DeepSeek has launched a newer model, DeepSeek V3.1, we suggest considering this model instead.
For more information, see Comparison of DeepSeek V3.1 to other models and API provider benchmarks for DeepSeek V3.1.
DeepSeek V3 0324 API Provider Benchmarking & Analysis
Analysis of API providers for DeepSeek V3 0324 across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Nebius Fast, Microsoft Azure, Hyperbolic, Nebius, SambaNova, Together.ai, Replicate, Fireworks, Novita, DeepInfra.
This model is an updated version of DeepSeek V3 and was launched on 24 March 2025 as DeepSeek-V3-0324. It is architecturally identical to the original December 2024 version of DeepSeek V3.
Fastest
SambaNova
Fireworks
Nebius Fast
Azure
ReplicateOutput speed
Total 10 providers
Lowest Latency
Fireworks
DeepInfraSambaNovaNebiusAzureTime to first token
Total 10 providers
Lowest Price
DeepInfra
NovitaNebiusFireworks
HyperbolicBlended price (per 1M tokens)
Total 10 providers
DeepSeek V3 0324 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 SambaNova (267.2 t/s), Fireworks (234.9 t/s), Nebius Fast (183.7 t/s). Speed varies significantly across providers, with a 313% difference between the fastest and slowest.
- For latency, Fireworks (0.47s), DeepInfra (0.55s), SambaNova (0.59s) offer the lowest time to first token.
- For pricing, DeepInfra (0.37), Novita (0.48), Nebius (0.75) offer the lowest blended prices per 1M tokens. Prices vary up to 3.4x across providers.
Pricing
Pricing: Input and Output Prices: DeepSeek V3 0324 Providers
Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Price per token generated by the model (received from the API), represented as USD per million Tokens.
Speed vs. Price: DeepSeek V3 0324 Providers
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
Speed
Measured by Output Speed (tokens per second)
Output Speed: DeepSeek V3 0324 Providers
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
Latency vs. Output Speed: DeepSeek V3 0324 Providers
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
Latency
Measured by Time (seconds) to First Token
Time to First Token: DeepSeek V3 0324 Providers
Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
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: DeepSeek V3 0324 Providers
Seconds to receive a 500 token response. Key components:
- Input time: Time to receive the first response token
- Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
- Answer time: Time to generate 500 output tokens, based on output speed
For fair comparison, the number of reasoning tokens is standardized across all providers for each model based on the model's representative query token counts.
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
API Features
Function (Tool) Calling & JSON Mode: DeepSeek V3 0324 Providers
SambaNova
Together.ai
Replicate
DeepInfraIndicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.
Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.
Context Window: DeepSeek V3 0324 Providers
Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
While models have their own context window, in cases this is limited by providers.