DeepSeek API Pricing 2026: V4 Flash and Pro Peak vs Off-Peak Rates

DeepSeek’s current V4 API uses time-of-day pricing. The new rates took effect at 2026-08-16 16:00 UTC, or midnight on August 17 in Beijing. Peak hours are 01:00-04:00 and 06:00-10:00 UTC; every other hour receives a 50% off-peak discount.

The current model IDs are deepseek-v4-flash and deepseek-v4-pro. Both have a 1M-token context window, 384K maximum output, thinking and non-thinking modes, JSON output, tool calls, Responses API, and OpenAI- and Anthropic-compatible endpoints.

Current DeepSeek Prices

USD per million tokens:

Model and billing period	Cached input	Cache-miss input	Output
deepseek-v4-flash, off-peak	$0.007	$0.22	$0.66
deepseek-v4-flash, peak	$0.014	$0.44	$1.32
deepseek-v4-pro, off-peak	$0.022	$0.66	$1.98
deepseek-v4-pro, peak	$0.044	$1.32	$3.96

DevTk.AI’s calculator uses the conservative peak rate. For workloads that can be scheduled, calculate a second forecast with the off-peak rate.

Peak Schedule

Billing period	UTC	Beijing time
Peak window 1	01:00-04:00	09:00-12:00
Peak window 2	06:00-10:00	14:00-18:00
Off-peak	All other hours	All other hours

The 2x statement compares the current peak and off-peak prices. It does not mean every old price simply doubled. For example, V4 Flash’s former $0.28/M output rate became $0.66/M off-peak and $1.32/M peak.

Current Versions and IDs

API ID	Served version	Context	Max output
deepseek-v4-flash	DeepSeek-V4-Flash-0731	1M	384K
deepseek-v4-pro	DeepSeek-V4-Pro-0813	1M	384K

The old deepseek-chat and deepseek-reasoner aliases were retired on July 24, 2026. Use the explicit V4 IDs in current integrations.

Cost Formula and Cache Fields

cost =
  prompt_cache_hit_tokens * cached_input_price / 1,000,000
+ prompt_cache_miss_tokens * cache_miss_input_price / 1,000,000
+ completion_tokens * output_price / 1,000,000

DeepSeek exposes the relevant usage counters:

usage.prompt_cache_hit_tokens
usage.prompt_cache_miss_tokens

Caching is best effort. Stable system prompts, repository rules, tool schemas, and conversation prefixes have the best chance of reuse. Monitor the actual cache-hit ratio rather than budgeting for a perfect cache.

Cost Examples

For 2M cache-miss input plus 500K output tokens across multiple requests:

Model and period	Cost
V4 Flash, off-peak	$0.77
V4 Flash, peak	$1.54
V4 Pro, off-peak	$2.31
V4 Pro, peak	$4.62

With 85% of input served from cache, the same workload becomes approximately $0.408 off-peak or $0.816 peak on V4 Flash. The result still depends on actual cache behavior and output-token use.

OpenAI-Compatible Example

from openai import OpenAI

client = OpenAI(
    api_key="your-deepseek-api-key",
    base_url="https://api.deepseek.com"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "system", "content": "You are a careful coding assistant."},
        {"role": "user", "content": "Explain this repository structure."}
    ],
)

print(response.choices[0].message.content)

For Anthropic-format coding agents:

export ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic
export ANTHROPIC_AUTH_TOKEN=your-deepseek-api-key

Is DeepSeek Still Cheap?

V4 Flash remains a useful low-cost model, especially off-peak and with repeated long context. It is no longer the universal price floor: Mistral Small 4 can be cheaper for short ordinary traffic, and GPT-5.6 Luna can be cheaper than V4 Flash during peak hours for some token mixes.

V4 Pro should be an escalation route. Its value depends on reducing failed tool loops, retries, or human repair enough to offset the higher price.

Read the full post-increase value analysis and use the AI Pricing Calculator for your workload.

Official sources checked August 17, 2026: DeepSeek pricing, V4 Pro 0813 and pricing announcement, context caching, and Anthropic API compatibility.