Open weights model

Released April 2026

DeepSeek V4 Flash (Non-reasoning) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Flash (Non-reasoning) for your use-case.

Fastest

#1
CoreWeaveCoreWeave
77.3 t/s
#2
MakoraMakora
52.6 t/s

Output speed

Total 3 providers

Lowest Latency

#1
MakoraMakora
1.28 s
#2
CoreWeaveCoreWeave
1.59 s

Time to first token

Total 3 providers

Lowest Price

#1
GMIGMI
$0.05
#2
MakoraMakora
$0.10
#3
CoreWeaveCoreWeave
$0.11

Blended price (per 1M tokens)

Total 3 providers

DeepSeek V4 Flash (Non-reasoning) is available through 3 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 CoreWeave (77.3 t/s) and Makora (52.6 t/s).
  • For latency, Makora (1.28s) and CoreWeave (1.59s) offer the lowest time to first token.
  • For pricing, GMI (0.05), Makora (0.10), and CoreWeave (0.11) offer the lowest blended prices per 1M tokens.

Highlights

Output tokens per second · Higher is better
Seconds · Lower is better
USD per 1M tokens (blended) · Lower is better

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher is better

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Speed

Measured by Output Speed (tokens per second)

Output Speed: DeepSeek V4 Flash (Non-reasoning)

Output speed: output tokens per second · 10,000 input tokens

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
Most attractive quadrant
Pareto line

Latency

Measured by Time (seconds) to First Token

Time to First Token

Seconds to first token received · Lower is better · 10,000 input tokens

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

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Key Comparison Metrics & API Features

GMI logoGMI
1.05M
Open
--
--
--
--
--
Makora logoMakora
1M
Open
--
53
1.28
10.78
--
CoreWeave logoCoreWeave
1M
Open
--
77
1.59
8.06
--

Frequently Asked Questions

Common questions about DeepSeek V4 Flash (Non-reasoning) providers