Standard & Paid Price
Standard Price
| Meter | Standard Price |
|---|---|
| Input price | $0.6600 / 1M tokens |
| Completion price | $1.9800 / 1M tokens |
| Cache read price | $0.0220 / 1M tokens |
Dynamic pricing · 2 tiers · Time rules
Billing details
Vendor list price comparison
Description
DeepSeek V4 Pro 0813 — the higher-capability DeepSeek V4 tier for coding, reasoning, and agentic work, with a 1M-token context window and a 384K maximum output. It runs in both thinking (default) and non-thinking modes and supports tool calling and JSON output. Text in, text out. On /v1/responses, send the whole conversation in the input array on every turn: no conversation state is kept upstream, so requests that carry previous_response_id or conversation are refused.
Capabilities
- Input modalities
- text
- Output modalities
- text
- Tasks
- chat, reasoning
API endpoints
POST /v1/chat/completions(openai)POST /v1/responses(openai-response)POST /v1/messages(anthropic)