DeepSeek
Available in Shortly AI
DeepSeek V4.1 Flash 1017 Ultrafast
Released November 6, 2026
ReasoningVision (Image)Tool Use
DeepSeek V4.1 Flash 1017 Ultrafast serves the October 17, 2026 update of DeepSeek V4.1 Flash through Fireworks' accelerated serverless endpoint. It supports text and image input, configurable reasoning, tool calling, structured outputs, and automatic prefix caching. Available in public preview without a waitroom or session time limit.
- Context window
- 1M tokens
- Maximum output
- 1M tokens
- Input pricing
- $2.40/M
- Output pricing
- $9.60/M
FAQ
Similar AI models
GPT-6.1 TerraOpenAIA fast reasoning model for writing, image analysis, and tool-assisted work.Kimi K3.1 ProMoonshot AIA long-context reasoning model with image input, tool calling, and structured outputs.Gemini 4 ArgonGoogleA multimodal reasoning model for complex tasks spanning documents, images, and code.
Available with one subscription
Start with DeepSeek V4.1 Flash 1017 Ultrafast in Shortly AI
Keep your conversations, files and model choices together in one workspace.