Pricing

Si-LLM

Category
Model
Price (USD)
Unit

chat

deepseek-ai/DeepSeek-R1

2.23

M tokens

chat

deepseek-ai/DeepSeek-V3

0.28

M tokens

chat

Qwen/QVQ-72B-Preview

1.3506

M tokens

chat

deepseek-ai/DeepSeek-V2.5

0.1814

M tokens

chat

meta-llama/Llama-3.3-70B-Instruct

0.5634

M tokens

chat

Qwen/QwQ-32B-Preview

0.1719

M tokens

chat

Qwen/Qwen2.5-Coder-32B-Instruct

0.1719

M tokens

chat

Qwen/Qwen2-VL-72B-Instruct

0.5634

M tokens

chat

OpenGVLab/InternVL2-26B

0.1364

M tokens

chat

TeleAI/TeleMM

0.1814

M tokens

chat

Qwen/Qwen2.5-72B-Instruct-128K

0.5634

M tokens

chat

Qwen/Qwen2.5-72B-Instruct

0.5634

M tokens

chat

deepseek-ai/deepseek-vl2

0.1351

M tokens

chat

Qwen/Qwen2.5-32B-Instruct

0.1719

M tokens

chat

Qwen/Qwen2.5-14B-Instruct

0.0955

M tokens

chat

Qwen/Qwen2.5-7B-Instruct

0.0001

M tokens

chat

Qwen/Qwen2.5-Coder-7B-Instruct

0.0001

M tokens

chat

TeleAI/TeleChat2

0.1814

M tokens

chat

internlm/internlm2_5-20b-chat

0.1364

M tokens

chat

internlm/internlm2_5-7b-chat

0.0001

M tokens

chat

meta-llama/Meta-Llama-3.1-405B-Instruct

2.8649

M tokens

chat

meta-llama/Meta-Llama-3.1-8B-Instruct

0.0001

M tokens

chat

meta-llama/Meta-Llama-3.1-70B-Instruct

0.5634

M tokens

chat

Qwen/Qwen2-7B-Instruct

0.0001

M tokens

chat

Qwen/Qwen2-1.5B-Instruct

0.0001

M tokens

chat

THUDM/glm-4-9b-chat

0.0001

M tokens

chat

THUDM/chatglm3-6b

0.0001

M tokens

chat

01-ai/Yi-1.5-9B-Chat-16K

0.0001

M tokens

chat

01-ai/Yi-1.5-6B-Chat

0.0001

M tokens

chat

01-ai/Yi-1.5-34B-Chat-16K

0.1719

M tokens

chat

google/gemma-2-9b-it

0.0001

M tokens

chat

google/gemma-2-27b-it

0.1719

M tokens

chat

AIDC-AI/Marco-o1

0.0001

M tokens

chat

LoRA/meta-llama/Meta-Llama-3.1-8B-Instruct

0.0859

M tokens

chat

LoRA/Qwen/Qwen2.5-32B-Instruct

0.2578

M tokens

chat

LoRA/Qwen/Qwen2.5-14B-Instruct

0.1432

M tokens

chat

Vendor-A/Qwen/Qwen2.5-72B-Instruct

0.1364

M tokens

chat

Pro/Qwen/Qwen2.5-Coder-7B-Instruct

0.0477

M tokens

chat

Pro/Qwen/Qwen2-VL-7B-Instruct

0.0477

M tokens

chat

Pro/OpenGVLab/InternVL2-8B

0.0477

M tokens

chat

Pro/Qwen/Qwen2.5-7B-Instruct

0.0477

M tokens

chat

Pro/meta-llama/Meta-Llama-3.1-8B-Instruct

0.0573

M tokens

chat

LoRA/Qwen/Qwen2.5-72B-Instruct

0.8458

M tokens

chat

Pro/Qwen/Qwen2-7B-Instruct

0.0477

M tokens

chat

Pro/Qwen/Qwen2-1.5B-Instruct

0.0191

M tokens

chat

LoRA/Qwen/Qwen2.5-7B-Instruct

0.0723

M tokens

chat

Pro/THUDM/glm-4-9b-chat

0.0819

M tokens

chat

Pro/google/gemma-2-9b-it

0.0819

M tokens

chat

deepseek-ai/DeepSeek-Coder-V2-Instruct

0.1814

M tokens

chat

Pro/Qwen/Qwen1.5-7B-Chat

0.0477

M tokens

chat

Pro/THUDM/chatglm3-6b

0.0477

M tokens

chat

Pro/01-ai/Yi-1.5-9B-Chat-16K

0.0573

M tokens

chat

Pro/01-ai/Yi-1.5-6B-Chat

0.0477

M tokens

chat

Pro/internlm/internlm2_5-7b-chat

0.0477

M tokens

chat

Pro/meta-llama/Meta-Llama-3-8B-Instruct

0.0573

M tokens

chat

Pro/mistralai/Mistral-7B-Instruct-v0.2

0.0477

M tokens

chat

Qwen/Qwen2-Math-72B-Instruct

0.5634

M tokens

chat

Vendor-A/Qwen/Qwen2-72B-Instruct

0.1364

M tokens

chat

Qwen/Qwen2.5-Math-72B-Instruct

0.5634

M tokens

chat

OpenGVLab/InternVL2-Llama3-76B

0.5634

M tokens

chat

nvidia/Llama-3.1-Nemotron-70B-Instruct

0.5634

M tokens

chat

Tencent/Hunyuan-A52B-Instruct

2.8649

M tokens

chat

mistralai/Mixtral-8x7B-Instruct-v0.1

0.1719

M tokens

chat

mistralai/Mistral-7B-Instruct-v0.2

0.0001

M tokens

chat

deepseek-ai/deepseek-llm-67b-chat

0.1364

M tokens

chat

Qwen/Qwen1.5-14B-Chat

0.0955

M tokens

chat

meta-llama/Meta-Llama-3-70B-Instruct

0.5634

M tokens

chat

meta-llama/Meta-Llama-3-8B-Instruct

0.0001

M tokens

chat

Qwen/Qwen1.5-7B-Chat

0.0001

M tokens

chat

Qwen/Qwen1.5-110B-Chat

0.5634

M tokens

chat

Qwen/Qwen1.5-32B-Chat

0.1719

M tokens

chat

deepseek-ai/DeepSeek-V2-Chat

0.1814

M tokens

chat

Qwen/Qwen2-72B-Instruct

0.5634

M tokens

chat

Qwen/Qwen2-57B-A14B-Instruct

0.1719

M tokens

image-to-image

stabilityai/stable-diffusion-xl-base-1.0

0.0001

M px * Steps

image-to-image

TencentARC/PhotoMaker

0.0001

M px * Steps

image-to-image

InstantX/InstantID

0.0001

M px * Steps

text-to-image

stabilityai/stable-diffusion-3-5-large

0.0001

M px * Steps

text-to-image

stabilityai/stable-diffusion-3-5-large-turbo

0.0004

M px * Steps

text-to-image

black-forest-labs/FLUX.1-pro

0.0505

M px * Steps

text-to-image

black-forest-labs/FLUX.1-dev

0.0004

M px * Steps

text-to-image

black-forest-labs/FLUX.1-schnell

0.0001

M px * Steps

text-to-image

stabilityai/stable-diffusion-3-medium

0.0001

M px * Steps

text-to-image

stabilityai/stable-diffusion-2-1

0.0001

M px * Steps

text-to-image

Pro/black-forest-labs/FLUX.1-schnell

0.0003

M px * Steps

text-to-image

LoRA/black-forest-labs/FLUX.1-dev

0.0007

M px * Steps

text-to-image

stabilityai/sd-turbo

0.0001

M px * Steps

text-to-image

stabilityai/sdxl-turbo

0.0001

M px * Steps

text-to-image

ByteDance/SDXL-Lightning

0.0001

M px * Steps

Si-Compute

Category
Product Name
Min Payment(USD)
Price(USD)

Virtual Machine

1*NVIDIA H100 GPU, 26 vCPUs, 200 GiB RAM

$50.00

$2.99/hour

Virtual Machine

2*NVIDIA H100 GPU, 52 vCPUs, 400 GiB RAM

$50.00

$5.98/hour

Virtual Machine

4*NVIDIA H100 GPU, 104 vCPUs, 800 GiB RAM

$50.00

$11.96/hour

Virtual Machine

6*NVIDIA H100 GPU, 156 vCPUs, 1.17 TiB RAM

$50.00

$17.94/hour

Virtual Machine

8*NVIDIA H100 GPU, 208 vCPUs, 1.56 TiB RAM

$50.00

$23.92/hour

Bare Metal

8* NVIDIA H100 GPU, 208 vCPUs, 1.56 TiB RAM, 10 Disks(21.92TB NVMe; 83.84TB NVMe)

$500.00

$23.92/hour

Bare Metal

8* NVIDIA H200 GPU, 208 vCPUs, 1.56 TiB RAM, 10 Disks(21.92TB NVMe; 83.84TB NVMe)

$500.00

$25.52/hour

Virtual Machine

General Compute 2vCPUs, 4GiB RAM

$0.01

$0.0954/hour

Virtual Machine

General Compute 4vCPUs, 8GiB RAM

$0.01

$0.1908/hour

Virtual Machine

General Compute 8vCPUs, 16GiB RAM

$0.01

$0.3816/hour

Virtual Machine

General Compute 16vCPUs, 32GiB RAM

$0.01

$0.7632/hour

Bandwidth

Dedicated Bandwidth

-

$0.0007/Mbps/hour

Storage

Block Storage

-

$0.0002/GiB/hour

Last updated