Skip to content

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

docs(deepseek): align V4 model metadata with official pricing and context

mason505267bf76514b15
diff --git a/README.md b/README.md
index b5da55f9..ab64e7b7 100644
--- a/README.md
+++ b/README.md
@@ -1854,10 +1854,10 @@ PentAGI supports 2 DeepSeek V4 models with tool calling, streaming, thinking mod
| Model ID | Thinking | Context | Price (Input/Output/Cache) | Use Case |
| --------------------- | -------- | ------- | -------------------------- | ---------------------------------------------------- |
-| `deepseek-v4-flash`* | ❌ | 128K | $0.28/$0.42/$0.03 | General dialogue, code generation, tool calling |
-| `deepseek-v4-pro`* | ✅ | 128K | $0.28/$0.42/$0.03 | Advanced reasoning, complex logic, security analysis |
+| `deepseek-v4-flash`* | ❌ | 1M | $0.14/$0.28/$0.0028 | General dialogue, code generation, tool calling |
+| `deepseek-v4-pro`* | ✅ | 1M | $0.435/$0.87/$0.003625 | Advanced reasoning, complex logic, security analysis |
-**Prices**: Per 1M tokens. Cache pricing is for prompt caching (10% of input cost). Models with thinking support include reinforcement learning chain-of-thought reasoning.
+**Prices**: Per 1M tokens. Cache pricing applies to prompt tokens served from cache and is heavily discounted versus input price. Models with thinking support include reinforcement learning chain-of-thought reasoning.
> The legacy model names `deepseek-chat` and `deepseek-reasoner` are scheduled
> for deprecation by DeepSeek on 2026-07-24. Existing user configurations
@@ -1865,7 +1865,7 @@ PentAGI supports 2 DeepSeek V4 models with tool calling, streaming, thinking mod
> use the current V4 names.
**Key Features**:
-- **Automatic Prompt Caching**: 40-60% cost reduction on repeated context (10% of input price)
+- **Automatic Prompt Caching**: Significant cost reduction on repeated context via cache-hit pricing far below input price
- **Extended Thinking**: Reinforcement learning CoT for complex security analysis (deepseek-v4-pro)
- **Strong Coding**: Optimized for code generation and exploit development
- **Tool Calling**: Seamless integration with 20+ pentesting tools via function calling
diff --git a/backend/pkg/providers/deepseek/config.yml b/backend/pkg/providers/deepseek/config.yml
index 4f95bf6a..bbecf21b 100644
--- a/backend/pkg/providers/deepseek/config.yml
+++ b/backend/pkg/providers/deepseek/config.yml
@@ -5,9 +5,9 @@ simple:
n: 1
max_tokens: 8192
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
simple_json:
model: deepseek-v4-flash
@@ -17,45 +17,45 @@ simple_json:
max_tokens: 4096
json: true
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
primary_agent:
model: deepseek-v4-pro
n: 1
max_tokens: 16384
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
assistant:
model: deepseek-v4-pro
n: 1
max_tokens: 16384
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
generator:
model: deepseek-v4-pro
n: 1
max_tokens: 32768
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
refiner:
model: deepseek-v4-pro
n: 1
max_tokens: 20480
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
adviser:
model: deepseek-v4-flash
@@ -64,18 +64,18 @@ adviser:
n: 1
max_tokens: 8192
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
reflector:
model: deepseek-v4-pro
n: 1
max_tokens: 4096
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
searcher:
model: deepseek-v4-flash
@@ -84,9 +84,9 @@ searcher:
n: 1
max_tokens: 4096
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
enricher:
model: deepseek-v4-flash
@@ -95,33 +95,33 @@ enricher:
n: 1
max_tokens: 4096
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
coder:
model: deepseek-v4-pro
n: 1
max_tokens: 20480
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
installer:
model: deepseek-v4-pro
n: 1
max_tokens: 16384
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
pentester:
model: deepseek-v4-pro
n: 1
max_tokens: 16384
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
diff --git a/backend/pkg/providers/deepseek/models.yml b/backend/pkg/providers/deepseek/models.yml
index 79aae7ed..79b465ee 100644
--- a/backend/pkg/providers/deepseek/models.yml
+++ b/backend/pkg/providers/deepseek/models.yml
@@ -1,15 +1,15 @@
- name: deepseek-v4-flash
- description: DeepSeek V4 Flash - Cost-efficient general-purpose model suitable for dialogue, code generation, and tool calling. Supports JSON output and tool calls. 128K context.
+ description: DeepSeek V4 Flash - Cost-efficient general-purpose model suitable for dialogue, code generation, and tool calling. Supports JSON output and tool calls. 1M context, up to 384K output tokens.
thinking: false
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
- name: deepseek-v4-pro
- description: DeepSeek V4 Pro - Higher-tier reasoning model suitable for complex logic, mathematical reasoning, and security analysis. 128K context.
+ description: DeepSeek V4 Pro - Higher-tier reasoning model suitable for complex logic, mathematical reasoning, and security analysis. 1M context, up to 384K output tokens.
thinking: true
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
diff --git a/examples/configs/deepseek.provider.yml b/examples/configs/deepseek.provider.yml
index 6c2cb6f4..b9774a28 100644
--- a/examples/configs/deepseek.provider.yml
+++ b/examples/configs/deepseek.provider.yml
@@ -5,9 +5,9 @@ simple:
n: 1
max_tokens: 4000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
simple_json:
model: deepseek-v4-flash
@@ -17,45 +17,45 @@ simple_json:
max_tokens: 4000
json: true
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
primary_agent:
model: deepseek-v4-pro
n: 1
max_tokens: 8000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
assistant:
model: deepseek-v4-pro
n: 1
max_tokens: 8000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
generator:
model: deepseek-v4-pro
n: 1
max_tokens: 8000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
refiner:
model: deepseek-v4-pro
n: 1
max_tokens: 8000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
adviser:
model: deepseek-v4-flash
@@ -64,18 +64,18 @@ adviser:
n: 1
max_tokens: 6000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
reflector:
model: deepseek-v4-pro
n: 1
max_tokens: 4000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
searcher:
model: deepseek-v4-flash
@@ -84,9 +84,9 @@ searcher:
n: 1
max_tokens: 4000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
enricher:
model: deepseek-v4-flash
@@ -95,33 +95,33 @@ enricher:
n: 1
max_tokens: 4000
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.14
+ output: 0.28
+ cache_read: 0.0028
coder:
model: deepseek-v4-pro
n: 1
max_tokens: 16384
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
installer:
model: deepseek-v4-pro
n: 1
max_tokens: 8192
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625
pentester:
model: deepseek-v4-pro
n: 1
max_tokens: 8192
price:
- input: 0.28
- output: 0.42
- cache_read: 0.028
+ input: 0.435
+ output: 0.87
+ cache_read: 0.003625