DeepSeek-R1-0528
deepseek/r1-0528От DeepSeek · семейство: deepseek-thinking · выпуск 2025-05-28 · дата знаний: 2024-07
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Возможности
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding64
- Tool calling40/40
- Structured output0/20
- Reasoning10/10
- Context window (100K → 1M)4/20
- Provider availability10/10
Agents75
- Tool calling35/35
- Structured output0/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output46
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume16/20
Cost efficiency54
- Headline price (log-scaled)54/95
- Has prompt-cache pricing0/5
Long context51
- Context window (100K → 2M)41/90
- Has published price for full window10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $2.85 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $5.70 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $1.65 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $4.90 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $5.82 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Детализация цен
Рекомендованная цена от nano-gpt · deepseek-ai/DeepSeek-R1-0528
Самый дешёвый провайдер: github-models · Unknown вход + Unknown выход
Доступна у 19 провайдеров
| Провайдер | ID модели провайдера | Вход / 1M | Выход / 1M | Контекст | Выпуск |
|---|---|---|---|---|---|
| Azure azure | deepseek-r1-0528 | $1.35 | $5.40 | 164K | 2025-05-28 |
| Deep Infra deepinfra | deepseek-ai/DeepSeek-R1-0528 | $0.500 | $2.15 | 164K | 2025-05-28 |
| Hugging Face huggingface | deepseek-ai/DeepSeek-R1-0528 | $3.00 | $5.00 | 164K | 2025-05-28 |
| NanoGPT nano-gpt | TEE/deepseek-r1-0528 | $2.00 | $2.00 | 128K | 2025-05-28 |
| NanoGPT nano-gpt | deepseek-ai/DeepSeek-R1-0528 | $0.400 | $1.70 | 128K | 2025-05-28 |
| submodel submodel | deepseek-ai/DeepSeek-R1-0528 | $0.500 | $2.15 | 75K | 2025-08-23 |
| IO.NET io-net | deepseek-ai/DeepSeek-R1-0528 | $2.00 | $8.75 | 128K | 2025-01-20 |
| Alibaba (China) alibaba-cn | deepseek-r1-0528 | $0.574 | $2.29 | 131K | 2025-05-28 |
| Alibaba (China) alibaba-cn | siliconflow/deepseek-r1-0528 | $0.500 | $2.18 | 164K | 2025-05-28 |
| Jiekou.AI jiekou | deepseek/deepseek-r1-0528 | $0.700 | $2.50 | 164K | 2026-01 |
| NovitaAI novita-ai | deepseek/deepseek-r1-0528 | $0.700 | $2.50 | 164K | 2025-05-28 |
| Qiniu qiniu-ai | deepseek-r1-0528 | Unknown | Unknown | 128K | 2025-08-05 |
| Kilo Gateway kilo | deepseek/deepseek-r1-0528 | $0.450 | $2.15 | 164K | 2025-05-28 |
| Azure Cognitive Services azure-cognitive-services | deepseek-r1-0528 | $1.35 | $5.40 | 164K | 2025-05-28 |
| Meganova meganova | deepseek-ai/DeepSeek-R1-0528 | $0.500 | $2.15 | 164K | 2025-05-28 |
| Synthetic synthetic | hf:deepseek-ai/DeepSeek-R1-0528 | $3.00 | $8.00 | 128K | 2025-08-01 |
| Cortecs cortecs | deepseek-r1-0528 | $0.585 | $2.31 | 164K | 2025-05-28 |
| LLM Gateway llmgateway | deepseek-r1-0528 | $0.800 | $2.40 | 64K | 2025-05-28 |
| GitHub Models github-models | deepseek/deepseek-r1-0528 | Unknown | Unknown | 66K | 2025-05-28 |
Расхождения данных между провайдерами
- context_window varies: 128000, 131072, 163840, 164000, 64000, 65536, 75000
- release_date varies (span 346d): 2025-01-20, 2025-05-28, 2025-08-01, 2025-08-05, 2025-08-23, 2026-01
Провайдеры сообщают разные значения для этой модели. Сводка выше использует репрезентативного провайдера; детали — в таблице.
Frequently asked questions
How much does DeepSeek-R1-0528 cost?
DeepSeek-R1-0528 costs $0.400 per 1M input tokens and $1.70 per 1M output tokens, sourced from nano-gpt. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of DeepSeek-R1-0528?
DeepSeek-R1-0528 has a context window of 164K tokens, with a max output of 164K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek-R1-0528 support tool calling?
Yes. DeepSeek-R1-0528 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does DeepSeek-R1-0528 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for DeepSeek-R1-0528 in our data source. Verify with DeepSeek's official documentation before relying on it in production.
Can DeepSeek-R1-0528 accept image input?
No. DeepSeek-R1-0528 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is DeepSeek-R1-0528 open-weight?
Yes. DeepSeek-R1-0528's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to DeepSeek-R1-0528?
If DeepSeek-R1-0528 doesn't fit, consider DeepSeek-V3.2, DeepSeek V4 Pro, DeepSeek-R1. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More DeepSeek models
- DeepSeek-V3.2$0.26 in / $0.38 out
- DeepSeek V4 Pro$1.74 in / $3.48 out
- DeepSeek-R1$0.40 in / $1.70 out
- DeepSeek-V3.1$0.20 in / $0.70 out
- DeepSeek V4 Flash$0.14 in / $0.28 out
Capability lists this model is in
Последнее обновление:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.