DeepSeek
DeepSeek API pricing
DeepSeek's API has two models: deepseek-flash (DeepSeek-V4.1-Flash-1017) and deepseek-v4-pro. As of 18 October 2026, Flash costs $0.30 per million input tokens (cache miss) and $1.20 per million output tokens at peak times, and exactly half of that off-peak. V4 Pro costs $1.32 input and $3.96 output at peak, also half off-peak. Both have a 1M-token context window. All prices are USD, checked against DeepSeek's official pricing page on 18 October 2026.
DeepSeek API prices (per 1M tokens)
| Model | Period | Input (cache hit) | Input (cache miss) | Output |
|---|---|---|---|---|
| deepseek-flash (V4.1-Flash-1017) | Peak | $0.006 | $0.30 | $1.20 |
| deepseek-flash (V4.1-Flash-1017) | Off-peak | $0.003 | $0.15 | $0.60 |
| deepseek-v4-pro | Peak | $0.044 | $1.32 | $3.96 |
| deepseek-v4-pro | Off-peak | $0.022 | $0.66 | $1.98 |
Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, excluding Chinese public holidays. All other hours, including weekends, count as off-peak. Off-peak rates are half the peak rates.
Source: DeepSeek pricing, checked 18 Oct 2026
Model details
| Detail | deepseek-flash | deepseek-v4-pro |
|---|---|---|
| Context length | 1M | 1M |
| Max output | Up to 384K | Up to 384K |
| Vision | Supported | Not supported |
| Thinking modes | Non-thinking and thinking (default) | Non-thinking and thinking (default) |
The older names deepseek-v4-flash and deepseek-v4-flash-vision-exp still work: they now route to DeepSeek-V4.1-Flash-1017 and are billed at the Flash price.
Search and Fetch API
DeepSeek Search and Fetch are each $0.75 per 1,000 successful requests.
Note (dated): Search and Fetch calls made through DeepSeek Harness, Claude Code or Codex are free for now. Per-request billing starts at 00:00 Beijing time on 1 November 2026.
DeepSeek vs Claude API prices (per 1M tokens, list price)
| Model | Input | Cached input | Output |
|---|---|---|---|
| DeepSeek V4.1 Flash, off-peak | $0.15 | $0.003 | $0.60 |
| DeepSeek V4.1 Flash, peak | $0.30 | $0.006 | $1.20 |
| DeepSeek V4 Pro, off-peak | $0.66 | $0.022 | $1.98 |
| DeepSeek V4 Pro, peak | $1.32 | $0.044 | $3.96 |
| Claude Haiku 5.5 (prompts up to 100K) | $0.10 | $0.01 | $0.50 |
| Claude Sonnet 5.5 | $2 | $0.10 | $10 |
| Claude Opus 5.5 | $4 | $0.20 | $20 |
Sources: Anthropic API pricing and DeepSeek pricing, checked 18 Oct 2026
These are list prices for tokens only. Models differ in capability, so compare price alongside quality for your own task.
Worked example (illustrative)
Example: a coding session that sends 1 million input tokens (all cache misses) and receives 200,000 output tokens costs, at list price:
- DeepSeek V4.1 Flash, peak: $0.30 + $0.24 = $0.54
- DeepSeek V4.1 Flash, off-peak: $0.15 + $0.12 = $0.27
- DeepSeek V4 Pro, peak: $1.32 + $0.792 = $2.112
- DeepSeek V4 Pro, off-peak: $0.66 + $0.396 = $1.056
- Claude Sonnet 5.5: $2.00 + $2.00 = $4.00
- Claude Opus 5.5: $4.00 + $4.00 = $8.00
Real bills depend on caching, retries and how many tokens your agent uses.
FAQ
How much does the DeepSeek API cost?
DeepSeek V4.1 Flash costs $0.30 per 1M input tokens (cache miss) and $1.20 per 1M output tokens at peak times, or $0.15 and $0.60 off-peak. DeepSeek V4 Pro costs $1.32 input and $3.96 output at peak, or $0.66 and $1.98 off-peak.
What are DeepSeek's peak hours?
01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, excluding Chinese public holidays. All other times are off-peak and cost half as much.
How much does DeepSeek cost compared with Claude?
At list price, DeepSeek V4.1 Flash off-peak is $0.15 input / $0.60 output per 1M tokens, versus $2 / $10 for Claude Sonnet 5.5 and $4 / $20 for Claude Opus 5.5. These are token prices only and do not compare model quality.
Is the DeepSeek Search API free?
Search and Fetch are $0.75 per 1,000 successful requests each. Calls made through DeepSeek Harness, Claude Code or Codex are free until per-request billing starts at 00:00 Beijing time on 1 November 2026.
What is the DeepSeek context window?
Both deepseek-flash and deepseek-v4-pro have a 1M-token context window with up to 384K output tokens.
Do cached tokens cost less on DeepSeek?
Yes. Cache-hit input is $0.006 per 1M tokens on Flash at peak and $0.044 on V4 Pro at peak, with off-peak at half those rates.
Get an email when DeepSeek API's price changes. One short email, sources included.
See all model prices · Claude Code cost · Agent cost cheat sheet
Independent. Prices change; check sources. Checked 18 Oct 2026.