Model API

DeepSeek

DeepSeek · source page ↗ · last checked Aug 24, 2026, 12:00 PM

Current pricing

● live captured Aug 24, 2026, 12:00 PM

Model / item	Input	Output
deepseek-v4-flash	$0.14 / 1M tokens (cache miss)	$0.28 / 1M tokens · Cache-hit input: $0.0028 / 1M tokens. 1M context, 384K max output. Non-thinking + thinking (default) modes. Replaces deprecated deepseek-chat (non-thinking) / deepseek-reasoner (thinking).
deepseek-v4-pro	$0.435 / 1M tokens (cache miss)	$0.87 / 1M tokens · Cache-hit input: $0.003625 / 1M tokens. 1M context, 384K max output. Non-thinking + thinking (default) modes.
DeepSeek-V4-Pro-0813	$0.007 / 1M tokens	$0.66 / 1M tokens

USD. Billing: expense = number of tokens x price. "Product prices may vary and DeepSeek reserves the right to adjust them" — check the page for the latest. Legacy model names deepseek-chat and deepseek-reasoner are deprecated 2026/07/24 15:59 UTC (mapping to v4-flash non-thinking / thinking modes). No off-peak/discount tier listed on this page version.

Rate & usage limits ● livestructure only

This provider doesn't publish numeric request/token limits on its docs — only the usage-tier structure below. Your actual limits appear in your account dashboard.

Tier	Notes
deepseek-v4-pro	Concurrency limit: 500. Per-user_id concurrency limit: 500 when using user_id isolation.
deepseek-v4-flash	Concurrency limit: 2500. Per-user_id concurrency limit: 2500 when using user_id isolation.
deepseek-v4-flash-vision-exp	Concurrency limit: 2500. Per-user_id concurrency limit: 2500 when using user_id isolation.

Limits are concurrency-based (concurrent connections), not traditional RPM/TPM/RPD rates. Account-level limits apply across all API keys. Per-user_id limits also enforced when user_id parameter is passed. Higher concurrency available via capacity expansion request at no additional cost.

Source: https://api-docs.deepseek.com/quick_start/rate_limit

Currently listed models

captured Aug 24, 2026, 12:00 PM

deepseek-ai/DeepSeek-Coder-V2-Base license:other 2024-06-14
deepseek-ai/DeepSeek-Coder-V2-Instruct license:other 2024-06-14
deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 license:other 2024-09-05
deepseek-ai/DeepSeek-Coder-V2-Lite-Base license:other 2024-06-14
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct license:other 2024-06-14
deepseek-ai/DeepSeek-Math-V2 license:apache-2.0 2025-11-27
deepseek-ai/DeepSeek-OCR license:mit 2025-10-17
deepseek-ai/DeepSeek-OCR-2 license:apache-2.0 2026-01-27
deepseek-ai/DeepSeek-Prover-V2-671B license:? 2025-04-30
deepseek-ai/DeepSeek-R1 license:mit 2025-01-20
deepseek-ai/DeepSeek-R1-0528 license:mit 2025-05-28
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B license:mit 2025-05-29
deepseek-ai/DeepSeek-R1-Distill-Llama-70B license:mit 2025-01-20
deepseek-ai/DeepSeek-R1-Distill-Llama-8B license:mit 2025-01-20
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B license:mit 2025-01-20
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B license:mit 2025-01-20
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B license:mit 2025-01-20
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B license:mit 2025-01-20
deepseek-ai/DeepSeek-R1-Zero license:mit 2025-01-20
deepseek-ai/DeepSeek-V2 license:other 2024-04-22
deepseek-ai/DeepSeek-V2-Chat license:other 2024-04-28
deepseek-ai/DeepSeek-V2-Chat-0628 license:other 2024-07-18
deepseek-ai/DeepSeek-V2-Lite license:other 2024-05-15
deepseek-ai/DeepSeek-V2-Lite-Chat license:other 2024-05-15
deepseek-ai/DeepSeek-V2.5 license:other 2024-09-05
deepseek-ai/DeepSeek-V2.5-1210 license:other 2024-12-10
deepseek-ai/DeepSeek-V3 license:? 2024-12-25
deepseek-ai/DeepSeek-V3-0324 license:mit 2025-03-24
deepseek-ai/DeepSeek-V3.1 license:mit 2025-08-21
deepseek-ai/DeepSeek-V3.1-Base license:mit 2025-08-19
deepseek-ai/DeepSeek-V3.1-Terminus license:mit 2025-09-22
deepseek-ai/DeepSeek-V3.2 license:mit 2025-12-01
deepseek-ai/DeepSeek-V3.2-Exp license:mit 2025-09-29
deepseek-ai/DeepSeek-V3.2-Exp-Base license:mit 2025-09-29
deepseek-ai/DeepSeek-V3.2-Speciale license:mit 2025-11-28
deepseek-ai/DeepSeek-V4-Flash license:mit 2026-04-22
deepseek-ai/DeepSeek-V4-Flash-0731 license:mit 2026-07-31
deepseek-ai/DeepSeek-V4-Flash-DSpark license:mit 2026-06-27
deepseek-ai/DeepSeek-V4-Pro license:mit 2026-04-22
deepseek-ai/DeepSeek-V4-Pro-0813 license:mit 2026-08-13
deepseek-ai/DeepSeek-V4-Pro-DSpark license:mit 2026-06-27
deepseek-ai/ESFT-gate-code-lite license:? 2024-07-04
deepseek-ai/ESFT-gate-intent-lite license:? 2024-07-04
deepseek-ai/ESFT-gate-law-lite license:? 2024-07-04
deepseek-ai/ESFT-gate-math-lite license:? 2024-07-04
deepseek-ai/ESFT-gate-summary-lite license:? 2024-07-04
deepseek-ai/ESFT-gate-translation-lite license:? 2024-07-04
deepseek-ai/ESFT-token-code-lite license:? 2024-07-04
deepseek-ai/ESFT-token-intent-lite license:? 2024-07-04
deepseek-ai/ESFT-token-law-lite license:? 2024-07-04
deepseek-ai/ESFT-token-math-lite license:? 2024-07-04
deepseek-ai/ESFT-token-summary-lite license:? 2024-07-04
deepseek-ai/ESFT-token-translation-lite license:? 2024-07-04
deepseek-ai/ESFT-vanilla-lite license:? 2024-07-04
deepseek-ai/Janus-1.3B license:mit 2024-10-18
deepseek-ai/Janus-Pro-1B license:mit 2025-01-26
deepseek-ai/Janus-Pro-7B license:mit 2025-01-26
deepseek-ai/JanusFlow-1.3B license:mit 2024-11-12
deepseek-ai/deepseek-coder-1.3b-instruct license:other 2023-10-29
deepseek-ai/deepseek-coder-33b-instruct license:other 2023-11-01

In the news · DeepSeek

DeepSeek releases new multimodal model via TahawulTech.com — DeepSeek releases new multimodal model TahawulTech.com · Aug 24, 2026, 9:21 AM
DeepSeek Launches Multimodal Vision Model V4-Flash-Vision-Exp via KuCoin — DeepSeek Launches Multimodal Vision Model V4-Flash-Vision-Exp KuCoin · Aug 24, 2026, 8:25 AM
Nvidia is going after OpenAI and DeepSeek with its $6 billion Poolside deal via India Today — Nvidia is going after OpenAI and DeepSeek with its $6 billion Poolside deal India Today · Aug 24, 2026, 4:30 AM
Nvidia Is Coming for OpenAI and DeepSeek With $6 Billion Poolside Deal to Build a Powerful Open-Weight AI via Benzinga — Nvidia Is Coming for OpenAI and DeepSeek With $6 Billion Poolside Deal to Build a Powerful Open-Weight AI Benzinga · Aug 24, 2026, 4:21 AM
Nvidia Is Coming for OpenAI and DeepSeek With $6 Billion Poolside Deal to Build a Powerful Open-Weight AI Model: Report via Longbridge — Nvidia Is Coming for OpenAI and DeepSeek With $6 Billion Poolside Deal to Build a Powerful Open-Weight AI Model: Report Longbridge · Aug 24, 2026, 4:21 AM
Nvidia Is Coming for OpenAI and DeepSeek With $6 Billion Poolside Deal to Build a Powerful Open-Weight AI Model: Report via Yahoo Finance — Nvidia Is Coming for OpenAI and DeepSeek With $6 Billion Poolside Deal to Build a Powerful Open-Weight AI Model: Report Yahoo Finance · Aug 24, 2026, 4:21 AM
DeepSeek API pricing: Weekend workloads avoid weekday peak rates Meta via dqindia.com — DeepSeek API pricing: Weekend workloads avoid weekday peak rates Meta dqindia.com · Aug 24, 2026, 4:02 AM
OpenAI Unveils Harness Post-Black Whale Launch: Competing for Dominance in the Agent Runtime Space via 36 Kr — OpenAI Unveils Harness Post-Black Whale Launch: Competing for Dominance in the Agent Runtime Space 36 Kr · Aug 24, 2026, 2:33 AM

Importance-filtered press coverage (Google News) mentioning DeepSeek. Headlines link to the original; verify before acting.

Change history

Pricing Aug 21, 2026, 12:00 PM

DeepSeek API pricing changed

Concurrency limit raised to 3; cache-based pricing tiers removed

rate_limitConcurrency limit increased from 2 to 3

pricing_structureCache hit/miss pricing tiers removed; standard per-token pricing now used

View raw diff +5 −4

- 1M INPUT TOKENS (CACHE HIT)
- 1M INPUT TOKENS (CACHE MISS)
- Concurrency Limit(2)
- (2) For more details on concurrency limits, please refer to Rate Limit & Isolation
+ 1M INPUT TOKENS
+ 1M INPUT TOKENS
+ Concurrency Limit(3)
+ (2) Images sent to deepseek-v4-flash-vision-exp are converted into tokens based on their dimensions and billed as input tokens together with your text tokens. See Vision: Token Usage for the conversion rule.
+ (3) For more details on concurrency limits, please refer to Rate Limit & Isolation.

Pricing Aug 16, 2026, 4:14 PM

DeepSeek API pricing changed

Pricing details for DeepSeek-V4-Pro-0813 have been published with specific token costs: $0.22 per 1M input tokens (cache miss), $0.66 per 1M output tokens, and discounted rates for cache hits.

now$0.00$0.02$0.01$0.04$0.22$0.66$0.44$1.32

View raw diff +22 −5

- (1) The deepseek-v4-flash model has been updated to DeepSeek-V4-Flash-0731, and the deepseek-v4-pro model has been updated to DeepSeek-V4-Pro-0813. The calling method remains unchanged — simply use deepseek-v4-flash or deepseek-v4-pro to access the latest version.
- -H "Authorization: Bearer ${DEEPSEEK_API_KEY}" \
- "model": "deepseek-v4-pro",
- model="deepseek-v4-pro",
- model: "deepseek-v4-pro",
+ The prices listed below are in units of per 1M tokens. A token, the smallest unit of text that the model recognizes, can be a word, a number, or even a punctuation mark. We will bill based on the total number of input and output tokens by the model.
+ DeepSeek-V4-Pro-0813
+ 1M INPUT TOKENS (CACHE HIT)
+ $0.007
+ $0.022
+ $0.014
+ $0.044
+ 1M INPUT TOKENS (CACHE MISS)
+ $0.22
+ $0.66
+ $0.44
+ $1.32
+ 1M OUTPUT TOKENS
+ $0.66
+ $1.98
+ $1.32
+ $3.96
+ Concurrency Limit(2)
+ (2) For more details on concurrency limits, please refer to Rate Limit & Isolation
+ The expense = number of tokens × price.
+ Product prices may vary and DeepSeek reserves the right to adjust them. We recommend topping up based on your actual usage and regularly checking this page for the most recent pricing information.
+ Token & Token Usage

Model Aug 13, 2026, 6:01 PM

DeepSeek (weights) models changed

DeepSeek model changed from deepseek-coder-33b-base to DeepSeek-V4-Pro-0813 with updated license and date.
- Model updated from deepseek-coder-33b-base to DeepSeek-V4-Pro-0813
- License changed from other to mit
- Release date changed from 2023-10-28 to 2026-08-13
View raw diff +1 −1
```
- deepseek-ai/deepseek-coder-33b-base license:other 2023-10-28
+ deepseek-ai/DeepSeek-V4-Pro-0813 license:mit 2026-08-13
```

Pricing Aug 13, 2026, 6:00 PM

DeepSeek API pricing changed

DeepSeek-V4-Flash and DeepSeek-V4-Pro models updated to new versions (DeepSeek-V4-Flash-0731 and DeepSeek-V4-Pro-0813) with unchanged API calling methods.

deepseek-v4-flash model updated to DeepSeek-V4-Flash-0731
deepseek-v4-pro model updated to DeepSeek-V4-Pro-0813
calling method remains unchanged for both models

View raw diff +5 −32

- The prices listed below are in units of per 1M tokens. A token, the smallest unit of text that the model recognizes, can be a word, a number, or even a punctuation mark. We will bill based on the total number of input and output tokens by the model.
- DeepSeek-V4-Pro-0813
- 1M INPUT TOKENS (CACHE HIT)
- $0.0028
- $0.003625
- 1M INPUT TOKENS (CACHE MISS)
- $0.14
- $0.435
- 1M OUTPUT TOKENS
- $0.28
- $0.87
- Concurrency Limit(2)
- (1) DeepSeek API pricing will be updated to peak / off-peak billing, with off-peak rates at half the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC (all other hours are off-peak). The new prices take effect at 16:00 UTC on August 16, 2026, as follows:
- 1M INPUT TOKENS (CACHE HIT)
- 1M INPUT TOKENS (CACHE MISS)
- 1M OUTPUT TOKENS
- $0.007
- $0.22
- $0.66
- $0.014
- $0.44
- $1.32
- $0.022
- $0.66
- $1.98
- $0.044
- $1.32
- $3.96
- (2) For more details on concurrency limits, please refer to Rate Limit & Isolation
- The expense = number of tokens × price.
- Product prices may vary and DeepSeek reserves the right to adjust them. We recommend topping up based on your actual usage and regularly checking this page for the most recent pricing information.
- Token & Token Usage
+ (1) The deepseek-v4-flash model has been updated to DeepSeek-V4-Flash-0731, and the deepseek-v4-pro model has been updated to DeepSeek-V4-Pro-0813. The calling method remains unchanged — simply use deepseek-v4-flash or deepseek-v4-pro to access the latest version.
+ -H "Authorization: Bearer ${DEEPSEEK_API_KEY}" \
+ "model": "deepseek-v4-pro",
+ model="deepseek-v4-pro",
+ model: "deepseek-v4-pro",

Pricing Aug 13, 2026, 12:00 PM

DeepSeek API pricing changed

DeepSeek API transitioning to peak/off-peak pricing tiers effective August 16, 2026

DeepSeek-V4-Pro · pricing_structureFlat rate pricing→Peak/off-peak tiered pricing effective Aug 16, 2026

View raw diff +13 −1

- (1) We plan to raise the overall pricing for DeepSeek API services in the near future, with a significant increase expected. Please plan your usage accordingly. The specific pricing plan will be subject to official notice.
+ (1) DeepSeek API pricing will be updated to peak / off-peak billing, with off-peak rates at half the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC (all other hours are off-peak). The new prices take effect at 16:00 UTC on August 16, 2026, as follows:
+ $0.007
+ $0.22
+ $0.66
+ $0.014
+ $0.44
+ $1.32
+ $0.022
+ $0.66
+ $1.98
+ $0.044
+ $1.32
+ $3.96

Pricing Aug 12, 2026, 6:00 PM

DeepSeek API pricing changed

DeepSeek-V4-Pro renamed to V4-Pro-0813 and concurrency limit lowered from 3 to 2

modelModel renamed from DeepSeek-V4-Pro to DeepSeek-V4-Pro-0813

rate_limitConcurrency limit reduced from (3) to (2)

View raw diff +4 −5

- DeepSeek-V4-Pro
- Concurrency Limit(3)
- (1) The Responses API currently only supports the deepseek-v4-flash model, and does not yet support the deepseek-v4-pro model. We will add support for the deepseek-v4-pro model in early August 2026.
- (2) We plan to raise the overall pricing for DeepSeek API services in the near future, with a significant increase expected. Please plan your usage accordingly. The specific pricing plan will be subject to official notice.
- (3) For more details on concurrency limits, please refer to Rate Limit & Isolation
+ DeepSeek-V4-Pro-0813
+ Concurrency Limit(2)
+ (1) We plan to raise the overall pricing for DeepSeek API services in the near future, with a significant increase expected. Please plan your usage accordingly. The specific pricing plan will be subject to official notice.
+ (2) For more details on concurrency limits, please refer to Rate Limit & Isolation

Pricing Aug 6, 2026, 6:00 AM

DeepSeek API pricing changed

Peak/off-peak pricing policy replaced with general price increase warning

Peak/off-peak pricing policy removed from messaging; general price increase warning now in effect

View raw diff +1 −1

- (2) The DeepSeek API service will soon adopt a peak/off-peak pricing policy. During peak hours, prices will be 2x the regular prices, applicable to all billing items. The effective date will be subject to the official announcement. [Peak hours: 9:00–12:00 and 14:00–18:00 (Beijing Time, UTC+8) daily]
+ (2) We plan to raise the overall pricing for DeepSeek API services in the near future, with a significant increase expected. Please plan your usage accordingly. The specific pricing plan will be subject to official notice.

Model Jul 31, 2026, 6:00 PM

DeepSeek (weights) models changed

DeepSeek model weights changed from deepseek-coder-1.3b-base to DeepSeek-V4-Flash-0731 with license change from other to MIT.
- Model identifier: deepseek-ai/deepseek-coder-1.3b-base → deepseek-ai/DeepSeek-V4-Flash-0731
- License: other → mit
- Date: 2023-10-28 → 2026-07-31
View raw diff +1 −1
```
- deepseek-ai/deepseek-coder-1.3b-base license:other 2023-10-28
+ deepseek-ai/DeepSeek-V4-Flash-0731 license:mit 2026-07-31
```

Pricing Jul 31, 2026, 6:00 AM

DeepSeek API pricing changed

Peak/off-peak pricing policy (2x multiplier) coming to DeepSeek API; Responses API Roadmap clarified

Peak/off-peak pricing policy announced (2x during peak hours, effective date TBD)

View raw diff +4 −2

- Concurrency Limit(1)
- (1) For more details on concurrency limits, please refer to Rate Limit & Isolation
+ Concurrency Limit(3)
+ (1) The Responses API currently only supports the deepseek-v4-flash model, and does not yet support the deepseek-v4-pro model. We will add support for the deepseek-v4-pro model in early August 2026.
+ (2) The DeepSeek API service will soon adopt a peak/off-peak pricing policy. During peak hours, prices will be 2x the regular prices, applicable to all billing items. The effective date will be subject to the official announcement. [Peak hours: 9:00–12:00 and 14:00–18:00 (Beijing Time, UTC+8) daily]
+ (3) For more details on concurrency limits, please refer to Rate Limit & Isolation

Pricing Jul 27, 2026, 6:00 AM

DeepSeek API pricing changed

Minor footnote update to concurrency limit reference

Concurrency limit footnote changed from (2) to (1)

View raw diff +2 −2

- Concurrency Limit(2)
- (2) For more details on concurrency limits, please refer to Rate Limit & Isolation
+ Concurrency Limit(1)
+ (1) For more details on concurrency limits, please refer to Rate Limit & Isolation

Model Jul 18, 2026, 12:00 AM

DeepSeek (weights) models changed

DeepSeek-R1-Distill-Qwen-14B model added with MIT license as of 2025-01-20
- Model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- License: MIT
- Date: 2025-01-20
View raw diff +1 −0
```
+ deepseek-ai/DeepSeek-R1-Distill-Qwen-14B license:mit 2025-01-20
```
Model Jun 28, 2026, 12:47 PM

DeepSeek (weights) models changed

Removed deepseek-coder-6.7b-base model from available weights.
- deepseek-coder-6.7b-base model removed
- license:other
- dated 2023-10-23
View raw diff +0 −1
```
- deepseek-ai/deepseek-coder-6.7b-base license:other 2023-10-23
```
Model Jun 27, 2026, 6:00 AM

DeepSeek (weights) models changed

Two new DeepSeek models added: DeepSeek-V4-Flash-DSpark and DeepSeek-V4-Pro-DSpark, both MIT licensed with release date 2026-06-27.
- deepseek-ai/DeepSeek-V4-Flash-DSpark
- deepseek-ai/DeepSeek-V4-Pro-DSpark
- license:mit, 2026-06-27
View raw diff +2 −0
```
+ deepseek-ai/DeepSeek-V4-Flash-DSpark license:mit 2026-06-27
+ deepseek-ai/DeepSeek-V4-Pro-DSpark license:mit 2026-06-27
```