DeepSeek R1 pricing for sql generation

Quick start

Call DeepSeek R1 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-r1",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.003015 per call at standard rates
# Input:  $0.55/MTok
# Output: $2.19/MTok

How DeepSeek R1 compares on cost

Per-call cost for all models scoring 50+ on sql generation benchmarks. Hover for details.

Highest-quality affordable option: Claude Haiku 4.5 at $0.006500/call (2.2x the cost, 72/100 quality). DeepSeek R1 is already the cheapest choice for sql generation.

What drives sql generation cost

The cheapest code use case on this list. A natural-language question plus a schema fits in 1.5K tokens, and the query that comes back is under 1K. That makes SQL generation a genuine candidate for a fast-tier model: the task is well-bounded, the output is short, and the quality gap between tiers narrows when there is little room to go wrong. Schema caching cuts the input side to near zero.

For DeepSeek R1 specifically, that means output tokens cost 4.0x more than input, at $2.19 vs $0.55 per MTok. At this use case’s 1,500/1,000 token split, output accounts for 73% of the $0.003015 per-call cost.

DeepSeek R1 quality benchmarks for sql generation

Benchmark data for sql generation is pending for DeepSeek R1. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for DeepSeek R1. We recommend testing against your own evaluation criteria.

About DeepSeek R1

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: $0.14/MTok input. No batch discount published. Reasoning model: output includes chain-of-thought tokens. Not yet benchmarked, so never recommended.

Other models from DeepSeek

You can compare DeepSeek R1 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