AI Recommendation
Should you use DeepSeek-V4-Pro-0813?
DeepSeek-V4-Pro-0813 is listed for chat workloads and supports a 8K context window.
Use it when ModelScope's free tier is enough for evaluation, demos, or light production traffic.
DeepSeek-V4-Pro-0813 Free API on ModelScope
Free API VerifiedDeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
Free APIOpenAI compatibleReasoningTool callingJSON mode
API Details
Copy-ready connection details
Base URL
https://api-inference.modelscope.cn/v1 Model ID
deepseek-ai/DeepSeek-V4-Pro-0813 API format OpenAI Chat Completions + OpenAI Responses
Technical Details
DeepSeek-V4-Pro-0813 specifications
Context window 8K
Max output 4K
Status Online
Family deepseek-thinking
Released Aug 12, 2026
Last updated Aug 22, 2026
Free listing since Aug 13, 2026
Input text
Output text
Capabilities reasoning, tool calling, structured output, temperature control
Open weights Yes
Weights Hugging Face
External benchmark references
| Benchmark | Score | Metric | Date |
|---|---|---|---|
| Humanity's Last Exam | 42.7 | score | Not listed |
| Humanity's Last Exam | 60 | score | Not listed |
| Terminal-Bench | 87.9 | score | Not listed |
| NL2Repo | 61.5 | score | Not listed |
Best for
- Chat
Strengths & Weaknesses
Strengths
- Reasoning mode listed
- Tool calling support
- Structured JSON output
- Open weights available
Watch outs
- Vision support is not listed
Benchmark Overview
Benchmark signals for DeepSeek-V4-Pro-0813
Intelligence General reasoning and instruction following
36/100 Coding Programming and code generation
68.8/100 Agentic Tool use and multi-step tasks
41.3/100 Speed Observed generation speed
116 tok/s Context Maximum listed context window
8K Pricing
DeepSeek-V4-Pro-0813 pricing per 1M tokens
Input $1.32 per 1M tokens
Output $3.96 per 1M tokens
Access Available ModelScope
Availability
DeepSeek-V4-Pro-0813 availability by provider
We only found this deepseek-v4-pro-0813 listing on ModelScope in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | deepseek-ai/DeepSeek-V4-Pro-0813 | Free tier | 8K | Native | Varies |
Compare
DeepSeek-V4-Pro-0813 alternatives to consider
| Model | Provider | Context | Access |
|---|---|---|---|
| Qwen/Qwen3.5-35B-A3B | ModelScope | 256K | Check provider |
| Qwen/Qwen3.5-27B | ModelScope | 256K | Check provider |
| MiniMax-M2.5-highspeed | ModelScope | 205K | Check provider |
| Kimi K2.5 | ModelScope | 262K | Check provider |
| Qwen/Qwen-Image | ModelScope | 131K | Check provider |
Typical Use Cases
DeepSeek-V4-Pro-0813 use cases
Chat
DeepSeek-V4-Pro-0813 is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
FAQ
DeepSeek-V4-Pro-0813 free API FAQ
Is DeepSeek-V4-Pro-0813 free to use?
DeepSeek-V4-Pro-0813 is listed with free API access on ModelScope, subject to the provider's quota and account policy.
What is the DeepSeek-V4-Pro-0813 model ID?
The model ID shown in this catalog is deepseek-ai/DeepSeek-V4-Pro-0813.
What context window does DeepSeek-V4-Pro-0813 support?
The listed context window is 8K tokens with up to 4K output tokens.
More about DeepSeek-V4-Pro-0813
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
For API keys, setup steps, and provider-level limits, see the ModelScope provider page.