The Orchestrator › Models › DeepSeek
DeepSeek: DeepSeek V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Specifications
| Provider | DeepSeek |
| Model ID | deepseek/deepseek-chat-v3.1 |
| Context window | 164K tokens (163,840) |
| Modalities | text → text |
| Tokenizer | DeepSeek |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2025-08-21 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | deepseek/deepseek-chat-v3.1 | $0.25 | $0.95 | 164K |
| alias | OpenRouter | deepseek/deepseek-chat | $0.257 | $1.03 | 164K |
| standard | TrustedRouter | deepseek/deepseek-v3.1 | $0.264 | $1.00 | 164K |
| standard | Vercel AI Gateway | deepseek/deepseek-v3.1 | $0.25 | $0.95 | 164K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.25 | $0.95 | 164K |
| 2026-11-14 | $0.264 | $1.00 | 164K |
| 2026-11-14 | $0.25 | $0.95 | 164K |
Capabilities
Agentic tool useStructured outputsControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p