Token Cost Calculator

DeepSeek API Pricing

V4-Pro and V4.1-Flash per-token rates, off-peak hours, and prompt-cache savings — compared to Claude, GPT, and Gemini.

Last updated: 2026-10-20

1,000
2,000
400
1,000 × 2,000in + 400out = 2,000,000 input,400,000 output tokens

Estimated cost across 21 models

Google Cheapest

Gemini 2.5 Flash-Lite

$0.360/ month
$4.32 / year
Input
$0.200
Output
$0.160400,000 tokens
Input
$0.10 / 1M2,000,000 tokens
Output
$0.40 / 1M
Context window
1,000,000Last updated: 2026-10-20
OpenAI

GPT-6 luna

$0.400/ month
$4.80 / year
Input
$0.200
Output
$0.200400,000 tokens
Input
$0.10 / 1M2,000,000 tokens
Output
$0.50 / 1M
Context window
1,050,000Last updated: 2026-10-20
MiniMax

MiniMax M3.1 Flash

$0.540/ month
$6.48 / year

Released 2026-10-19; $0.15 / $0.60 / $0.015 (¥1 / ¥4 / ¥0.1). Flat rate — no long-context tier, and unlike M3 it does not accept service_tier=priority.

Input
$0.300
Output
$0.240400,000 tokens
Input
$0.15 / 1M2,000,000 tokens
Output
$0.60 / 1M
Context window
1,000,000Last updated: 2026-10-20
DeepSeek

DeepSeek V4.1-Flash 1017

$1.08/ month
$12.96 / year
Peak hours

Checkpoint DeepSeek-V4.1-Flash-1017 (released 2026-10-17), served under the API model name `deepseek-flash`; open weights on Hugging Face / ModelScope. The 2026-09-10 launch price is unchanged. The launch checkpoint is kept as its own row (deepseek-flash-0910).

Input
$0.600
Output
$0.480400,000 tokens
Input
$0.30 / 1M2,000,000 tokens
Output
$1.20 / 1M
Context window
1,000,000Last updated: 2026-10-20
MiniMax

MiniMax M3

$1.08/ month
$12.96 / year

Released 2026-06-01. service_tier=priority costs 1.5× ($0.45 / $1.80 / $0.09). No separate cache-write charge. The cached-input rate above 512k doubles to $0.12; cost.ts applies the input multiplier to the cached rate as well.

Input
$0.600
Output
$0.480400,000 tokens
Input
$0.30 / 1M2,000,000 tokens
Output
$1.20 / 1M
Context window
1,000,000Last updated: 2026-10-20
Google

Gemini 3.1 Flash-Lite

$1.10/ month
$13.20 / year
Input
$0.500
Output
$0.600400,000 tokens
Input
$0.25 / 1M2,000,000 tokens
Output
$1.50 / 1M
Context window
1,000,000Last updated: 2026-10-20
Google

Gemini 2.5 Flash

$1.60/ month
$19.20 / year
Input
$0.600
Output
$1.00400,000 tokens
Input
$0.30 / 1M2,000,000 tokens
Output
$2.50 / 1M
Context window
1,000,000Last updated: 2026-10-20
Google

Gemini 3.8 Flash

$3.00/ month
$36.00 / year

Introductory pricing: $0.75 / $3.75 / $0.075 through 2026-12-31, then $1.50 / $7.50 / $0.15 from 2027-01-01.

Input
$1.50
Output
$1.50400,000 tokens
Input
$0.75 / 1M2,000,000 tokens
Output
$3.75 / 1M
Context window
1,000,000Last updated: 2026-10-20
Anthropic

Claude Haiku 4.5

$4.00/ month
$48.00 / year
Input
$2.00
Output
$2.00400,000 tokens
Input
$1.00 / 1M2,000,000 tokens
Output
$5.00 / 1M
Context window
200,000Last updated: 2026-10-20
DeepSeek

DeepSeek V4-Pro

$4.22/ month
$50.69 / year
Peak hours
Input
$2.64
Output
$1.58400,000 tokens
Input
$1.32 / 1M2,000,000 tokens
Output
$3.96 / 1M
Context window
1,000,000Last updated: 2026-10-20
Grok

Grok 4.7

$6.40/ month
$76.80 / year
Input
$4.00
Output
$2.40400,000 tokens
Input
$2.00 / 1M2,000,000 tokens
Output
$6.00 / 1M
Context window
500,000Last updated: 2026-10-20
Google

Gemini 2.5 Pro

$6.50/ month
$78.00 / year
Input
$2.50
Output
$4.00400,000 tokens
Input
$1.25 / 1M2,000,000 tokens
Output
$10.00 / 1M
Context window
1,000,000Last updated: 2026-10-20
OpenAI

GPT-6 sol

$8.00/ month
$96.00 / year
Input
$4.00
Output
$4.00400,000 tokens
Input
$2.00 / 1M2,000,000 tokens
Output
$10.00 / 1M
Context window
1,050,000Last updated: 2026-10-20
Anthropic

Sonnet 5

$8.00/ month
$96.00 / year
Input
$4.00
Output
$4.00400,000 tokens
Input
$2.00 / 1M2,000,000 tokens
Output
$10.00 / 1M
Context window
1,000,000Last updated: 2026-10-20
Google

Gemini 4 Argon

$8.00/ month
$96.00 / year

Introductory pricing: $2 / $10 / $0.10 through 2026-11-30, then $4 / $20 / $0.20 from 2026-12-01. Implicit caching only — explicit caching is not supported. Batch and Flex run at half the standard rate; Priority is 1.8×.

Input
$4.00
Output
$4.00400,000 tokens
Input
$2.00 / 1M2,000,000 tokens
Output
$10.00 / 1M
Context window
1,048,576Last updated: 2026-10-20
Google

Gemini 3.1 Pro Preview

$8.80/ month
$106 / year
Input
$4.00
Output
$4.80400,000 tokens
Input
$2.00 / 1M2,000,000 tokens
Output
$12.00 / 1M
Context window
1,000,000Last updated: 2026-10-20
OpenAI

GPT-5.6 sol

$16.00/ month
$192 / year

Promotional pricing ($4 / $20 / $0.40) is available at least through 2026-11-21; the pre-promo rate was $5 / $30. Re-check after that date.

Input
$8.00
Output
$8.00400,000 tokens
Input
$4.00 / 1M2,000,000 tokens
Output
$20.00 / 1M
Context window
1,050,000Last updated: 2026-10-20
Anthropic

Opus 5.5

$16.00/ month
$192 / year
Input
$8.00
Output
$8.00400,000 tokens
Input
$4.00 / 1M2,000,000 tokens
Output
$20.00 / 1M
Context window
1,000,000Last updated: 2026-10-20
OpenAI

GPT-6 astra

$40.00/ month
$480 / year
Input
$20.00
Output
$20.00400,000 tokens
Input
$10.00 / 1M2,000,000 tokens
Output
$50.00 / 1M
Context window
1,050,000Last updated: 2026-10-20
Anthropic

Fable 5.1

$40.00/ month
$480 / year
Input
$20.00
Output
$20.00400,000 tokens
Input
$10.00 / 1M2,000,000 tokens
Output
$50.00 / 1M
Context window
1,000,000Last updated: 2026-10-20
OpenAI

GPT-5.6 cyber

$55.00/ month
$660 / year
Input
$25.00
Output
$30.00400,000 tokens
Input
$12.50 / 1M2,000,000 tokens
Output
$75.00 / 1M
Context window
400,000Last updated: 2026-10-20

Prices verified 2026-10-20. Source: official provider pricing pages. · Machine-readable: /api/prices.json

Quick takeaways
  • 1DeepSeek V4.1-Flash is $0.30 input / $1.20 output per 1M tokens — roughly 8× cheaper than GPT-5 on output.
  • 2V4-Pro is $1.32 / $3.96 per 1M — comparable to Claude Sonnet 4.5 on benchmarks, ~2.3× cheaper on output.
  • 3Off-peak (Mon–Fri outside 01:00–04:00 & 06:00–10:00 UTC, plus all weekends & Chinese holidays) is 50% of peak — schedule batch jobs accordingly.
  • 4Cache hits drop V4.1-Flash input from $0.30/M to $0.003/M — 99% off. Cache aggressively when the system prompt or tool schema repeats.

Off-peak hours, explained

Mon–Fri (excluding Chinese public holidays), DeepSeek bills at the full peak rate only during 01:00–04:00 and 06:00–10:00 UTC. All other times — including all weekend hours — are off-peak and bill at 50% of peak for both input and output.

Off-peak = 50% of peak · Mon–Fri · weekends & Chinese holidays all-day off-peak

Prompt-cache pricing

DeepSeek cache hits are aggressive — V4.1-Flash drops cached input by 98% from the standard rate, V4-Pro by 97%. For any workload with a repeated prefix (system prompt, tool definitions, document context) caching the prefix is the single highest-leverage cost saving.

  • DeepSeek V4.1-Flash 1017: $0.006/M (98% off)
  • DeepSeek V4-Pro: $0.044/M (97% off)
Token Cost Calculator

How to bring the bill down

  1. 1Use V4.1-Flash for routing / classification — output is $1.20/M vs $3.96/M on V4-Pro, ~3.3× cheaper.
  2. 2Cache repeat prefixes — V4.1-Flash cache hit is $0.003/M, a 99% drop from $0.30/M. The single biggest cost saver for repeat-prompt workloads.
  3. 3Batch non-urgent jobs into off-peak hours (Mon–Fri outside 01:00–04:00 and 06:00–10:00 UTC) for ~50% cheaper inference.
  4. 4Set max_tokens explicitly — output is the expensive side; capping it prevents runaway replies.
  5. 5Going direct to DeepSeek's API beats OpenRouter by a few percent. OpenRouter wins on automatic fallback + a single invoice.
Token Cost Calculator

Frequently asked questions

How much does the DeepSeek API cost?
DeepSeek V4-Pro is $1.32 per 1M input tokens / $3.96 per 1M output tokens. DeepSeek V4.1-Flash is $0.30 / $1.20. New accounts get a small free credit to start; top-up minimums start at $5. Numbers above are re-verified against platform.deepseek.com/api-docs/pricing.
When is DeepSeek off-peak?
Off-peak runs Monday through Friday outside the peak windows (UTC 01:00–04:00 and 06:00–10:00) and all day on weekends and Chinese public holidays. During off-peak, both input and output are billed at 50% of the peak rate. The schedule is published at platform.deepseek.com.
Is DeepSeek cheaper than GPT-5?
Yes — at peak, DeepSeek V4.1-Flash output is $1.20 per 1M tokens versus GPT-5 output at roughly $10 per 1M (~8× cheaper on output). V4-Pro output at $3.96 is roughly 2.5× cheaper than GPT-5 output. For high-volume workloads the difference dominates every other cost lever.
What is DeepSeek V4.1-Flash?
V4.1-Flash is the fast non-reasoning model in the V4 family: 1M context window, $0.30 / $1.20 per 1M, with a $0.003 cache-hit price on input. It is the cheapest model in the active registry — input is roughly 17× cheaper than Claude Opus 4.5 and output is roughly 21× cheaper.
What is DeepSeek V4-Pro?
V4-Pro is the flagship reasoning model: 1M context window, $1.32 / $3.96 per 1M, with a $0.022 cache-hit price. It benchmarks in the same tier as Claude Sonnet 4.5 on most reasoning evals while costing roughly 2.3× less. Use it when you need Sonnet-class reasoning at sub-Haiku price.
Does DeepSeek have prompt caching?
Yes. V4.1-Flash cache hits are $0.003 per 1M input tokens — a 99% drop from $0.30/M standard. V4-Pro cache hits are $0.022 per 1M, a 98% drop from $1.32/M. For repeat-prefix workloads (system prompts, tool schemas, large document context) caching is the single biggest cost lever.
Is the DeepSeek API the same as OpenRouter?
No — going direct to platform.deepseek.com bills at the official rate; OpenRouter adds a small markup (typically ~5%) for routing, billing, and automatic fallback. For single-model high-volume workloads direct is cheaper; OpenRouter wins when you need fallback across providers or a single invoice for many models.
How do I get a DeepSeek API key?
Sign up at platform.deepseek.com, complete the minimum top-up (currently $5), and generate a key from the API Keys page in the console. The calculator above always shows the current per-million rates, and /api/prices.json exposes the same numbers in a machine-readable form for AI agents.
More calculators

Pick the right page for your use case

Token Cost Calculator

Compare prices across OpenAI, Claude, Gemini, DeepSeek, MiniMax, and Grok. Real tokenizer for OpenAI, accurate estimates for the rest.

Open

OpenRouter Pricing Calculator

See what your tokens actually cost after the OpenRouter markup — and when going direct to the provider is cheaper.

Open

Claude Token Cost Calculator

Cost per token and monthly estimates for Claude Opus, Sonnet, and Haiku — with the Anthropic API.

Open

ChatGPT API Pricing

GPT-6 and GPT-5 per-token rates, Batch API 50% off, and prompt-cache savings — compared to Claude, Gemini, and DeepSeek.

Open