DeepSeek-V4-Flash

reasoning
coding

Announce Date: 22.04.2026
Parameters: 293B
Experts: 256
Activated at inference: 13B
Context: 1049K
Layers: 43
Attention Type: DeepSeek Sparse Attention
Developer: DeepSeek
Transformers Version: 4.57.1
License: MIT

Public endpoint

Use our pre-built public endpoints for free to test inference and explore DeepSeek-V4-Flash capabilities. You can obtain an API access token on the token management page after registration and verification.
Model Name Context Type GPU Status Link
There are no public endpoints for this model yet.

Private server

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

  • maximize endpoint performance,
  • enable full context for long sequences,
  • ensure top-tier security for data processing in an isolated, dedicated environment,
  • use custom weights, such as fine-tuned models or LoRA adapters.

Recommended server configurations for hosting DeepSeek-V4-Flash

Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa100-3.32.384.240
1,048,576.0
pipeline
 3 $7.36 3.312 Launch
h100nvl-2.24.192.240
1,048,576.0
tensor
 2 $8.17 1.933 Launch
teslaa100-4.16.256.240
1,048,576.0
tensor
 4 $9.14 4.865 Launch
h200-2.24.256.240
1,048,576.0
tensor
 2 $9.41 7.730 Launch
h200-2.24.256.240.nvlink
1,048,576.0
tensor
 2 $9.41 7.730 Launch
teslaa100-4.32.384.320.nvlink
1,048,576.0
tensor
 4 $9.50 4.865 Launch
rtx5090-8.44.256.240
1,048,576.0
tensor
 8 $11.55 1.275 Launch
h100-3.32.384.240
1,048,576.0
pipeline
 3 $11.73 3.312 Launch
h100-4.16.256.240
1,048,576.0
tensor
 4 $14.96 4.865 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
dedicated-h100-8.96.768.5760-1
1,048,576.0
tensor
 8 4.865 Launch
teslaa100-6.44.512.480.nvlink
1,048,576.0
pipeline
 6 $14.10 3.312 Launch
h200-3.32.512.480
1,048,576.0
pipeline
 3 $14.36 4.624 Launch
h100nvl-4.32.384.480
1,048,576.0
tensor
 4 $16.23 1.933 Launch
teslaa100-8.44.512.480.nvlink
1,048,576.0
tensor
 8 $18.35 4.865 Launch
h200-4.32.768.480
1,048,576.0
tensor
 4 $19.23 7.730 Launch
h200-4.32.768.480.nvlink
1,048,576.0
tensor
 4 $19.23 7.730 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
h200-6.52.896.960
1,048,576.0
pipeline
 6 $28.39 4.624 Launch
h200-8.52.1024.960
1,048,576.0
tensor
 8 $37.37 7.730 Launch
h200-8.52.1024.960.nvlink
1,048,576.0
tensor
 8 $37.37 7.730 Launch

Related models

DeepSeek-V4-Pro

Need help?

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.