DeepSeek V4 Pro 0813 API Pricing
DeepSeek V4 Pro 0813 costs $0.66 per 1M input tokens and $1.98 per 1M output tokens. These rates were last verified on .
DeepSeek V4 Pro 0813: current and scheduled rates
Rates effective since August 16, 2026 at 4:00 PM UTC. Prices are USD per 1M tokens.
| Model | Rate period | Input | Cached | Output | Input / output vs current |
|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | Off-peak baseline | $0.66 | $0.022 | $1.98 | Comparison baseline |
| DeepSeek V4 Pro 0813 | Off-peak | $0.66 | $0.022 | $1.98 | No change / No change |
| DeepSeek V4 Pro 0813 | Peak | $1.32 | $0.044 | $3.96 | 100% higher / 100% higher |
DeepSeek V4 Pro 0813: Peak windows: 01:00-04:00 and 06:00-10:00 UTC. Peak days (UTC): Monday, Tuesday, Wednesday, Thursday, Friday. Weekends and Chinese public holidays are off-peak in full. All other hours are off-peak.
Built from the scheduled rate card in the canonical pricing API.
Published rates and billing units
| Billing dimension | USD list price |
|---|---|
| Input / 1M tokens | $0.66 |
| Cached input / 1M tokens | $0.022 |
| Output / 1M tokens | $1.98 |
Verified 2026-11-12 · Official source · Pricing methodology. Taxes, optional services and account-specific discounts are not included.
Cost examples
These examples use published list prices only. They exclude taxes, enterprise discounts, minimum charges, retries, batch discounts, and provider-specific billing rules.
1M input + 1M output
$2.64
A direct per-million comparison against every other text model.
100K input + 25K output
$0.1155
A compact chat, summarization, or analysis workload.
10M input + 2M output
$10.56
A monthly production estimate for heavier RAG or agent traffic.
75% cached input + 250K output
$0.6765
Cached input is about 97% cheaper than standard input at list price.
We tested this model at different reasoning-effort levels in a Labs experiment →
Calculator for DeepSeek V4 Pro 0813
Enter your own input, output, and cached-token assumptions. This calculator is preloaded with only DeepSeek V4 Pro 0813, so the result stays focused on this model.
Input cost
$0.66
Output cost
$1.98
Total
$2.64
Estimates use the current listed rates, not future rates. Token estimates use the off-peak reference, not an all-hours quote. Peak: $1.32 input / $0.044 cached input / $3.96 output per 1M tokens during 01:00-04:00 and 06:00-10:00 UTC, on Monday through Friday. Weekends and Chinese public holidays are off-peak in full. Separate per-request tool fees are excluded. Cache storage and other non-token fees are excluded.
Price history
input moved from $1.74 to $0.66 and output moved from $3.48 to $1.98 across 201 daily snapshots.
When to use DeepSeek V4 Pro 0813
Good fit
- reasoning-heavy prompts, planning, analysis, and multi-step tool use
- high-volume routing, classification, extraction, summaries, and fallback traffic
- long-document and repository-scale prompts where context window matters
Be careful with
- blind migration without testing your own prompts, latency, and failure modes