DeepSeek V4 Flash pricing
DeepSeek V4 Flash, Small-tier from DeepSeek, costs $0.44 per 1M input tokens and $1.32 per 1M output tokens.
Input$0.44per 1M tokens
Output$1.32per 1M tokens
Context window1Mtokens
TierSmallDeepSeek
Price your own workload against DeepSeek V4 Flash in the calculator →
Specs and pricing
| Provider | DeepSeek |
| Tier | Small |
| Context window | 1M tokens |
| Max output | 384K tokens |
| Input price | $0.44 / 1M tokens |
| Output price | $1.32 / 1M tokens |
| Cache read | $0.014 / 1M tokens |
| Modalities | text |
| Released | 2026-04 |
Note. Peak cache-miss rate, this dataset's standard tier. Off-peak is half: $0.22 input / $0.66 output, cache-hit input $0.007. Peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday to Friday per DeepSeek's own page.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.44 | $0.33 | $0.77 |
| 10,000,000 in / 2,500,000 out | $4.40 | $3.30 | $7.70 |
| 100,000,000 in / 25,000,000 out | $44.00 | $33.00 | $77.00 |
Cheaper alternatives
Same tier (Small), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct-Turbo | DeepInfra | $0.02 | $0.04 | 96.1% cheaper blended |
| Solar Pro 4 | OpenRouter | $0.03 | $0.12 | 92.2% cheaper blended |
| GPT-OSS 20B | OpenRouter | $0.03 | $0.13 | 91.9% cheaper blended |
| schematron-v2-turbo | inference.net | $0.03 | $0.15 | 91.2% cheaper blended |
| Amazon Nova Micro | Amazon (Nova) | $0.035 | $0.14 | 90.9% cheaper blended |