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 Results for other workloads are historical and no longer updated.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 V4 Pro 0813 (max). We suggest considering it instead.
For more information, see comparison of DeepSeek V4 Pro 0813 (max) to other models and API provider benchmarks for DeepSeek V4 Pro 0813 (max).
DeepSeek V4 Pro 0424 (Reasoning, Max Effort) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Pro 0424 (Reasoning, Max Effort) for your use-case.
Fastest
Output speed
Total 10 providers
Lowest Latency
Time to first answer token
Total 10 providers
Lowest Price
Blended price (per 1M tokens)
Total 10 providers
DeepSeek V4 Pro (max) is available through 10 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 (145.6 t/s), Nebius (108.9 t/s), and CoreWeave (87.5 t/s). Speed varies significantly across providers, with a 210% difference between the fastest and slowest.
- For latency, Baseten (30.87s), Nebius (41.50s), and CoreWeave (51.57s) offer the lowest time to first answer token.
- For pricing, DeepSeek (0.18), GMI (0.31), and DeepInfra (FP4) (0.59) 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 (Reasoning, Max 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
1.05M | Open | $1.19 | 48 | 1.32 | 102.25 | 90.58 | |||
1M | Open | $9.65 | 84 | 1.62 | 59.88 | 52.29 | |||
1.05M | Open | $1.09 | 82 | 1.91 | 61.30 | 53.30 | |||
1M | Open | $0.71 | 79 | 2.41 | 64.09 | 55.36 | |||
1.05M | Open | -- | 47 | 2.46 | 105.68 | 92.63 | |||
1M | Open | $1.46 | 87 | 1.55 | 57.28 | 50.02 | |||
1.05M | Open | -- | -- | -- | -- | -- | |||
1M | Open | $9.70 | 103 | 1.32 | 48.45 | 42.30 | |||
1M | Open | $3.73 | 146 | 0.81 | 34.30 | 30.06 | |||
1M | Open | $0.12 | 79 | 1.67 | 63.60 | 55.58 | |||
Frequently Asked Questions
Common questions about DeepSeek V4 Pro 0424 (Reasoning, Max Effort) providers
DeepSeek V4 Pro 0424 (Reasoning, Max Effort) is available through 10 API providers: DeepInfra (FP4), Azure, Novita, Bitdeer AI, SiliconFlow (FP8), CoreWeave, GMI, Nebius, Baseten, and DeepSeek. Each provider offers different performance characteristics and pricing.
DeepSeek V4 Pro 0424 (Reasoning, Max Effort) is currently available through 10 API providers that we benchmark and track.
The most affordable providers for DeepSeek V4 Pro 0424 (Reasoning, Max Effort) by blended price are DeepSeek ($0.18 per 1M tokens), GMI ($0.31 per 1M tokens), and DeepInfra (FP4) ($0.59 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 (Reasoning, Max Effort) are DeepSeek ($0.43 per 1M input tokens), GMI ($0.68 per 1M input tokens), and Bitdeer AI ($1.25 per 1M input tokens).
The providers with the lowest output token pricing for DeepSeek V4 Pro 0424 (Reasoning, Max Effort) are DeepSeek ($0.87 per 1M output tokens), GMI ($1.36 per 1M output tokens), and DeepInfra (FP4) ($2.60 per 1M output tokens).
Output speed for DeepSeek V4 Pro 0424 (Reasoning, Max Effort) varies significantly across providers. Baseten is the fastest at 145.6 t/s, which is 3.1x faster than SiliconFlow (FP8) at 46.9 t/s.
All 10 providers of DeepSeek V4 Pro 0424 (Reasoning, Max Effort) support JSON mode for structured output.
All 10 providers of DeepSeek V4 Pro 0424 (Reasoning, Max Effort) support function calling (tool use).
When choosing a provider for DeepSeek V4 Pro 0424 (Reasoning, Max 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 Pro 0424 (Reasoning, Max Effort)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview