This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
DeepSeek has launched a newer release, DeepSeek V4 Flash 0731. We suggest considering it instead.
DeepSeek V4 Flash 0420 (High) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Flash 0420 (High) for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 4 providers
Lowest Cost per Task
Cost per Intelligence Index task
Total 4 providers
DeepSeek V4 Flash (high) is available through 4 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
Please see the models page for DeepSeek V4 Flash 0420 (High) for details of the model and its intelligence compared to other models.
Pricing
Cost per Intelligence Index Task: DeepSeek V4 Flash 0420 (High)
Pricing: Cache Hit, Input, and Output: DeepSeek V4 Flash 0420 (High)
Output Speed vs. Cost per Task: DeepSeek V4 Flash 0420 (High)
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: DeepSeek V4 Flash 0420 (High)
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: DeepSeek V4 Flash 0420 (High)
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: DeepSeek V4 Flash 0420 (High)
Caching
Cache Hit Rate: DeepSeek V4 Flash 0420 (High)
Cost per Task vs. Cache Hit Rate: DeepSeek V4 Flash 0420 (High)
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about DeepSeek V4 Flash 0420 (High) providers
DeepSeek V4 Flash 0420 (High) is available through 4 API providers: DeepInfra (FP4), GMI, Parasail (FP8), and SiliconFlow (FP8). Each provider offers different performance characteristics and pricing.
DeepSeek V4 Flash 0420 (High) is currently available through 4 API providers that we benchmark and track.
The most affordable providers for DeepSeek V4 Flash 0420 (High) by blended price are DeepInfra (FP4) ($0.0486 per 1M tokens), GMI ($0.0508 per 1M tokens), and SiliconFlow (FP8) ($0.0736 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 (High) are DeepInfra (FP4) ($0.09 per 1M input tokens), GMI ($0.0938 per 1M input tokens), and SiliconFlow (FP8) ($0.13 per 1M input tokens).
The providers with the lowest output token pricing for DeepSeek V4 Flash 0420 (High) are DeepInfra (FP4) ($0.18 per 1M output tokens), GMI ($0.19 per 1M output tokens), and Parasail (FP8) ($0.28 per 1M output tokens).
Prices for DeepSeek V4 Flash 0420 (High) vary up to 2.2x across providers. The most affordable is DeepInfra (FP4) at $0.0486 per 1M tokens, while Parasail (FP8) charges $0.11 per 1M tokens.
All 4 providers of DeepSeek V4 Flash 0420 (High) support JSON mode for structured output.
All 4 providers of DeepSeek V4 Flash 0420 (High) support function calling (tool use).
When choosing a provider for DeepSeek V4 Flash 0420 (High), consider: time per task (how quickly the provider completes an Intelligence Index task), 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 (High)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview