The Orchestrator › Models › DeepSeek
DeepSeek: DeepSeek-R1
DeepSeek-R1 provides customers a state-of-the-art reasoning model, optimized for general reasoning tasks, math, science, and code generation.
Specifications
| Provider | DeepSeek |
| Model ID | deepseek/deepseek-r1 |
| Context window | 128K tokens (128,000) |
| Modalities | text → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2025-01-20 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | deepseek/deepseek-r1 | $1.35 | $5.40 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.35 | $5.40 | 128K |
Capabilities
Agentic tool useControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning