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 Results for other workloads are historical and no longer updated.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 release, DeepSeek V4 Flash 0731. We suggest considering it instead.
DeepSeek V4 Flash 0420 (Reasoning, High Effort) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Flash 0420 (Reasoning, High Effort) for your use-case.
Fastest
Novita
Makora
Parasail (FP8)
SiliconFlow (FP8)
DeepInfra (FP4)Output speed
Total 6 providers
Lowest Latency
NovitaMakoraParasail (FP8)SiliconFlow (FP8)DeepInfra (FP4)Time to first answer token
Total 6 providers
Lowest Price
DeepInfra (FP4)
GMISiliconFlow (FP8)NovitaMakoraBlended price (per 1M tokens)
Total 6 providers
DeepSeek V4 Flash (high) 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 Novita (142.2 t/s), Makora (88.4 t/s), and Parasail (FP8) (73.1 t/s). Speed varies significantly across providers, with a 288% difference between the fastest and slowest.
- For latency, Novita (10.31s), Makora (14.84s), and Parasail (FP8) (18.51s) offer the lowest time to first answer token.
- For pricing, DeepInfra (FP4) (0.05), GMI (0.05), and SiliconFlow (FP8) (0.07) offer the lowest blended prices per 1M tokens. Prices vary up to 2.2x across providers.
- Novita offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepInfra (FP4) 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 V4 Flash 0420 (Reasoning, High Effort)
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 V4 Flash 0420 (Reasoning, High Effort) providers
DeepSeek V4 Flash 0420 (Reasoning, High Effort) is available through 6 API providers: DeepInfra (FP4), GMI, Makora, Parasail (FP8), SiliconFlow (FP8), and Novita. Each provider offers different performance characteristics and pricing.
DeepSeek V4 Flash 0420 (Reasoning, High Effort) is currently available through 6 API providers that we benchmark and track.
The fastest providers for DeepSeek V4 Flash 0420 (Reasoning, High Effort) by output speed are Novita (142.2 t/s), Makora (88.4 t/s), and Parasail (FP8) (73.1 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 V4 Flash 0420 (Reasoning, High Effort) are Novita (10.31s), Makora (14.84s), and Parasail (FP8) (18.51s). Lower latency means faster initial response time.
The most affordable providers for DeepSeek V4 Flash 0420 (Reasoning, High Effort) by blended price are DeepInfra (FP4) ($0.05 per 1M tokens), GMI ($0.05 per 1M tokens), and SiliconFlow (FP8) ($0.07 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 V4 Flash 0420 (Reasoning, High Effort) are DeepInfra (FP4) ($0.09 per 1M input tokens), Makora ($0.09 per 1M input tokens), and GMI ($0.09 per 1M input tokens).
The providers with the lowest output token pricing for DeepSeek V4 Flash 0420 (Reasoning, High Effort) are DeepInfra (FP4) ($0.18 per 1M output tokens), GMI ($0.19 per 1M output tokens), and Makora ($0.20 per 1M output tokens).
Prices for DeepSeek V4 Flash 0420 (Reasoning, High Effort) vary up to 2.2x across providers. The most affordable is DeepInfra (FP4) at $0.05 per 1M tokens, while Parasail (FP8) charges $0.11 per 1M tokens.
Output speed for DeepSeek V4 Flash 0420 (Reasoning, High Effort) varies significantly across providers. Novita is the fastest at 142.2 t/s, which is 3.9x faster than DeepInfra (FP4) at 36.7 t/s.
All 6 providers of DeepSeek V4 Flash 0420 (Reasoning, High Effort) support JSON mode for structured output.
All 6 providers of DeepSeek V4 Flash 0420 (Reasoning, High Effort) support function calling (tool use).
For DeepSeek V4 Flash 0420 (Reasoning, High Effort), Novita offers the best performance with highest speed and lowest latency. For cost optimization, DeepInfra (FP4) provides the most competitive pricing.
When choosing a provider for DeepSeek V4 Flash 0420 (Reasoning, High Effort), 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 V4 Flash 0420 (Reasoning, High Effort)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview