自行调整。

Llama系列

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
meta-llama/llama-3.2-1b-instruct 0.01 0.02 0.005/2 131k -
meta-llama/llama-3.2-3b-instruct 0.03 0.05 0.015/1.666666667 131k -
meta-llama/llama-3.2-11b-vision-instruct 0.055 0.055 0.0275/1 131k -
meta-llama/llama-3.2-90b-vision-instruct 0.35 0.4 0.175/1.142857143 131k -
meta-llama/llama-3.1-8b-instruct 0.055 0.055 0.0275/1 131k -
meta-llama/llama-3.1-70b-instruct 0.3 0.3 0.15/1 131k -
meta-llama/llama-3.1-405b-instruct 1.79 1.79 0.895/1 131k -
meta-llama/llama-3-8b-instruct 0.055 0.055 0.0275/1 8k -
meta-llama/llama-3-70b-instruct 0.35 0.4 0.175/1.142857143 8k -
json片段

模型倍率

"meta-llama/llama-3.2-1b-instruct":0.005,
"meta-llama/llama-3.2-3b-instruct":0.015,
"meta-llama/llama-3.2-11b-vision-instruct":0.0275,
"meta-llama/llama-3.2-90b-vision-instruct":0.175,
"meta-llama/llama-3.1-8b-instruct":0.0275,
"meta-llama/llama-3.1-70b-instruct":0.15,
"meta-llama/llama-3.1-405b-instruct":0.895,
"meta-llama/llama-3-8b-instruct":0.0275,
"meta-llama/llama-3-70b-instruct":0.175
补全倍率
"meta-llama/llama-3.2-1b-instruct":2,
"meta-llama/llama-3.2-3b-instruct":1.666666667,
"meta-llama/llama-3.2-11b-vision-instruct":1,
"meta-llama/llama-3.2-90b-vision-instruct":1.142857143,
"meta-llama/llama-3.1-8b-instruct":1,
"meta-llama/llama-3.1-70b-instruct":1,
"meta-llama/llama-3.1-405b-instruct":1,
"meta-llama/llama-3-8b-instruct":1,
"meta-llama/llama-3-70b-instruct":1.142857143

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
meta-llama/Llama-3.2-3B-Instruct-Turbo 0.06 0.06 0.03/1 131k -
meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo 0.18 0.18 0.09/1 131k -
meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo 1.2 1.2 0.6/1 131k -
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo 0.18 0.18 0.09/1 131k -
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo 0.88 0.88 0.44/1 131k -
meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo 3.5 3.5 1.75/1 131k -
meta-llama/Meta-Llama-3-8B-Instruct-Turbo 0.88 0.88 0.44/1 8k -
meta-llama/Meta-Llama-3-70B-Instruct-Turbo 0.18 0.18 0.09/1 8k -
meta-llama/Meta-Llama-3-8B-Instruct-Lite 0.1 0.1 0.05/1 8k -
meta-llama/Meta-Llama-3-70B-Instruct-Lite 0.54 0.54 0.27/1 8k -
meta-llama/Llama-3-8b-chat-hf 0.2 0.2 0.1/1 8k -
meta-llama/Llama-3-70b-chat-hf 0.9 0.9 0.45/1 8k -
json片段

模型倍率

"meta-llama/Llama-3.2-3B-Instruct-Turbo":0.03,
"meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo":0.09,
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo":0.6,
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo":0.09,
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo":0.44,
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo":1.75,
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo":0.44,
"meta-llama/Meta-Llama-3-70B-Instruct-Turbo":0.09,
"meta-llama/Meta-Llama-3-8B-Instruct-Lite":0.05,
"meta-llama/Meta-Llama-3-70B-Instruct-Lite":0.27,
"meta-llama/Llama-3-8b-chat-hf":0.1,
"meta-llama/Llama-3-70b-chat-hf":0.45
补全倍率
"meta-llama/Llama-3.2-3B-Instruct-Turbo":1,
"meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo":1,
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo":1,
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo":1,
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo":1,
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo":1,
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo":1,
"meta-llama/Meta-Llama-3-70B-Instruct-Turbo":1,
"meta-llama/Meta-Llama-3-8B-Instruct-Lite":1,
"meta-llama/Meta-Llama-3-70B-Instruct-Lite":1,
"meta-llama/Llama-3-8b-chat-hf":1,
"meta-llama/Llama-3-70b-chat-hf":1

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
Pro/meta-llama/Meta-Llama-3.1-8B-Instruct 0.42 0.42 0.21/1 32k -
meta-llama/Meta-Llama-3.1-70B-Instruct 4.13 4.13 2.065/1 32k -
meta-llama/Meta-Llama-3.1-405B-Instruct 21 21 10.5/1 32k -
meta-llama/Meta-Llama-3-70B-Instruct 4.13 4.13 2.065/1 8k -
Pro/meta-llama/Meta-Llama-3-8B-Instruct 0.42 0.42 0.21/1 8k -
json片段

模型倍率

"Pro/meta-llama/Meta-Llama-3.1-8B-Instruct":0.21,
"meta-llama/Meta-Llama-3.1-70B-Instruct":2.065,
"meta-llama/Meta-Llama-3.1-405B-Instruct":10.5,
"meta-llama/Meta-Llama-3-70B-Instruct":2.065,
"Pro/meta-llama/Meta-Llama-3-8B-Instruct":0.21
补全倍率
"Pro/meta-llama/Meta-Llama-3.1-8B-Instruct":1,
"meta-llama/Meta-Llama-3.1-70B-Instruct":1,
"meta-llama/Meta-Llama-3.1-405B-Instruct":1,
"meta-llama/Meta-Llama-3-70B-Instruct":1,
"Pro/meta-llama/Meta-Llama-3-8B-Instruct":1

Qwen系列

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
qwen-turbo-latest 0.04 0.08 0.02/2 128K -
qwen-plus-latest 0.11 0.28 0.055/2.545454545 128K -
qwen-max-latest 2.8 8.4 1.4/3 32K -
qwen-long 0.07 0.28 0.035/4 100K -
qwen-vl-plus 1.12 1.12 0.56/1 8K -
qwen-vl-max 2.8 2.8 1.4/1 32K -
qwen-math-turbo-latest 0.28 0.84 0.14/3 4K -
qwen-math-plus-latest 0.56 1.68 0.28/3 4K -
qwen-coder-turbo-latest 0.28 0.84 0.14/3 128K -
qwen2.5-7b-instruct 0.14 0.28 0.07/2 128K -
qwen2.5-14b-instruct 0.28 0.84 0.14/3 128K -
qwen2.5-32b-instruct 0.49 0.98 0.245/2 128K -
qwen2.5-72b-instruct 0.56 1.68 0.28/3 128K -
qwen2.5-math-7b-instruct 0.14 0.28 0.07/2 4K -
qwen2.5-math-72b-instruct 0.56 1.68 0.28/3 4K -
qwen2.5-coder-7b-instruct 0.14 0.28 0.07/2 128K -
json片段

模型倍率

"qwen-turbo-latest":0.02,
"qwen-plus-latest":0.055,
"qwen-max-latest":1.4,
"qwen-long":0.035,
"qwen-vl-plus":0.56,
"qwen-vl-max":1.4,
"qwen-math-turbo-latest":0.14,
"qwen-math-plus-latest":0.28,
"qwen-coder-turbo-latest":0.14,
"qwen2.5-7b-instruct":0.07,
"qwen2.5-14b-instruct":0.14,
"qwen2.5-32b-instruct":0.245,
"qwen2.5-72b-instruct":0.28,
"qwen2.5-math-7b-instruct":0.07,
"qwen2.5-math-72b-instruct":0.28,
"qwen2.5-coder-7b-instruct":0.07
补全倍率
"qwen-turbo-latest":2,
"qwen-plus-latest":2.545454545,
"qwen-max-latest":3,
"qwen-long":4,
"qwen-vl-plus":1,
"qwen-vl-max":1,
"qwen-math-turbo-latest":3,
"qwen-math-plus-latest":3,
"qwen-coder-turbo-latest":3,
"qwen2.5-7b-instruct":2,
"qwen2.5-14b-instruct":3,
"qwen2.5-32b-instruct":2,
"qwen2.5-72b-instruct":3,
"qwen2.5-math-7b-instruct":2,
"qwen2.5-math-72b-instruct":3,
"qwen2.5-coder-7b-instruct":2

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
eva-unit-01/eva-qwen-2.5-14b 0.25 0.5 0.125/2 32k -
qwen/qwen-2.5-72b-instruct 0.35 0.4 0.175/1.142857143 131k -
qwen/qwen-2-vl-7b-instruct 0.1 0.1 0.05/1 32k -
qwen/qwen-2-vl-72b-instruct 0.4 0.4 0.2/1 32k -
qwen/qwen-2-7b-instruct 0.054 0.054 0.027/1 32k -
qwen/qwen-2-72b-instruct 0.34 0.34 0.17/1 32k -
json片段

模型倍率

"eva-unit-01/eva-qwen-2.5-14b":0.125,
"qwen/qwen-2.5-72b-instruct":0.175,
"qwen/qwen-2-vl-7b-instruct":0.05,
"qwen/qwen-2-vl-72b-instruct":0.2,
"qwen/qwen-2-7b-instruct":0.027,
"qwen/qwen-2-72b-instruct":0.17
补全倍率
"eva-unit-01/eva-qwen-2.5-14b":2,
"qwen/qwen-2.5-72b-instruct":1.142857143,
"qwen/qwen-2-vl-7b-instruct":1,
"qwen/qwen-2-vl-72b-instruct":1,
"qwen/qwen-2-7b-instruct":1,
"qwen/qwen-2-72b-instruct":1

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
Qwen/Qwen2-72B-Instruct 0.9 0.9 0.3/1 - -
Qwen/Qwen1.5-72B-Chat 0.9 0.9 0.3/1 - -
Qwen/Qwen1.5-110B-Chat 1.8 1.8 0.6/1 - -
json片段

模型倍率

"Qwen/Qwen2-72B-Instruct":0.3,
"Qwen/Qwen1.5-72B-Chat":0.3,
"Qwen/Qwen1.5-110B-Chat":0.6
补全倍率
"Qwen/Qwen2-72B-Instruct":1,
"Qwen/Qwen1.5-72B-Chat":1,
"Qwen/Qwen1.5-110B-Chat":1

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
Pro/Qwen/Qwen2.5-7B-Instruct 0.35 0.35 0.175/1 32k -
Qwen/Qwen2.5-14B-Instruct 0.7 0.7 0.35/1 32k -
Qwen/Qwen2.5-32B-Instruct 1.26 1.26 0.63/1 32k -
Qwen/Qwen2.5-72B-Instruct 4.13 4.13 2.065/1 32k -
Qwen/Qwen2.5-72B-Instruct-128K 4.13 4.13 2.065/1 128k -
Qwen/Qwen2.5-Math-72B-Instruct 4.13 4.13 2.065/1 4k -
Pro/Qwen/Qwen2-1.5B-Instruct 0.14 0.14 0.07/1 32k -
Pro/Qwen/Qwen2-7B-Instruct 0.35 0.35 0.175/1 32k -
Qwen/Qwen2-72B-Instruct 4.13 4.13 2.065/1 32k -
Qwen/Qwen2-Math-72B-Instruct 4.13 4.13 2.065/1 4k -
Qwen/Qwen2-57B-A14B-Instruct 1.26 1.26 0.63/1 32k -
json片段

模型倍率

"Pro/Qwen/Qwen2.5-7B-Instruct":0.175,
"Qwen/Qwen2.5-14B-Instruct":0.35,
"Qwen/Qwen2.5-32B-Instruct":0.63,
"Qwen/Qwen2.5-72B-Instruct":2.065,
"Qwen/Qwen2.5-72B-Instruct-128K":2.065,
"Qwen/Qwen2.5-Math-72B-Instruct":2.065,
"Pro/Qwen/Qwen2-1.5B-Instruct":0.07,
"Pro/Qwen/Qwen2-7B-Instruct":0.175,
"Qwen/Qwen2-72B-Instruct":2.065,
"Qwen/Qwen2-Math-72B-Instruct":2.065,
"Qwen/Qwen2-57B-A14B-Instruct":0.63
补全倍率
"Pro/Qwen/Qwen2.5-7B-Instruct":1,
"Qwen/Qwen2.5-14B-Instruct":1,
"Qwen/Qwen2.5-32B-Instruct":1,
"Qwen/Qwen2.5-72B-Instruct":1,
"Qwen/Qwen2.5-72B-Instruct-128K":1,
"Qwen/Qwen2.5-Math-72B-Instruct":1,
"Pro/Qwen/Qwen2-1.5B-Instruct":1,
"Pro/Qwen/Qwen2-7B-Instruct":1,
"Qwen/Qwen2-72B-Instruct":1,
"Qwen/Qwen2-Math-72B-Instruct":1,
"Qwen/Qwen2-57B-A14B-Instruct":1

零一万物

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
yi-large 20 20 10/1 32k -
yi-medium 2.5 2.5 1.25/1 16k -
yi-vision 6 6 3/1 16k -
yi-medium-200k 12 12 6/1 200k -
yi-spark 1 1 0.5/1 16k -
yi-large-rag 25 25 12.5/1 16k -
yi-large-fc 20 20 10/1 32k -
yi-large-turbo 12 12 6/1 16k -
yi-large-preview 20 20 10/1 16k -
json片段

模型倍率

"yi-large":10,
"yi-medium":1.25,
"yi-vision":3,
"yi-medium-200k":6,
"yi-spark":0.5,
"yi-large-rag":12.5,
"yi-large-fc":10,
"yi-large-turbo":6,
"yi-large-preview":10
补全倍率
"yi-large":1,
"yi-medium":1,
"yi-vision":1,
"yi-medium-200k":1,
"yi-spark":1,
"yi-large-rag":1,
"yi-large-fc":1,
"yi-large-turbo":1,
"yi-large-preview":1

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
nousresearch/nous-hermes-yi-34b 0.72 0.72 0.36/1 4k -
json片段

模型倍率

"nousresearch/nous-hermes-yi-34b":0.36
补全倍率
"nousresearch/nous-hermes-yi-34b":1

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
NousResearch/Nous-Hermes-2-Yi-34B 0.8 0.8 0.4/1 4k -
json片段

模型倍率

"NousResearch/Nous-Hermes-2-Yi-34B":0.4
补全倍率
"NousResearch/Nous-Hermes-2-Yi-34B":1

名称 Input($/M) Output($/M) 倍率(in/out) Context 备注
01-ai/Yi-1.5-34B-Chat-16K 1.26 1.26 0.63/1 16k -
Pro/01-ai/Yi-1.5-9B-Chat-16K 0.42 0.42 0.21/1 16k -
Pro/01-ai/Yi-1.5-6B-Chat 0.35 0.35 0.175/1 4k -
json片段

模型倍率

"01-ai/Yi-1.5-34B-Chat-16K":0.63,
"Pro/01-ai/Yi-1.5-9B-Chat-16K":0.21,
"Pro/01-ai/Yi-1.5-6B-Chat":0.175
补全倍率
"01-ai/Yi-1.5-34B-Chat-16K":1,
"Pro/01-ai/Yi-1.5-9B-Chat-16K":1,
"Pro/01-ai/Yi-1.5-6B-Chat":1