DeepSeek V4 Pro Max
DeepSeek V4 Pro Max is served by 1 provider that kRouter can route to, with a 1M-token context window and pricing from $0.14 per 1M input tokens. Routing through kRouter means any OpenAI-compatible tool can reach it, with failover to another model if the provider is rate limited.
How to route to DeepSeek V4 Pro Max
| Provider | Route as |
|---|---|
| DeepSeek | deepseek/deepseek-v4-pro-max |
What DeepSeek V4 Pro Max is suited for
A 1M window is large enough to hold a substantial part of a codebase in one turn, so it suits whole-repo refactors and long agent sessions where the history keeps growing. It supports extended reasoning, which helps on debugging and multi-step planning but spends output tokens on thinking before the answer appears — worth knowing when you set max_tokens. Tool and function calling are supported, so it can drive an agent loop. Cached input is billed at $0.00 against $0.14 fresh, which is the difference that matters most for agent work — the same context is resent on every turn.
Specs
- Context window
- 1M
- Max output
- 384K
- Input / 1M
- $0.14
- Output / 1M
- $0.28
- Extended reasoning
- Tool / function calling
DeepSeek V4 Pro Max FAQ
How much does DeepSeek V4 Pro Max cost?
DeepSeek V4 Pro Max is $0.14 per 1M input tokens and $0.28 per 1M output tokens. Cached input is $0.00, which matters a lot for agent work that resends the same context each turn.
Which providers serve DeepSeek V4 Pro Max?
DeepSeek serves it. kRouter routes to it as deepseek/deepseek-v4-pro-max.
What is DeepSeek V4 Pro Max's context window?
1M tokens, with up to 384K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.
Route to DeepSeek V4 Pro Max from any tool
kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.
Install kRouter