DeepSeek V4 Flash 0420 (Reasoning, High Effort) API Pricing

DeepSeek · released 2026-04-24 · merges 3 reasoning-effort tiers

Benchmarks shown for the highest-scoring reasoning tier. Merged tiers: DeepSeek V4 Flash 0420 (Reasoning, High Effort), DeepSeek V4 Flash 0420 (Reasoning, Max Effort), DeepSeek V4 Flash 0420 (Non-reasoning).

Pricing

$0.13
input / 1M tokens
0.013¢ / 1K
$0.28
output / 1M tokens
0.028¢ / 1K
$0.168
blended / 1M tokens
0.017¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.0149¢
RAG query4,000 in / 500 out0.066¢
Long document summary50,000 in / 1,000 out0.678¢
Code review of a 2k-line file30,000 in / 2,000 out0.446¢
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$4.47

Cost = (input tokens ÷ 1,000,000 × $0.13) + (output tokens ÷ 1,000,000 × $0.28).

Benchmarks

26.0
Intelligence
#72 of 533
52.0
Coding
#67 of 197
Math
Tokens/sec
Time to first token

Similar intelligence, lower price

ModelIntelligenceBlended $/1M
Ling 3.0 Flash24.9$0.111
Ling-3.0-flash-VL24.6$0.111

Leaderboard neighbours

ModelIntelligenceBlended $/1M
Claude Opus 4.6 (Non-reasoning, High Effort)26.4$10.00
Gemini 3 Flash Preview (Reasoning)26.3$1.125
GLM-5.1 (Reasoning)26.1$2.00
DeepSeek V4 Flash 0420 (Reasoning, High Effort)26.0$0.168
GPT-5.5 Instant (June 2026)26.0$11.25
MiMo-V2.5-Pro26.0$0.544
Kimi K2.7 Code25.8$1.712

More from DeepSeek

ModelIntelligenceBlended $/1M
DeepSeek V4.1 Flash (Reasoning, Max Effort)39.5$0.525
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)36.0$1.98
DeepSeek V4 Flash Vision (Reasoning, Max Effort)34.8$0.66
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)34.3$0.66
DeepSeek V4 Pro 0424 (Reasoning, Max Effort)30.4$0.544
DeepSeek V3.2 (Reasoning)21.5$0.315
DeepSeek V3.2 Exp (Reasoning)16.6$0.315
DeepSeek V3.2 (Non-reasoning)16.0$0.315

Count tokens & estimate cost for DeepSeek V4 Flash 0420 (Reasoning, High Effort) See DeepSeek V4 Flash 0420 (Reasoning, High Effort) on the leaderboard

Source: Artificial Analysis · last synced 2026-09-22

FAQ

Who develops DeepSeek V4 Flash 0420 (Reasoning, High Effort)?

DeepSeek V4 Flash 0420 (Reasoning, High Effort) is developed by DeepSeek, released 2026-04-24.

How much does DeepSeek V4 Flash 0420 (Reasoning, High Effort) cost per million tokens?

DeepSeek V4 Flash 0420 (Reasoning, High Effort) costs $0.13 per 1M input tokens and $0.28 per 1M output tokens ($0.168 blended), per Artificial Analysis's official pricing data.

How does DeepSeek V4 Flash 0420 (Reasoning, High Effort) rank on benchmarks?

DeepSeek V4 Flash 0420 (Reasoning, High Effort) scores 26.0 on the Artificial Analysis Intelligence Index, ranking #72 of 533 models we track.

Is there a cheaper model with similar intelligence to DeepSeek V4 Flash 0420 (Reasoning, High Effort)?

Yes — Ling 3.0 Flash scores similar intelligence (24.9) at $0.111/1M blended, versus $0.168/1M for DeepSeek V4 Flash 0420 (Reasoning, High Effort).

Where does this data come from?

Pricing and benchmark data for DeepSeek V4 Flash 0420 (Reasoning, High Effort) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.