← All models
Balanced — strong quality at a mid priceOpen Weights
DeepSeek V3 Pricing
DeepSeek · deepseek-deepseek-chat
Input / 1M tokens
$0.257
Output / 1M tokens
$1.03
Context window
163,840 tokens
≈ 218 pages of text
Max output
16k tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0007
1,000 requests / month$0.7204/mo10,000 requests / month$7.20/mo100,000 requests / month$72.04/moEstimate your own workloadOpens the calculator with DeepSeek V3 preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Strong performance on code generation, mathematical reasoning, and long-context tasks up to 128k tokens.
The business tradeoff
Open weights require self-hosting or third-party inference, introducing latency and hardware cost variability; ecosystem tooling remains less mature than major closed providers.
Cheaper from DeepSeek
Head-to-head
Vendor list rates, as of Jul 30, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.