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 Results for other workloads are historical and no longer updated.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 R1 0528. We suggest considering it instead.

For more information, see comparison of DeepSeek R1 0528 to other models and API provider benchmarks for DeepSeek R1 0528.

DeepSeek R1 (Jan '25) logo
DeepSeek
•

Open weights model

•

Released January 2025

DeepSeek R1 (Jan '25) API Provider Benchmarking & Analysis

Model Comparison

Analysis of API providers for DeepSeek R1 (Jan '25) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Amazon Bedrock, Novita Turbo, Together AI, Novita, Microsoft Azure, and Hyperbolic.

Fastest

#1
AmazonAmazon
171.5 t/s
#2
Novita TurboNovita Turbo
22.8 t/s

Output speed

Total 6 providers

Lowest Latency

#1
AmazonAmazon
14.78 s
#2
Novita TurboNovita Turbo
104.40 s

Time to first answer token

Total 6 providers

Lowest Price

#1
Novita TurboNovita Turbo
$0.88
#2
AmazonAmazon
$1.76
#3
AzureAzure
$1.76
#4
HyperbolicHyperbolic
$2.00
#5
Together AITogether AI
$3.40

Blended price (per 1M tokens)

Total 6 providers

DeepSeek R1 (Jan) is available through 6 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 Amazon (171.5 t/s) and Novita Turbo (22.8 t/s).
  • For latency, Amazon (14.78s) and Novita Turbo (104.40s) offer the lowest time to first answer token.
  • For pricing, Novita Turbo (0.88), Amazon (1.76), and Azure (1.76) offer the lowest blended prices per 1M tokens. Prices vary up to 4.5x across providers.
  • Amazon offers the best performance with both the highest speed and lowest latency. For cost optimization, Novita Turbo provides the most competitive pricing.

Highlights

Speed

Output tokens per second · Higher is better

End-to-End Response Time

Seconds · Lower is better

Price

USD per 1M tokens (blended) · Lower is better

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Speed

Measured by Output Speed (tokens per second)

Output Speed: DeepSeek R1 (Jan '25)

Output speed: output tokens per second · 10,000 input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
Most attractive quadrant

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

Seconds to first token received · Lower is better · 10,000 input tokens

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

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

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Key Comparison Metrics & API Features

Amazon Bedrock logoAmazon Bedrock
128k
Open
$0.26
164
1.11
18.43
14.29
Novita logoNovita
64k
Open
$0.13
--
--
--
--
Novita logoNovita
64k
Open
$0.57
--
--
--
--
Together AI logoTogether AI
164k
Open
$0.50
--
--
--
--
Microsoft Azure logoMicrosoft Azure
128k
Open
$0.26
--
--
--
--
Hyperbolic logoHyperbolic
164k
Open
$0.29
--
--
--
--

Frequently Asked Questions

Common questions about DeepSeek R1 (Jan '25) providers

DeepSeek R1 (Jan '25) is available through 6 API providers: Amazon, Novita Turbo, Together AI, Novita, Azure, and Hyperbolic. Each provider offers different performance characteristics and pricing.

DeepSeek R1 (Jan '25) is currently available through 6 API providers that we benchmark and track.

The fastest providers for DeepSeek R1 (Jan '25) by output speed are Amazon (171.5 t/s) and Novita Turbo (22.8 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 (Jan '25) are Amazon (14.78s) and Novita Turbo (104.40s). Lower latency means faster initial response time.

The most affordable providers for DeepSeek R1 (Jan '25) by blended price are Novita Turbo ($0.88 per 1M tokens), Amazon ($1.76 per 1M tokens), and Azure ($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 (Jan '25) are Novita Turbo ($0.70 per 1M input tokens), Amazon ($1.35 per 1M input tokens), and Azure ($1.35 per 1M input tokens).

The providers with the lowest output token pricing for DeepSeek R1 (Jan '25) are Hyperbolic ($2.00 per 1M output tokens), Novita Turbo ($2.50 per 1M output tokens), and Novita ($4.00 per 1M output tokens).

Prices for DeepSeek R1 (Jan '25) vary up to 4.5x across providers. The most affordable is Novita Turbo at $0.88 per 1M tokens, while Novita charges $4.00 per 1M tokens.

Output speed for DeepSeek R1 (Jan '25) varies significantly across providers. Amazon is the fastest at 171.5 t/s, which is 7.5x faster than Novita Turbo at 22.8 t/s.

3 of 6 providers support JSON mode for DeepSeek R1 (Jan '25): Novita Turbo, Novita, and Azure.

4 of 6 providers support function calling for DeepSeek R1 (Jan '25): Novita Turbo, Together AI, Novita, and Hyperbolic.

For DeepSeek R1 (Jan '25), Amazon offers the best performance with highest speed and lowest latency. For cost optimization, Novita Turbo provides the most competitive pricing.

When choosing a provider for DeepSeek R1 (Jan '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 (Jan '25)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview