DeepSeek V4.1 Flash (batch)
by DeepSeek · deepseek/deepseek-v4.1-flash:batch · #84 cheapest of 457 paid models
Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.112
per 1M tokens
Output
$0.336
per 1M tokens
Blended (3:1)
$0.168
3 input : 1 output
Cache read
$0.0034
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for DeepSeek V4.1 Flash (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.168 | $0.0118 | — |
| 50% | $0.127 | $0.006328 | −46% |
| 90% | $0.095 | $0.001982 | −83% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000157 | $0.1568 |
| Document summary | 8,000 | 1,000 | $0.001232 | $1.23 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.004032 | $4.03 |
| Long-context analysis | 150,000 | 5,000 | $0.0185 | $18.48 |
Specs
Context window
1.05M
tokens
Max output
131K
tokens
Input modalities
text, image
Tokenizer
DeepSeek