DeepSeek: R1 0528✓ Catalog verified
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 in an inference pass. Fully open-source model.
Overview
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 in an inference pass. Fully open-source model.
Access: available through the official DeepSeek API. Context window: 164K.
Specifications
| API identifier | deepseek/deepseek-r1-0528 |
| Provider | DeepSeek |
| Model type | Text LLM |
| Context window | 164K catalog |
| Input modalities | text |
| Output modalities | text |
| Released | May 28, 2025 |
| Tokenizer | DeepSeek |
| Instruction format | deepseek-r1 |
| Moderated | No |
| Architecture modality | text->text |
API defaults
{
"top_p": null,
"temperature": null,
"frequency_penalty": null
}Pricing
Live pricing components for deepseek/deepseek-r1-0528 as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $4.5e-7 | $0.45 / 1M | Per input token |
| Completion tokens | $0.00000215 | $2.15 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.66Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | Not advertised | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | ✓ Supported | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call DeepSeek: R1 0528 through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="deepseek/deepseek-r1-0528",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| Meta: Llama Guard 4 12B | Meta | 164K | $0.18 | View → |
| TNG: DeepSeek R1T2 Chimera | Tngtech | 164K | $0.30 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does DeepSeek: R1 0528 cost?
$0.45 per 1M input tokens and $2.15 per 1M output tokens on the official DeepSeek API.
What is the context window of DeepSeek: R1 0528?
DeepSeek: R1 0528 supports up to 164K tokens of context.
Does DeepSeek: R1 0528 support tool / function calling?
Yes, DeepSeek: R1 0528 supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access DeepSeek: R1 0528?
Use the official DeepSeek API with the model id `deepseek/deepseek-r1-0528`. See the Quick start section above for code examples.