The Orchestrator › Models › DeepSeek
DeepSeek: DeepSeek V4.1 Flash 1017 Ultrafast
DeepSeek V4.1 Flash 1017 Ultrafast via TrustedRouter
Specifications
| Provider | DeepSeek |
| Model ID | deepseek/deepseek-v4-1-flash-1017-ultrafast |
| Context window | 1M tokens (1,000,000) |
| Modalities | text + image → text |
| Tokenizer | unknown |
| Router sources | TrustedRouter, Vercel AI Gateway |
| Released | — |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | TrustedRouter | deepseek/deepseek-v4-1-flash-1017-ultrafast | $3.17 | $12.66 | 1M |
| standard | Vercel AI Gateway | deepseek/deepseek-v4.1-flash-1017-ultrafast | $2.40 | $9.60 | 1.0M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $2.40 | $9.60 | 1.0M |
| 2026-11-14 | $3.17 | $12.66 | 1M |
Capabilities
Vision (image input)Agentic tool useStructured outputs1M+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
tools, max_tokens, reasoning, include_reasoning, structured_outputs