1M input tokens
$0.66
Input-only example at the listed standard token price.
DeepSeek model cost planner
DeepSeek-V4-Pro
Higher-capability DeepSeek V4 model for advanced reasoning, coding, agentic workflows, and long outputs.
Pricing details
DeepSeek-V4-Pro pricing
These values come from the central model pricing data used by the calculator.
Input price
$0.66 / 1M tokens
Output price
$1.98 / 1M tokens
Cached input price
$0.022 / 1M tokens
Pricing unit
Per 1M tokens
Verified provider pricing
StableDeepSeekdeepseek-v4-pro
Last verified Aug 28, 2026Official source
Estimates vary by tier, modality, caching, batch usage, token thresholds, and other provider conditions.
- Pricing notes
- Higher-capability DeepSeek V4 model for advanced reasoning, coding, agentic workflows, and long outputs.
Deterministic cost examples
These shared examples apply the listed token prices directly. They illustrate arithmetic only and are not claims about a typical user workload.
1M output tokens
$1.98
Output-only example at the listed standard token price.
Example 1M-token mix
$0.99
Defined as 750K input tokens plus 250K output tokens.
1M cached-input tokens
$0.022
Cached-input-only example using the listed cached price.
Calculator
Calculate DeepSeek-V4-Pro API cost
DeepSeek and DeepSeek-V4-Pro are preselected so the estimate starts on this exact model.
Estimated results
Run the calculator to see projected cost and usage volume.
Enter your usage details, then select Calculate estimate to see your projected cost.
Estimated cost = input usage cost + output usage cost + supported optional charges.
Verified model facts
DeepSeek-V4-Pro model details
Only fields present in canonical pricing, identity, or reviewed catalog data are shown.
- Provider
- DeepSeek
- Model family
- DeepSeek V4
- Lifecycle
- Stable
- API availability
- Available
- Catalog category
- Reasoning
- Context window
- 1,000,000 tokens
- Max output tokens
- 384,000 tokens
- Input modalities
- Text
- Output modalities
- Text
- Capabilities
- Advanced reasoning, Coding, Json output, Tool calls, Chat prefix completion beta, Fim completion beta, Context caching, Agents
- Service tier
- Standard
- Context tier
- Default
- Pricing region
- global
Use-case calculators
Plan workflows with DeepSeek-V4-Pro
These calculator pages are selected from canonical model capabilities and provider context.
AI Agent Cost Calculator
Estimate multi-step agent cost from tasks, tool calls, and token usage.
AI Chatbot Cost Calculator
Estimate product chat and assistant usage from users, messages, and tokens.
Customer Support AI Cost Calculator
Model support automation costs from tickets, replies, and token usage.
Related models
Other DeepSeek models
Run the same assumptions against another model from this provider.
Alternatives
Capability-linked lower-price alternatives
Every candidate shares at least one listed capability, uses the same pricing unit, and has a lower canonical input or output price. Price does not establish equivalent quality.
DeepSeek
DeepSeek-V4-Flash
Lower input and output prices. Input $0.22 / 1M tokens, output $0.66 / 1M tokens.
Shared listed capabilities: Text, Function calling.
Cohere
Command R7B
Lower input and output prices. Input $0.0375 / 1M tokens, output $0.15 / 1M tokens.
Shared listed capabilities: Text, Function calling.
Groq
Llama 3.1 8B
Lower input and output prices. Input $0.05 / 1M tokens, output $0.08 / 1M tokens.
Shared listed capabilities: Text.
Entity relationships
Provider, calculator, and exact comparisons
Continue to this model's canonical provider, provider calculator, or an exact related comparison.