DeepSeek V4 Pro API: pricing, base URL and quick setup
Use DeepSeek V4 Pro on A2Agent with model ID deepseek-v4-pro. The catalog lists a 1M context window. Check token rates below and verify the features your app needs.
Specifications and pricing
| Model ID | deepseek-v4-pro |
|---|---|
| Platform | DeepSeek |
| Context window | 1M |
| Tagged for | chat, reasoning |
| Discount | — |
| Input / 1M tokens | $0.435 |
| Output / 1M tokens | $0.870 |
USD per 1M tokens. Final billing depends on your API key group and metered usage.
Cheapest way to use DeepSeek V4 Pro
Prices on this page come from the live catalog. Compare the official price with the A2Agent price in the table above, then multiply by your monthly token volume.
Quick setup
curl https://a2agent.me/v1/chat/completions \
-H "content-type: application/json" \
-H "authorization: Bearer sk-your-a2agent-key" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Reply with OK"}]
}'Using it from a coding client
Follow the Claude Code or Codex CLI guide, then test a small reasoning task and tool call. Compare billed usage and accepted outputs with Flash before choosing a default.
How it compares within its family
These comparisons use catalog context limits, tags and reference rates, not independent quality benchmarks. Rates can change. Check current pricing above and test your workload; a higher price or a larger context window does not establish better results.
V4 Pro and V4 Flash both carry a 1M context and both are tagged for reasoning here, so the catalog alone does not establish a quality difference. V4 Pro lists at $0.435 per million input tokens and $0.87 per million output. V4 Flash lists at $0.14 and $0.28. That is roughly three times the rate for the same window and the same tags. The question to test is whether Pro produces more usable answers on your task. Run the same prompts on both and count failed outputs and retries as part of the cost. Three attempts are not a guarantee of a correct answer. Nothing in the catalog data separates the two on context, so a prompt that fits Flash fits Pro as well.
Other models on this platform
Questions
How does V4 Pro differ from V4 Flash?
Same 1M context, same reasoning tag. Pro lists at about three times Flash on both input and output. The decision is cost against capability, not features.
What is the context window?
1M tokens, per the DeepSeek pricing page that feeds the same billing table this gateway charges against.
Do I need a Chinese phone number to use it?
No. A2Agent fronts the upstream, so you register here with an email address and call it from anywhere the gateway serves.
Which API protocol should I use?
The one your client speaks. The Claude Code guide uses Anthropic Messages and the Codex CLI guide uses OpenAI Responses; each gives the endpoint. Call GET /v1/models with your key first to confirm it can reach this model.
Billed per token. Top up from $1, no top-up fee.