DeepSeek-V4-Pro Pricing & Specs: Cost per Token & Context Window

DeepSeek-V4-Pro is DeepSeek's model priced at $0.435 per 1M input tokens and $0.87 per 1M output tokens, with a context window of about 128K tokens. Below are its full specs and how it stacks up against models from other providers on price and context.

DeepSeek-V4-Pro pricing

Standard text/chat rates, per 1,000,000 tokens, as of June 2026. Verify against the provider's official page.
Token typePrice (per 1,000,000 tokens)
Input $0.435
Output $0.87
Cached input $0.0036

Standard cache-miss input pricing; off-peak discounts may apply.

Source: official DeepSeek pricing.

DeepSeek-V4-Pro specifications

Specs as configured for standard text/chat use.
SpecValue
Vendor DeepSeek
Context window 128K tokens
Input price $0.435 / 1M tokens
Output price $0.87 / 1M tokens
Cached input price $0.0036 / 1M tokens

Compare DeepSeek-V4-Pro with other models

Head-to-head pricing and spec comparisons against models from other providers:

Running DeepSeek-V4-Pro in production? See its DeepSeek rate limits and common error codes, or estimate spend with the token cost calculator.

Prices change often — these are as of June 2026. Context windows are approximate (some models offer larger beta/long-context tiers) — verify against provider docs. GPT counts are exact via the o200k tokenizer; Anthropic/Google/DeepSeek counts are estimates.