DeepSeek Flash pricing for rag pipeline

Quick start

Call DeepSeek Flash with the OpenAI Python SDK pointed at api.deepseek.com:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.deepseek.com/v1",
    api_key=os.environ["DEEPSEEK_API_KEY"],
)
response = client.chat.completions.create(
    model="deepseek-flash",
    max_tokens=1500,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.001800 per call at standard rates
# Input:  $0.15/MTok
# Output: $0.60/MTok

How DeepSeek Flash compares on cost

Per-call cost for all models scoring 50+ on rag pipeline benchmarks. Hover for details.

Highest-quality affordable option: GPT 5.6 Luna at $0.003000/call (1.7x the cost, 85/100 quality). DeepSeek Flash is already the cheapest choice for rag pipeline.

What drives rag pipeline cost

Retrieval-augmented calls are dominated by the retrieved passages, not the question. Retrieving eight chunks instead of three roughly triples input cost for an answer that is often no better, so retrieval tuning is cost tuning. The system prompt and instructions are identical on every call, which makes cache reads the first thing to enable.

For DeepSeek Flash specifically, that means output tokens cost 4.0x more than input, at $0.60 vs $0.15 per MTok. At this use case’s 6,000/1,500 token split, output accounts for 50% of the $0.001800 per-call cost.

DeepSeek Flash quality benchmarks for rag pipeline

Benchmark data for rag pipeline is pending for DeepSeek Flash. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for DeepSeek Flash. We recommend testing against your own evaluation criteria.

About DeepSeek Flash

Prices are off-peak rates from api-docs.deepseek.com (read 2026-10-11). Peak-hour prices are 2x the listed input and output rates — Tokeven does not model time-of-day tiers; off-peak is used as the base. Cache hit: $0.003/MTok input. No batch discount published. Not yet benchmarked, so never recommended.

Other models from DeepSeek

You can compare DeepSeek Flash head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions