DeepSeek-R1
Summary
DeepSeek-R1 is an open-weight language model from DeepSeek, released on 20 Jan 2025. It accepts text and generates text, with a 64K-token context window and up to 33K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.70 per million input tokens and $2.50 per million output tokens (Hugging Face Inference Providers), across 3 providers we track.
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | DeepSeek |
|---|---|
| Release date | 20 Jan 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 684B [Hugging Face] |
| Context window | 64K (64,000 tokens) [models.dev] |
| Max output | 33K tokens [models.dev] |
| Knowledge cutoff | Jul 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | deepseek-ai/DeepSeek-R1 [Hugging Face] |
DeepSeek-R1 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Hugging Face Inference Providers deepseek-ai/DeepSeek-R1 | $0.70 | $2.50 | – | 64K | models.dev, 18 Nov 2026 |
| Novita AI deepseek/deepseek-r1-turbo | $0.70 | $2.50 | – | 64K | models.dev, 18 Nov 2026 |
| Snowflake Cortex deepseek-r1 | – | – | – | 128K | models.dev, 18 Nov 2026 |
Running DeepSeek-R1 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 415 GB | 416 GB | 418 GB |
| Q8_0 (8-bit) | 727 GB | 729 GB | 730 GB |
| FP16 / BF16 (16-bit) | 1369 GB | 1370 GB | 1372 GB |
At 4-bit with an 8K conversation, DeepSeek-R1 needs about 416 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of DeepSeek-R1?
DeepSeek-R1 has a context window of 64,000 tokens (64K) and can generate up to 32,768 tokens in a single response, according to models.dev.
How much does the DeepSeek-R1 API cost?
DeepSeek-R1 is listed from $0.70 per million input tokens and $2.50 per million output tokens (Hugging Face Inference Providers). Prices last verified 18 Nov 2026.
Is DeepSeek-R1 open source?
DeepSeek-R1 is an open-weight model: its weights are published on Hugging Face as deepseek-ai/DeepSeek-R1 under the mit license. Check the license terms before commercial use.
When was DeepSeek-R1 released?
DeepSeek released DeepSeek-R1 on 20 Jan 2025, according to models.dev.
Which providers offer DeepSeek-R1?
We track DeepSeek-R1 on 3 providers: Hugging Face Inference Providers, Novita AI, Snowflake Cortex.
How much VRAM does DeepSeek-R1 need?
About 416 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 729 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Aion-RP 1.0 (8B) | Aion Labs | 4 Feb 2025 | 33K | $0.80 | $1.60 | Open |
| Qwen2.5-VL 72B Instruct | Alibaba (Qwen) | 26 Jan 2025 | 128K | $0.80 | $1 | Open |
| GLM-4.5V | Zhipu AI (Z.ai) | 11 Aug 2025 | 64K | $0.60 | $1.80 | Open |
| Aya Expanse 32B | Cohere | 24 Oct 2024 | 128K | $0.50 | $1.50 | Open |
| Skyfall 36B V2 | Thedrummer | 10 Mar 2025 | 33K | $0.55 | $0.80 | Open |
| Kimi K2 Instruct | Moonshot AI | 11 Jul 2025 | 131K | $0.57 | $2.30 | Open |
Change history
- Max output changed from 16K to 33K
- Name changed from DeepSeek R1 (Turbo) to DeepSeek-R1
- Name changed from DeepSeek-R1 to DeepSeek R1 (Turbo)
- Max output changed from 33K to 16K
- Max output changed from 16K to 33K
- Name changed from DeepSeek R1 (Turbo) to DeepSeek-R1
- Max output changed from 33K to 16K
- Name changed from DeepSeek-R1 to DeepSeek R1 (Turbo)
- No longer listed on cloudflare-workers-ai
- Name changed from Deepseek R1 Distill Qwen 32B to DeepSeek-R1
- Structured output changed from no to yes
- Context window changed from 80K to 64K
- Max output changed from 80K to 33K
- Tool calling changed from no to yes
- Name changed from DeepSeek R1 (Turbo) to Deepseek R1 Distill Qwen 32B
- Max output changed from 16K to 80K
- Tool calling changed from yes to no
- Context window changed from 64K to 80K
- Structured output changed from yes to no
- Max output changed from 33K to 16K
- Name changed from DeepSeek-R1 to DeepSeek R1 (Turbo)
- Name changed from Deepseek R1 Distill Qwen 32B to DeepSeek-R1
- Context window changed from 80K to 64K
- Structured output changed from no to yes
- Max output changed from 80K to 33K
Sources
- https://openrouter.ai/deepseek/deepseek-r1
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/deepseek-ai/DeepSeek-R1.toml
- https://huggingface.co/deepseek-ai/DeepSeek-R1
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/deepseek/deepseek-r1-turbo.toml
- https://github.com/sst/models.dev/blob/dev/providers/snowflake-cortex/models/deepseek-r1.toml