DeepSeek-V4 Pro 现在可在 Together AI 上使用
TL;DR · AI 摘要
Together AI 推出 DeepSeek-V4 Pro 模型，提供高性能推理和多种计算选项。
核心要点
- DeepSeek-V4 Pro 在 NVIDIA Blackwell 上实现 1.3 倍速度提升。
- Together AI 提供 GPU 集群、批量推理 API 和模型微调平台。
- 支持自定义硬件和容器推理，满足多样化需求。
结构提纲
按章节快速跳转。
- §引言
介绍 Together AI 推出 DeepSeek-V4 Pro 模型及其优势。
- ·性能提升
DeepSeek-V4 Pro 在 NVIDIA Blackwell 上实现 1.3 倍速度提升。
- ·计算选项
Together AI 提供 GPU 集群、批量推理 API 和模型微调平台。
支持自定义硬件和容器推理，满足多样化需求。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- Together AI DeepSeek-V4 Pro 发布
- 性能优化
- FlashAttention-4 加速 1.3 倍
- 计算服务
- GPU 集群
- NVIDIA Blackwell 支持
- 模型部署
- 批量推理 API
- 成本降低 50%
金句 / Highlights
值得收藏与分享的关键句。
DeepSeek-V4 Pro 在 NVIDIA Blackwell 上实现 1.3 倍速度提升。
Together AI 提供 GPU 集群、批量推理 API 和模型微调平台。
支持自定义硬件和容器推理，满足多样化需求。
DeepSeek-V4 Pro now available on Together AI
⚡️ FlashAttention-4: up to 1.3× faster than cuDNN on NVIDIA Blackwell →
Introducing Together AI's new look →
🔎 ATLAS: runtime-learning accelerators delivering up to 4x faster LLM inference →
⚡ Together GPU Clusters: self-service NVIDIA GPUs, now generally available →
📦 Batch Inference API: Process billions of tokens at 50% lower cost for most models →
🪛 Fine-Tuning Platform Upgrades: Larger Models, Longer Contexts →
[](https://www.together.ai/)
- 
- 
- 
- 
Nano Banana Pro 
Qwen3.5-397B 
GLM-5 
kimi k2.5 
gpt-oss-120B Model library Explore the top open-source models](https://www.together.ai/models)
Accelerated Compute
- 
- 
Developer Environments
- 
Storage
- 
- 
- 
Llama 4 Maverick Model library Fine-tune top open-source models](https://www.together.ai/models)
- 
- 
Featured publications
- 
- 
- 
- 
Resources
- 
- 
- 
- 
- 
Company
- 
- 
*
- 
- 
- 
- 
* Accelerated Compute
- 
- 
Developer Environments
- 
Storage
- 
*
- 
- 
*
- 
- 
Featured publications
*
- 
- 
- 
- 
* Resources
- 
- 
- 
- 
- 
Company
- 
- 
Model Library
Published 4/29/2026
DeepSeek-V4 Pro now available on Together AI
1.6T-parameter MoE reasoning model with 512K context on Together AI, controllable reasoning modes, and cached-input pricing for long-context workloads.
- Authors Sonny Khan
- Table of contents
- Links in this article Try now
What's New
- **DeepSeek V4 Pro on Together AI:** DeepSeek V4 Pro is now available on Together AI with a 512K-token context window for long-context reasoning workloads.
- Large-scale MoE architecture: DeepSeek V4 Pro uses a 1.6T-parameter Mixture-of-Experts architecture with 49B activated parameters.
- Controllable reasoning modes: Non-Think, Think High, and Think Max let teams choose between fast responses, deeper reasoning, and maximum reasoning effort.
- Transparent serverless pricing: DeepSeek V4 Pro is available at $2.10 per 1M input tokens, $0.20 per 1M cached input tokens, and $4.40 per 1M output tokens.
Long-context reasoning changes what teams can ask a model to do. Entire repositories, large document sets, long agent traces, and tool outputs can fit into the model’s working context instead of being compressed into brittle summaries. But the models that can use that much context are also the hardest to serve: a 1.6T-parameter MoE with million-token context is not something most teams want to deploy, tune, and operate themselves.
DeepSeek-V4 Pro is now available on Together AI, the AI Native Cloud, so teams can start with Serverless Inference at 512K context and move to dedicated infrastucture for full 1M context, reserved capacity, and production control. DeepSeek-V4 Flash is coming soon, giving teams another V4 option for workloads where speed and cost matter more than maximum reasoning depth.
**At a glance**
| Spec | Value | | --- | --- | | Model | DeepSeek V4 Pro on Together AI | | Endpoint | deepseek-ai/DeepSeek-V4-Pro | | Architecture | 1.6T-parameter MoE | | Activated parameters | 49B | | Context on Together AI | 512K tokens | | Model-level context | 1M tokens | | Reasoning modes | Non-Think, Think High, Think Max | | Deployment | Serverless, Monthly Reserved | | Input price | $2.10 / 1M tokens | | Cached input price | $0.20 / 1M tokens | | Output price | $4.40 / 1M tokens | | Best-fit workloads | Code agents, document intelligence, long-context agents, research synthesis |
**Built for long-context reasoning**
DeepSeek V4 Pro is built for workloads where the model needs to reason over more than a short prompt: large repositories, long technical documents, dense retrieval bundles, tool-call histories, and research corpora.
DeepSeek V4 Pro supports million-token context at the model level; on Together AI, it is currently available with a 512K-token context window. That distinction matters because model capability and deployed serving profile are not always the same thing. Together AI is launching DeepSeek V4 Pro with a context window designed for reliable production serving, while still giving teams enough room for serious long-context workloads.
The architecture also matters because long context is not only a product spec. As context grows, serving cost, memory pressure, KV cache usage, latency, and concurrency all become part of the system design. DeepSeek V4 Pro uses hybrid attention, combining Compressed Sparse Attention and Heavily Compressed Attention, with DeepSeek reporting 27% of single-token inference FLOPs and 10% of KV cache compared to DeepSeek V3.2 at million-token context.
**Choose reasoning effort by workload**
DeepSeek V4 Pro supports three reasoning modes, so teams can match reasoning depth to task difficulty instead of treating every request the same.
| Mode | Use when | Tradeoff | | --- | --- | --- | | Non-Think | Extraction, classification, simple Q&A, routine responses | Fastest path for lower-complexity tasks | | Think High | Code planning, document analysis, multi-step reasoning | More reasoning depth for complex work | | Think Max | Hard debugging, deep research synthesis, agentic decision points | Maximum reasoning effort; expect higher latency and token usage |
A document assistant might use Non-Think for simple extraction, Think High for conflict analysis across policies, and Think Max only when the model needs to reason through a difficult decision. A code agent might use Think High for planning a migration and Think Max for debugging a subtle cross-service failure.
DeepSeek reports benchmark results across coding, reasoning, long-context, and agentic tasks, including 93.5% LiveCodeBench, 90.1% GPQA Diamond, 80.6% SWE-bench Verified, 83.5% MRCR 1M, and 62.0% CorpusQA 1M.
**Make repeated long-context queries cheaper with cached input pricing**
Long-context systems often reuse the same large context across multiple questions: a repository snapshot, a document bundle, a policy archive, a retrieval payload, or a long agent trace. Cached input pricing makes those repeated workloads more practical.
DeepSeek V4 Pro is priced at $2.10 / 1M input tokens, with cached input at $0.20 / 1M tokens and output at $4.40 / 1M tokens. That represents a 90% cost reduction for reused context, which matters when the expensive part of the request is a stable block of text that gets reused across follow-up analysis.
Example pattern:
- Load a large stable context, such as a 300K-token repo summary, contract set, or policy archive.
- Ask several follow-up questions over that same context.
- Use cached input pricing where applicable to drastically reduce the cost of repeated analysis.
**Workload patterns**
Code agents
Use DeepSeek V4 Pro when an agent needs to reason across repository slices, issue traces, internal documentation, prior tool calls, and proposed patches. Think High or Think Max is most useful for planning changes, debugging failures, or resolving cross-file dependencies.
Document intelligence
Use long context for contracts, policy sets, technical manuals, or research collections that need to be compared in one request. Non-Think can handle extraction and simple Q&A; Think High is better for conflict analysis, interpretation, and synthesis.
Long-context agent traces
Use DeepSeek V4 Pro to inspect long tool-call histories, intermediate results, and execution traces. Higher reasoning modes are most useful at decision points: when the agent needs to decide whether to continue, call another tool, revise a plan, or stop.
Research synthesis
Use DeepSeek V4 Pro for workflows that combine papers, notes, benchmark reports, retrieved documents, and prior analysis. Cached input pricing is especially useful when the same evidence set is reused across multiple questions.
**Start serverless, move to reserved capacity**
DeepSeek V4 Pro is available on Together AI Serverless Inference and Monthly Reserved infrastructure. Serverless is the right starting point for evaluation, development, and variable traffic. Monthly Reserved is better for steadier production demand where teams need more predictable capacity and cost control.
For long-context workloads, the deployment path matters. Teams are not only choosing a model; they are choosing how to manage throughput, concurrency, latency, KV cache pressure, and cost as context sizes grow. Together AI gives teams a path from evaluation to production without standing up the serving stack themselves.
Try it now
DeepSeek-V4 Pro is available today on Together AI Serverless Inference and Dedicated Endpoints.
from together import Together
client = Together()
stream = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V4-Pro",
messages=[
{
"role": "user",
"content": "Prove that the square root of 2 is irrational.",
}
],
stream=True,
)
for chunk in stream:
if not chunk.choices:
continue
delta = chunk.choices[0].delta
if hasattr(delta, "reasoning") and delta.reasoning:
print(delta.reasoning, end="", flush=True)
if hasattr(delta, "content") and delta.content:
print(delta.content, end="", flush=True)Start with Serverless Inference for development and evaluation. For production workloads that require full 1M context, reserved capacity, workload isolation, or more predictable throughput, contact sales to deploy DeepSeek-V4 Pro on Together AI Dedicated Inference.
Get started
→ Follow our DeepSeek-V4 quickstart to get up and running in minutes
→ View the DeepSeek-V4 Pro Model Page
→ Try DeepSeek-V4 Pro in the Playground
→ Contact Sales for Dedicated Inference deployment and volume pricing
Start building on Together AI
From optimized training and model shaping to large-scale production inference
* Products
- Models
See all modelsDeepSeek Meta Qwen Google OpenAI Mistral AI Custom models * Developers
Pricing
* Resources
© 2026 Together AI. All Rights Reserved.
- [](https://discord.gg/9Rk6sSeWEG)
- [](https://x.com/togethercompute)
- [](https://www.linkedin.com/company/togethercomputer/)