The Orchestrator › Models › DeepSeek
DeepSeek: R1 0528
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
Specifications
| Provider | DeepSeek |
| Model ID | deepseek/deepseek-r1-0528 |
| Context window | 164K tokens (163,840) |
| Modalities | text → text |
| Tokenizer | DeepSeek |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-05-28 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | deepseek/deepseek-r1-0528 | $0.5 | $2.15 | 164K |
| standard | TrustedRouter | deepseek/deepseek-r1-0528 | $0.528 | $2.27 | 164K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.528 | $2.27 | 164K |
| 2026-11-14 | $0.5 | $2.15 | 164K |
Capabilities
Agentic tool useStructured outputsReasoning (always on)Controllable reasoningNo content storage (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