Using DeepSeek V4 Pro 0813 on Together AI
Implementation guide · DeepSeek V4 · DeepSeek
ServerlessProvisioned
Open SourceTogether AI exposes DeepSeek V4 Pro 0813 through model ID deepseek-ai/DeepSeek-V4-Pro-0813. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Together AI SDK or REST API to call
deepseek-ai/DeepSeek-V4-Pro-0813— see the documentation for request format. - 3
Code Examples
Install
pip install togetherAPI key
TOGETHER_API_KEYModel ID
deepseek-ai/DeepSeek-V4-Pro-0813Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
from together import Together
client = Together() # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V4-Pro-0813",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Together AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.32 |
| Output tokens | $3.96 |
Capabilities
Reasoning
About DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is the official (post-preview) DeepSeek V4 Pro release, launched on 2026-08-13 with agent upgrades and flexible reasoning effort. DeepSeek kept the API model name unchanged. MIT-licensed open weights are on Hugging Face as DeepSeek-V4-Pro-0813.
Model Specs
Released2026-08-13
ArchitectureMixture of Experts