DeepSeek V4 Pro 0813
DeepSeek’s flagship open-weight model for coding, tool use, and long-context agentic work.
Quantization
FP4 + FP8
Mixed precision
Context Window
1.0M
Tokens
Intelligence
53
AA Index
Released
Aug 2026
13 Aug 2026
Frontier reasoning, open weights
DeepSeek V4 Pro 0813 is DeepSeek’s official V4 Pro release, optimized for advanced reasoning, coding, tool use and agentic workloads.
It serves a 1M-token context window in a mixed FP4 + FP8 quantization, keeping long-context research and repository-scale work affordable across every latency tier.
1M context · FP4 + FP8 mixed precision
Best for repository-scale engineering
Complex Coding
Repository-scale engineering: multi-file edits, large refactors and iterative debugging across long sessions.
Agentic Workflows
Configurable reasoning effort for long-horizon planning, tool orchestration and recovery across many steps.
Tool Use
Enhanced structured generation for reliable function calling across multi-step tool chains.
Long-Context Research
A 1M-token window keeps entire repositories, specs and document sets in a single request.
Also strong on research workflows and enhanced structured generation.
Flexible Pricing Tiers
Choose the optimal balance of speed and cost for your workflow. Prices are per 1M tokens.
| Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Batch | $0.66 | $1.98 |
| Async | $0.99 | $2.97 |
| Realtime | $1.32 | $3.96 |
Context window natively supported up to 1,048,576 tokens. We can offer custom pricing for bulk discounts, large workloads, and dedicated deployments — reach out to hello@doubleword.ai.
Start Building in Minutes
DeepSeek V4 Pro 0813 is accessible via OpenAI-compatible endpoints. Default sampling: temperature=1.0, top_p=0.95.
from openai import OpenAI
client = OpenAI(
api_key="your-api-key-here",
base_url="https://api.doubleword.ai/v1"
)
# Long-context agentic coding task
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V4-Pro-0813",
messages=[
{"role": "user", "content": "Plan a refactor of this service and list the tool calls you need."}
],
temperature=1.0,
top_p=0.95,
)
print(response.choices[0].message.content)💡 Pro Tip
Route long-running agent steps through the async tier and bulk evals through batch — same model, same API, at half the realtime rate. See the docs for the batch job format.