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 Results for other workloads are historical and no longer updated.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 V3.1 Terminus. We suggest considering it instead.
DeepSeek V3.1 (Non-reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V3.1 (Non-reasoning) for your use-case.
Fastest
SambaNova
Amazon
CoreWeave
DeepInfra (FP4)Output speed
Total 7 providers
Lowest Latency
CoreWeaveAmazonDeepInfra (FP4)SambaNovaTime to first token
Total 7 providers
Lowest Price
DeepInfra (FP4)
NovitaCoreWeave
FireworksAmazonBlended price (per 1M tokens)
Total 7 providers
DeepSeek V3.1 (non-reasoning) is available through 7 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 SambaNova (180.0 t/s), Amazon (166.4 t/s), and CoreWeave (70.3 t/s). Speed varies significantly across providers, with a 1982% difference between the fastest and slowest.
- For latency, CoreWeave (1.29s), Amazon (1.41s), and DeepInfra (FP4) (1.69s) offer the lowest time to first token.
- For pricing, DeepInfra (FP4) (0.24), Novita (0.25), and CoreWeave (0.66) offer the lowest blended prices per 1M tokens. Prices vary up to 13.3x across providers.
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 V3.1 (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 V3.1 (Non-reasoning) providers
DeepSeek V3.1 (Non-reasoning) is available through 7 API providers: Amazon, CoreWeave, Novita, Together AI, Fireworks, DeepInfra (FP4), and SambaNova. Each provider offers different performance characteristics and pricing.
DeepSeek V3.1 (Non-reasoning) is currently available through 7 API providers that we benchmark and track.
The providers with the lowest time to first token for DeepSeek V3.1 (Non-reasoning) are CoreWeave (1.29s), Amazon (1.41s), and DeepInfra (FP4) (1.69s). Lower latency means faster initial response time.
The most affordable providers for DeepSeek V3.1 (Non-reasoning) by blended price are DeepInfra (FP4) ($0.24 per 1M tokens), Novita ($0.25 per 1M tokens), and CoreWeave ($0.66 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 V3.1 (Non-reasoning) are DeepInfra (FP4) ($0.25 per 1M input tokens), Novita ($0.27 per 1M input tokens), and CoreWeave ($0.55 per 1M input tokens).
The providers with the lowest output token pricing for DeepSeek V3.1 (Non-reasoning) are DeepInfra (FP4) ($0.95 per 1M output tokens), Novita ($1.00 per 1M output tokens), and CoreWeave ($1.65 per 1M output tokens).
Prices for DeepSeek V3.1 (Non-reasoning) vary up to 13.3x across providers. The most affordable is DeepInfra (FP4) at $0.24 per 1M tokens, while SambaNova charges $3.15 per 1M tokens.
Output speed for DeepSeek V3.1 (Non-reasoning) varies significantly across providers. SambaNova is the fastest at 180.0 t/s, which is 20.8x faster than DeepInfra (FP4) at 8.6 t/s.
5 of 7 providers support JSON mode for DeepSeek V3.1 (Non-reasoning): CoreWeave, Novita, Fireworks, DeepInfra (FP4), and SambaNova.
The best provider for DeepSeek V3.1 (Non-reasoning) depends on your priorities: SambaNova offers the highest output speed, CoreWeave has the lowest latency, and DeepInfra (FP4) provides the most competitive pricing.
When choosing a provider for DeepSeek V3.1 (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 V3.1 (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview