DeepSeek Flash pricing for customer support bot

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=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.001050 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 customer support bot benchmarks. Hover for details.

Highest-quality affordable option: GPT 5.6 Luna at $0.001800/call (1.7x the cost, 85/100 quality). DeepSeek Flash is already the cheapest choice for customer support bot.

What drives customer support bot cost

Support bots combine RAG's retrieved context with a chatbot's growing history, so they carry both cost curves at once. Volume is high and margins per conversation are thin, which makes the per-call rate matter more than in almost any other use case here. Caching the knowledge base and product context is the single highest-leverage change.

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 3,000/1,000 token split, output accounts for 57% of the $0.001050 per-call cost.

DeepSeek Flash quality benchmarks for customer support bot

Benchmark data for customer support bot 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