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 Results for other workloads are historical and no longer updated.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 V4.1 Flash. We suggest considering it instead.
DeepSeek V4 Flash 0731 (Max) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Flash 0731 (Max) for your use-case.
Fastest
PrimaLabs
Systalyze
Baseten
DeepSeek
CrusoeOutput speed
Total 17 providers
Lowest Latency
PrimaLabsSystalyzeBasetenDeepSeekCrusoeTime to first answer token
Total 17 providers
Lowest Price
DeepInfraPrimaLabs
Bitdeer AISystalyzeBasetenBlended price (per 1M tokens)
Total 17 providers
DeepSeek V4 Flash 0731 (max) is available through 17 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 PrimaLabs (325.4 t/s), Systalyze (322.1 t/s), and Baseten (282.4 t/s). Speed varies significantly across providers, with a 722% difference between the fastest and slowest.
- For latency, PrimaLabs (6.63s), Systalyze (7.46s), and Baseten (7.68s) offer the lowest time to first answer token.
- For pricing, DeepInfra (0.04), PrimaLabs (0.06), and Bitdeer AI (0.06) offer the lowest blended prices per 1M tokens. Prices vary up to 5.9x across providers.
- PrimaLabs offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepInfra 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 0731 (Max)
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
 CoreWeave | 262k | Open | $0.44 | 88 | 1.64 | 30.10 | 22.77 | ||
 Wafer | 1M | Open | $0.54 | 90 | 0.78 | 28.59 | 22.25 | ||
| Systalyze | 1.05M | Open | $0.16 | 318 | 1.18 | 9.04 | 6.29 | ||
 Nebius | 1.05M | Open | $0.65 | 70 | 1.95 | 37.71 | 28.60 | ||
| DeepSeek | 1M | Open | $0.22 | 216 | 0.97 | 12.53 | 9.24 | ||
| Bitdeer AI | 1M | Open | $0.27 | 167 | 2.04 | 17.03 | 11.99 | ||
 Parasail | 1.05M | Open | -- | 67 | 1.22 | 38.80 | 30.06 | ||
 SiliconFlow | 1.05M | Open | $0.15 | 44 | 2.13 | 58.62 | 45.19 | ||
| Baseten | 1.05M | Open | $0.42 | 291 | 0.56 | 9.16 | 6.87 | ||
| Crusoe | 1.05M | Open | $0.19 | 163 | 0.96 | 16.32 | 12.29 | ||
 GMI | 1.05M | Open | -- | 127 | 2.64 | 22.38 | 15.79 | ||
 Novita | 1.05M | Open | $0.26 | 122 | 1.61 | 22.04 | 16.34 | ||
| DeepInfra | 1M | Open | $0.10 | 42 | 1.04 | 59.93 | 47.11 | ||
 DigitalOcean | 1.05M | Open | $0.16 | 62 | 0.88 | 40.92 | 32.03 | ||
 Makora | 1M | Open | $0.42 | 83 | 0.86 | 31.11 | 24.21 | ||
| PrimaLabs | 1.05M | Open | $0.06 | 309 | 0.58 | 8.68 | 6.48 | ||
 Fireworks | 1.05M | Open | $0.09 | -- | -- | -- | -- | ||
Frequently Asked Questions
Common questions about DeepSeek V4 Flash 0731 (Max) providers
DeepSeek V4 Flash 0731 (Max) is available through 17 API providers: CoreWeave, Wafer (FAST), Systalyze, Nebius, DeepSeek, Bitdeer AI, Parasail, SiliconFlow, Baseten, Crusoe, GMI, Novita, DeepInfra, DigitalOcean, Makora, PrimaLabs, and Fireworks. Each provider offers different performance characteristics and pricing.
DeepSeek V4 Flash 0731 (Max) is currently available through 17 API providers that we benchmark and track.
The most affordable providers for DeepSeek V4 Flash 0731 (Max) by blended price are DeepInfra ($0.04 per 1M tokens), PrimaLabs ($0.06 per 1M tokens), and Bitdeer AI ($0.06 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
Output speed for DeepSeek V4 Flash 0731 (Max) varies significantly across providers. PrimaLabs is the fastest at 325.4 t/s, which is 8.2x faster than SiliconFlow at 39.6 t/s.
All 17 providers of DeepSeek V4 Flash 0731 (Max) support JSON mode for structured output.
All 17 providers of DeepSeek V4 Flash 0731 (Max) support function calling (tool use).
When choosing a provider for DeepSeek V4 Flash 0731 (Max), 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 0731 (Max)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview