DeepSeek API pricing calculator

Estimate DeepSeek API costs per request and per month. Prices shown are peak-hour prices; off-peak is half.

0 characters0 words0 tokens (GPT o200k)

ModelInput tokensPrice / 1M (in → out)Per requestPer month
Claude Fable 5.1$10 → $50
Claude Opus 5.5$4 → $20
Claude Opus 5$5 → $25
Claude Sonnet 5.5$2 → $10
Claude Sonnet 5$2 → $10
Claude Haiku 5.5$0.1 → $0.5
Claude Sonnet 4.6$3 → $15
Claude Haiku 4.5$1 → $5
GPT-6 Astra$10 → $50
GPT-6.1 Sol$2 → $10
GPT-6.1 Terra$1 → $5
GPT-6 Sol$2 → $10
GPT-6 Luna$0.1 → $0.5
GPT-5.6 Sol$4 → $20
GPT-5.6 Terra$2 → $12
GPT-5.6 Luna$0.2 → $1.2
GPT-5.5$5 → $30
GPT-5.4$2.5 → $15
GPT-5.4 mini$0.75 → $4.5
GPT-5.4 nano$0.2 → $1.25
GPT-5 mini$0.25 → $2
GPT-4.1$2 → $8
GPT-4o mini$0.15 → $0.6
o3$2 → $8
o4-mini$1.1 → $4.4
Gemini 4 Argon$2 → $10
Gemini 3.8 Flash$0.75 → $3.75
Gemini 3.6 Flash$0.75 → $3.75
Gemini 3.5 Flash-Lite$0.3 → $2.5
Gemini 3.1 Pro (preview)$2 → $12
Gemini 3.1 Flash-Lite$0.25 → $1.5
Gemini 2.5 Pro$1.25 → $10
Gemini 2.5 Flash$0.3 → $2.5
Gemini 2.5 Flash-Lite$0.1 → $0.4
Grok 4.7$2 → $6
Grok 4.6$2 → $6
Grok 4.5$2 → $6
Grok 4.3$1.25 → $2.5
Grok 4.20$1.25 → $2.5
Grok Build 0.1$1 → $2
DeepSeek V4 Pro$1.32 → $3.96
DeepSeek Flash$0.3 → $1.2
Mistral Large 3$0.5 → $1.5

≈ = estimated token count: only OpenAI publishes its tokenizer. Claude counts use Anthropic’s published ratios; use the count_tokens API for an exact number.

Price per million tokens

Prices checked on October 28, 2026. USD, standard tier.

DeepSeek

ModelInputCached inputOutputBatch
DeepSeek V4 Pro deepseek-v4-pro
Peak price. Off-peak is half: outside 01–04 and 06–10 UTC on weekdays, plus weekends and Chinese public holidays.
$1.32$0.044$3.96—
DeepSeek Flash deepseek-flash
Peak price. Off-peak is half: outside 01–04 and 06–10 UTC on weekdays, plus weekends and Chinese public holidays.
$0.3$0.006$1.2—

Sources: api-docs.deepseek.com

Frequently asked questions

What is a token?

A token is a piece of text a language model reads or writes — often part of a word. In English, 1,000 tokens is roughly 750 words. APIs bill per million tokens, with separate prices for input (your prompt) and output (the answer).

Why do Claude and GPT count different tokens for the same text?

Each company uses its own tokenizer. Anthropic says Claude Opus 4.7 and later produce about 30% more tokens than earlier Claude models for the same text, so comparing price per token alone is misleading — compare the cost of the same prompt, as this calculator does.

Are the token counts exact?

For GPT-4o, GPT-4.1, the o-series and GPT-5, yes: we use OpenAI’s public o200k tokenizer in your browser. Other providers don’t publish their tokenizers, so their counts are estimates (marked ≈). For an exact Claude count, use Anthropic’s count_tokens API.

How do prompt caching and the Batch API lower the cost?

Cached input is billed at a fraction of the normal price (10% on most Claude models, less on some). The Batch API halves prices for requests that can wait up to 24 hours. Use the slider and checkbox to see the effect.

More calculators