Author's Description
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/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.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
DeepSeek: R1 0528, an open-source model with 671B parameters (37B active in inference), demonstrates strong performance across various benchmarks, often on par with proprietary models like OpenAI o1. Its reliability is exceptional, achieving a 100% success rate across all evaluated benchmarks, indicating consistent and usable responses. While excelling in reliability, the model tends to have longer response times, ranking in the 13th percentile for speed. Similarly, its pricing is positioned at premium levels, falling into the 17th percentile for cost-effectiveness. In terms of specific performance, DeepSeek: R1 0528 shows particular strength in Instruction Following (achieving 85% accuracy in one test), Coding (93% accuracy), Reasoning (98% accuracy), and General Knowledge (99.5% accuracy). Its fully open reasoning tokens are a significant advantage for transparency and debugging. However, its performance in the initial Instruction Following benchmark was moderate (50% accuracy), suggesting some variability in this category. The model's primary weaknesses lie in its speed and cost, which are generally higher than many competitors.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.2 |
Completion | $0.8 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
InferenceNet
|
InferenceNet | deepseek/deepseek-r1-0528 | 128K | $0.2 / 1M tokens | $0.8 / 1M tokens |
DeepInfra
|
DeepInfra | deepseek/deepseek-r1-0528 | 163K | $0.5 / 1M tokens | $2.15 / 1M tokens |
Lambda
|
Lambda | deepseek/deepseek-r1-0528 | 163K | $0.5 / 1M tokens | $2.18 / 1M tokens |
Novita
|
Novita | deepseek/deepseek-r1-0528 | 163K | $0.7 / 1M tokens | $2.5 / 1M tokens |
Parasail
|
Parasail | deepseek/deepseek-r1-0528 | 163K | $0.79 / 1M tokens | $4 / 1M tokens |
GMICloud
|
GMICloud | deepseek/deepseek-r1-0528 | 131K | $0.8 / 1M tokens | $2.3 / 1M tokens |
Nebius
|
Nebius | deepseek/deepseek-r1-0528 | 163K | $0.8 / 1M tokens | $2.4 / 1M tokens |
Enfer
|
Enfer | deepseek/deepseek-r1-0528 | 32K | $0.2 / 1M tokens | $0.8 / 1M tokens |
BaseTen
|
BaseTen | deepseek/deepseek-r1-0528 | 163K | $2.55 / 1M tokens | $5.95 / 1M tokens |
Kluster
|
Kluster | deepseek/deepseek-r1-0528 | 163K | $0.2 / 1M tokens | $0.8 / 1M tokens |
Together
|
Together | deepseek/deepseek-r1-0528 | 163K | $3 / 1M tokens | $7 / 1M tokens |
Fireworks
|
Fireworks | deepseek/deepseek-r1-0528 | 163K | $3 / 1M tokens | $8 / 1M tokens |
SambaNova
|
SambaNova | deepseek/deepseek-r1-0528 | 32K | $5 / 1M tokens | $7 / 1M tokens |
DeepSeek
|
DeepSeek | deepseek/deepseek-r1-0528 | 64K | $0.2 / 1M tokens | $0.8 / 1M tokens |
Enfer
|
Enfer | deepseek/deepseek-r1-0528 | 32K | $0.2 / 1M tokens | $0.8 / 1M tokens |
Cent-ML
|
Cent-ML | deepseek/deepseek-r1-0528 | 131K | $0.2 / 1M tokens | $0.8 / 1M tokens |
Crusoe
|
Crusoe | deepseek/deepseek-r1-0528 | 131K | $0.2 / 1M tokens | $0.8 / 1M tokens |
Crusoe
|
Crusoe | deepseek/deepseek-r1-0528 | 131K | $0.5 / 1M tokens | $2.18 / 1M tokens |
Targon
|
Targon | deepseek/deepseek-r1-0528 | 163K | $0.5 / 1M tokens | $2 / 1M tokens |
Chutes
|
Chutes | deepseek/deepseek-r1-0528 | 163K | $0.2 / 1M tokens | $0.8 / 1M tokens |
Google
|
Google | deepseek/deepseek-r1-0528 | 163K | $1.35 / 1M tokens | $5.4 / 1M tokens |
Friendli
|
Friendli | deepseek/deepseek-r1-0528 | 163K | $3 / 1M tokens | $7 / 1M tokens |
Nebius
|
Nebius | deepseek/deepseek-r1-0528 | 32K | $2 / 1M tokens | $6 / 1M tokens |
SiliconFlow
|
SiliconFlow | deepseek/deepseek-r1-0528 | 163K | $0.5 / 1M tokens | $2.18 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by deepseek
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V3.1 | Aug 21, 2025 | ~671B | 131K |
Text input
Text output
|
★★ | ★★★★★ | $$$ |
DeepSeek: DeepSeek V3.1 Base | Aug 20, 2025 | ~671B | 163K |
Text input
Text output
|
★★ | ★ | $$ |
DeepSeek: R1 Distill Qwen 7B Unavailable | May 30, 2025 | 7B | 131K |
Text input
Text output
|
★ | ★ | $$$$ |
DeepSeek: Deepseek R1 0528 Qwen3 8B | May 29, 2025 | 8B | 131K |
Text input
Text output
|
★★★ | ★★★ | $$ |
DeepSeek: DeepSeek Prover V2 | Apr 30, 2025 | ~671B | 131K |
Text input
Text output
|
★★ | ★★★★★ | $$$$ |
DeepSeek: DeepSeek V3 Base Unavailable | Mar 29, 2025 | ~671B | 163K |
Text input
Text output
|
★ | ★ | $$$ |
DeepSeek: DeepSeek V3 0324 | Mar 24, 2025 | ~685B | 163K |
Text input
Text output
|
★★★★ | ★★★★★ | $$ |
DeepSeek: R1 Distill Llama 8B | Feb 07, 2025 | 8B | 32K |
Text input
Text output
|
★ | ★★ | $$ |
DeepSeek: R1 Distill Qwen 1.5B Unavailable | Jan 31, 2025 | 5B | 131K |
Text input
Text output
|
★★★ | ★ | $$$ |
DeepSeek: R1 Distill Qwen 32B | Jan 29, 2025 | 32B | 131K |
Text input
Text output
|
★ | ★★★★★ | $$$ |
DeepSeek: R1 Distill Qwen 14B | Jan 29, 2025 | 14B | 64K |
Text input
Text output
|
★ | ★★ | $$$ |
DeepSeek: R1 Distill Llama 70B | Jan 23, 2025 | 70B | 131K |
Text input
Text output
|
★★★ | ★★★★★ | $$ |
DeepSeek: R1 | Jan 20, 2025 | ~671B | 128K |
Text input
Text output
|
★★★ | ★★★★★ | $$$ |
DeepSeek: DeepSeek V3 | Dec 26, 2024 | — | 163K |
Text input
Text output
|
★★★ | ★★★★★ | $$$ |