deepseek/deepseek-v4.1-flash-1017-ultrafast idDeepSeek 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.
# Drop-in OpenAI-compatible client$ import { generateText } from 'ai'$$ const { text } = await generateText({$ model: 'deepseek/deepseek-v4.1-flash-1017-ultrafast',$ baseURL: 'https://synapse.garden/api/v1',$ apiKey: process.env.MG_KEY,$ prompt: 'Why is the sky blue?',$ })
| Rate | Per million tokens · USD |
|---|---|
| Input | $2.64/M |
| Output | $10.56/M |
| Cache read | $0.053/M |
Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘deepseek/deepseek-v4.1-flash-1017-ultrafast’ and supply your Synapse Garden API key. No code changes beyond the base URL.
Input: $2.64/M per million tokens. Output: $10.56/M per million tokens. The free tier includes a million tokens every month at no cost.
deepseek-v4.1-flash-1017-ultrafast supports a context window of 1.0M tokens, with a maximum output of 1.0M tokens.
No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.
Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.