DeepSeek-V4-Flash-0731 is the officially updated version of the DeepSeek-V4-Flash model. The model is built on the same Mixture-of-Experts (MoE) architecture with 284 billion parameters, of which only 13 billion are activated per token, delivering high performance at relatively modest inference compute costs. The model supports a context length of up to one million tokens. It employs the signature engineering innovation of the V4 family — a hybrid attention mechanism that radically reduces the cost of long-context processing. Instead of uniformly handling all tokens, the model uses three modes simultaneously: Compressed Sparse Attention (CSA) compresses the context at a 1:4 ratio, after which the Lightning Indexer selects only the most relevant blocks for computation; Heavily Compressed Attention (HCA) applies extreme 1:128 compression and performs full global attention over ultra-compact representations of the entire history; in parallel, a sliding window of 128 tokens processes the immediate context without compression, preserving detailed local awareness.
In version 0731, a built-in DSpark module has been added that implements speculative decoding: the model can generate several tokens “ahead” and verify them in a single step, noticeably accelerating inference without quality loss (it increases memory footprint and is disabled by default; it can be enabled via the speculative parameter differently across inference engines). However, the key innovation is the improvement in post-training, as a result of which the model’s agentic capabilities have increased several-fold: compared to the preview version, scores on Terminal Bench 2.1 rose from 61.8% to 82.7%, on DeepSWE from 7.3% to 54.4%, and on Cybergym from 38.7% to 76.7%. Furthermore, 0731 outperforms much larger models, notably DeepSeek-V4-Pro (Preview) and the popular GLM-5.2, on most agentic benchmarks, and comes close to the strongest proprietary models such as Opus-4.8.
Use cases span a wide range of tasks where both context length and deployment cost-efficiency are critical: analysis and summarization of large documents — legal dossiers, scientific articles, corporate reports up to a million tokens; search across extensive corporate knowledge bases and information extraction from voluminous archives; multi-step agent work with long sessions and numerous tools; programming and mathematical modeling tasks that demand both reasoning accuracy and the ability to keep large codebases or specifications in view; building chatbots, automatic code generation systems, intelligent document assistants, and research agents. The MIT license allows unrestricted commercial use.
| Model Name | Context | Type | GPU | TPS | Tooling | Status | Link |
|---|---|---|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Flash-0731 | 1M | Public | 8×H100 tensor |
475.7 | AVAILABLE | chat |
curl https://chat.immers.cloud/v1/endpoints/generate/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer USER_API_KEY" \
--data-binary @- <<"EOF"
{"model": "deepseek-v4-flash-0731", "messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Say this is a test"}
], "temperature": 0, "max_tokens": 150
}
EOF
$response = Invoke-WebRequest https://chat.immers.cloud/v1/endpoints/generate/chat/completions `
-Method POST `
-Headers @{
"Authorization" = "Bearer USER_API_KEY"
"Content-Type" = "application/json; charset=utf-8"
} `
-Body ([System.Text.Encoding]::UTF8.GetBytes((@{
model = "deepseek-v4-flash-0731"
messages = @(
@{ role = "system"; content = "You are a helpful assistant." },
@{ role = "user"; content = "Say this is a test" })
} | ConvertTo-Json -Depth 10)))
([System.Text.Encoding]::UTF8.GetString($response.RawContentStream.ToArray()) | ConvertFrom-Json).choices[0].message.content
#!pip install OpenAI --upgrade
from openai import OpenAI
client = OpenAI(
api_key="USER_API_KEY",
base_url="https://chat.immers.cloud/v1/endpoints/generate/",
)
chat_response = client.chat.completions.create(
model="deepseek-v4-flash-0731",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Say this is a test"},
]
)
print(chat_response.choices[0].message.content)
# linux
export ANTHROPIC_BASE_URL=https://chat.immers.cloud/v1/endpoints/generate/
export ANTHROPIC_API_KEY=USER_API_KEY
export ANTHROPIC_MODEL=deepseek-v4-flash-0731
# windows (ps)
[Environment]::SetEnvironmentVariable("ANTHROPIC_BASE_URL", "https://chat.immers.cloud/v1/endpoints/generate/", "User")
[Environment]::SetEnvironmentVariable("ANTHROPIC_AUTH_TOKEN", "USER_API_KEY", "User")
[Environment]::SetEnvironmentVariable("ANTHROPIC_MODEL", "deepseek-v4-flash-0731", "User")
# linux
export OPENAI_BASE_URL=https://chat.immers.cloud/v1/endpoints/generate/
export OPENAI_API_KEY=USER_API_KEY
export OPENAI_MODEL=deepseek-v4-flash-0731
# windows (ps)
[Environment]::SetEnvironmentVariable("OPENAI_BASE_URL", "https://chat.immers.cloud/v1/endpoints/generate/", "User")
[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "USER_API_KEY", "User")
[Environment]::SetEnvironmentVariable("OPENAI_MODEL", "deepseek-v4-flash-0731", "User")
An endpoint is a server with pre-installed software that automatically downloads neural network weights and launches an OpenAI-compatible API to handle incoming requests.
A private endpoint is created within the user's project, belongs exclusively to the user, and is billed per server configuration in accordance with the infrastructure pricing.
We recommend creating private endpoints when you need to:
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.