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 Results for other workloads are historical and no longer updated.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 V4 Pro 0424 (Non-reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Pro 0424 (Non-reasoning) for your use-case.
Fastest
Baseten
CoreWeave
Nebius
Azure
DeepSeekOutput speed
Total 6 providers
Lowest Latency
BasetenNebiusCoreWeaveDeepSeekAzureTime to first token
Total 6 providers
Lowest Price
DeepSeek
Bitdeer AICoreWeaveBasetenAzureBlended price (per 1M tokens)
Total 6 providers
DeepSeek V4 Pro (Non-reasoning) 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 Baseten (153.2 t/s), CoreWeave (118.0 t/s), and Nebius (112.3 t/s). Speed varies significantly across providers, with a 60% difference between the fastest and slowest.
- For latency, Baseten (0.72s), Nebius (1.29s), and CoreWeave (1.37s) offer the lowest time to first token.
- For pricing, DeepSeek (0.18), Bitdeer AI (0.66), and CoreWeave (0.69) offer the lowest blended prices per 1M tokens. Prices vary up to 10.9x across providers.
- Baseten offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepSeek 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 Pro 0424 (Non-reasoning)
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First 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 Pro 0424 (Non-reasoning) providers
DeepSeek V4 Pro 0424 (Non-reasoning) is currently available through 6 API providers that we benchmark and track.
The most affordable providers for DeepSeek V4 Pro 0424 (Non-reasoning) by blended price are DeepSeek ($0.18 per 1M tokens), Bitdeer AI ($0.66 per 1M tokens), and CoreWeave ($0.69 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 Pro 0424 (Non-reasoning) are DeepSeek ($0.43 per 1M input tokens), Bitdeer AI ($1.25 per 1M input tokens), and CoreWeave ($1.31 per 1M input tokens).
Output speed for DeepSeek V4 Pro 0424 (Non-reasoning) varies significantly across providers. Baseten is the fastest at 153.2 t/s, which is 1.6x faster than Bitdeer AI at 95.5 t/s.
All 6 providers of DeepSeek V4 Pro 0424 (Non-reasoning) support JSON mode for structured output.
All 6 providers of DeepSeek V4 Pro 0424 (Non-reasoning) support function calling (tool use).
When choosing a provider for DeepSeek V4 Pro 0424 (Non-reasoning), 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 Pro 0424 (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview