DeepSeek
Available in Shortly AI
DeepSeek V4.1 Flash 1017
Released October 17, 2026
ReasoningVision (Image)Tool Use
DeepSeek V4.1 Flash 1017 served by Baseten for multimodal reasoning, tool calling, and structured output, with automatic prefix caching.
- Context window
- 1M tokens
- Maximum output
- 262.1K tokens
- Input pricing
- $0.30/M
- Output pricing
- $1.20/M
Independent benchmark
LiveBench performance
72.9overall
Benchmark data from LiveBench 2.0, release 2026-10-25.
35.7
89.1
96.0
67.2
79.5
79.5
83.4
| Category | Score |
|---|---|
| Long Agentic | 35.700 |
| Reasoning | 89.100 |
| Coding | 96.000 |
| Browser Use | 67.200 |
| Data Analysis | 79.500 |
| Research | 79.500 |
| Design | 83.400 |
Benchmarks measure selected evaluation tasks and do not guarantee performance for every prompt or workflow.
FAQ
Similar AI models
ApexCallstackApex is Callstack’s agentic coding model for mobile and web development, optimized for React Native, React, and Next.js. With a 256K context window, it supports feature development, debugging, code reviews, testing, and large refactors.Mistral Large 4MistralMistral Large 4 is Mistral AI's open-weight, natively multimodal model, available in public preview with 1.05 trillion total parameters and 49 billion active parameters. It leads aggregated benchmarks among open-weight models from the US and Europe, with strengths in cyber defense, manufacturing, finance, and visual grounding.MiMo V2.6 ProXiaomiMiMo V2.6 Pro is Xiaomi's flagship multimodal reasoning model for complex software engineering, long-running agent tasks, and professional workflows. It supports text, image, audio, and video inputs with a 1M-token context window and up to 128K tokens of output. Deep thinking, tool calling, JSON mode, and prompt caching support applications that combine large inputs with multi-step reasoning.
Available with one subscription
Start with DeepSeek V4.1 Flash 1017 in Shortly AI
Keep your conversations, files and model choices together in one workspace.