This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
DeepSeek has launched a newer model, DeepSeek V3.1. We suggest considering it instead.
For more information, see comparison of DeepSeek V3.1 to other models and API provider benchmarks for DeepSeek V3.1.
DeepSeek R1 0528 (May '25) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek R1 0528 (May '25) for your use-case.
Fastest
Google Vertex
Novita
DeepInfraOutput speed
Total 5 providers
Lowest Latency
Google VertexNovitaDeepInfraTime to first answer token
Total 5 providers
Lowest Price
DeepInfraNovitaGoogle Vertex
Hyperbolic
Together AIBlended price (per 1M tokens)
Total 5 providers
DeepSeek R1 0528 is available through 5 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For output speed, the top providers are Google Vertex (153.8 t/s), Novita (28.1 t/s), and DeepInfra (23.7 t/s).
- For latency, Google Vertex (14.07s), Novita (72.71s), and DeepInfra (85.29s) offer the lowest time to first answer token.
- For pricing, DeepInfra (0.56), Novita (0.88), and Google Vertex (1.76) offer the lowest blended prices per 1M tokens. Prices vary up to 6.1x across providers.
- Google Vertex offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepInfra provides the most competitive pricing.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: DeepSeek R1 0528 (May '25)
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about DeepSeek R1 0528 (May '25) providers
DeepSeek R1 0528 (May '25) is available through 5 API providers: Together AI, Hyperbolic, Google Vertex, Novita, and DeepInfra. Each provider offers different performance characteristics and pricing.
DeepSeek R1 0528 (May '25) is currently available through 5 API providers that we benchmark and track.
The fastest providers for DeepSeek R1 0528 (May '25) by output speed are Google Vertex (153.8 t/s), Novita (28.1 t/s), and DeepInfra (23.7 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first answer token for DeepSeek R1 0528 (May '25) are Google Vertex (14.07s), Novita (72.71s), and DeepInfra (85.29s). Lower latency means faster initial response time.
The most affordable providers for DeepSeek R1 0528 (May '25) by blended price are DeepInfra ($0.56 per 1M tokens), Novita ($0.88 per 1M tokens), and Google Vertex ($1.76 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for DeepSeek R1 0528 (May '25) are DeepInfra ($0.50 per 1M input tokens), Novita ($0.70 per 1M input tokens), and Google Vertex ($1.35 per 1M input tokens).
The providers with the lowest output token pricing for DeepSeek R1 0528 (May '25) are DeepInfra ($2.15 per 1M output tokens), Novita ($2.50 per 1M output tokens), and Hyperbolic ($3.00 per 1M output tokens).
Prices for DeepSeek R1 0528 (May '25) vary up to 6.1x across providers. The most affordable is DeepInfra at $0.56 per 1M tokens, while Together AI charges $3.40 per 1M tokens.
Output speed for DeepSeek R1 0528 (May '25) varies significantly across providers. Google Vertex is the fastest at 153.8 t/s, which is 6.5x faster than DeepInfra at 23.7 t/s.
4 of 5 providers support JSON mode for DeepSeek R1 0528 (May '25): Together AI, Google Vertex, Novita, and DeepInfra.
All 5 providers of DeepSeek R1 0528 (May '25) support function calling (tool use).
For DeepSeek R1 0528 (May '25), Google Vertex offers the best performance with highest speed and lowest latency. For cost optimization, DeepInfra provides the most competitive pricing.
When choosing a provider for DeepSeek R1 0528 (May '25), consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about DeepSeek R1 0528 (May '25)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview