DeepSeek · October 2026
DeepSeek API pricing, every model
14 DeepSeek models, from $0.091 to $1.60 per million input tokens. The price floor for strong open-weight models, with very cheap cache reads.
Prices from OpenRouter’s models API, updated October 29, 2026
DeepSeek V4 Flash 0423
$0.091 in · $0.182 outAbout $6.28 a month for a 1,000-chats-a-day support bot.
DeepSeek V4.1 Flash 1017
$0.15 in · $0.60 outReleased 2026-10-17, 1.05M tokens of context.
DeepSeek V4.1 Flash 1017
−98%Cached input costs $0.003 instead of $0.15 per 1M tokens.
All DeepSeek models and prices
| Model | Released | Input /1M | Output /1M | Cache read /1M | Batch in / out | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 2026-10-17 | $0.15 | $0.60 | $0.003 | – | 1.05M | $13.95 |
| DeepSeek V4.1 Flash | 2026-09-10 | $0.045 | $0.50 | $0.006 | $0.05 / $0.15 | 1.05M | $8.03 |
| DeepSeek V4 Flash Vision Exp | 2026-08-21 | $0.216 | $0.647 | $0.0069 | – | 1.05M | $17.46 |
| DeepSeek V4 Pro 0813 | 2026-08-12 | $0.66 | $1.98 | $0.022 | – | 1.05M | $53.46 |
| DeepSeek V4 Flash 0731 | 2026-07-31 | $0.119 | $0.238 | $0.024 | – | 1.05M | $8.21 |
| DeepSeek V4 Flash 0423 | 2026-04-24 | $0.091 | $0.182 | $0.018 | – | 1.05M | $6.28 |
| DeepSeek V4 Pro 0423 | 2026-04-24 | $1.60 | $3.20 | $0.135 | – | 1.05M | $110 |
| DeepSeek V3.2 | 2025-12-01 | $0.28 | $0.42 | $0.028 | – | 164K | $17.64 |
| DeepSeek V3.2 Exp | 2025-09-29 | $0.27 | $0.41 | – | – | 164K | $17.07 |
| DeepSeek V3.1 Terminus | 2025-09-22 | $0.27 | $1 | – | – | 164K | $24.15 |
| DeepSeek V3.1 | 2025-08-21 | $0.25 | $0.95 | $0.13 | – | 164K | $22.65 |
| R1 0528 | 2025-05-28 | $0.50 | $2.15 | $0.35 | – | 164K | $48.30 |
| DeepSeek V3 0324 | 2025-03-24 | $0.29 | $1.14 | $0.11 | – | 164K | $26.73 |
| DeepSeek V3 | 2024-12-26 | $0.257 | $1.03 | – | – | 164K | $23.93 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
What three real workloads cost a month
| Model | Support chatbot | Daily summaries | Coding agent |
|---|---|---|---|
| DeepSeek V4 Flash 0423 | $6.28 | $98.28 | $27.96 |
| DeepSeek V4 Flash 0731 | $8.21 | $129 | $36.56 |
| DeepSeek V4.1 Flash | $8.03 | $85.50 | $21.94 |
| DeepSeek V4.1 Flash 1017 | $13.95 | $189 | $37.73 |
| DeepSeek V3.2 Exp | $17.07 | $280 | $204 |
| DeepSeek V3.2 | $17.64 | $290 | $66.53 |
| DeepSeek V4 Flash Vision Exp | $17.46 | $252 | $50.52 |
| DeepSeek V3.1 | $22.65 | $311 | $134 |
Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out · Daily summaries: 10,000 a day, 3,000 tokens in, 300 out · Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out. Cached share billed at the cache-read price where the model has one.
Compare with other providers
DeepSeek pricing questions
How much does the DeepSeek API cost?
DeepSeek’s models range from $0.091 per 1M input tokens and $0.182 per 1M output tokens (DeepSeek V4 Flash 0423) to $1.60 and $3.20 (DeepSeek V4 Pro 0423). The newest, DeepSeek V4.1 Flash 1017, costs $0.15 in and $0.60 out.
Which DeepSeek model is the cheapest?
DeepSeek V4 Flash 0423, at $0.091 per 1M input tokens. A support chatbot doing 1,000 chats a day would cost about $6.28 a month on it.
Does DeepSeek discount cached prompts?
Yes. On DeepSeek V4.1 Flash 1017, cached input costs $0.003 per 1M tokens instead of $0.15, 98% less. Long, repeated system prompts and agent loops benefit most.
Is there a batch discount?
1 DeepSeek models have a batch price, typically half the normal rate, for jobs that can wait (up to 24 hours). See the Batch column below.
How do I track my DeepSeek spend per product?
Route it through OpenRouter with one API key per product and connect OpenRouter to Glow: you get spend by model, API key and product every day, with cache hit rate. Track AI spend.
See your real DeepSeek bill.
Glow shows what you actually spend by model, API key and product, every day, and which cheaper model would do the same job.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial