DeepSeek V4 Flash
DeepSeek V4 Flash is served by 3 providers that kRouter can route to, with a 1M-token context window and pricing from $0.30 per 1M input tokens. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.
Where to get DeepSeek V4 Flash
| Provider | Route as |
|---|---|
| OpenCode Go | opencode-go/deepseek-v4-flash |
| CodeBuddy CN | cbcn/deepseek-v4-flash |
| DeepSeek | deepseek/deepseek-v4-flash |
What DeepSeek V4 Flash 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 $0.01 against $0.30 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
- $0.30
- Output / 1M
- $1.20
- Extended reasoning
- Tool / function calling
Cheaper alternatives to DeepSeek V4 Flash
Comparable capabilities at a lower rate. With a kRouter combo you can send routine turns to one of these and reserve DeepSeek V4 Flash for the work that actually needs it.
- Gemini 2.5 Flash Lite$0.15 in · $1.25 out per 1M
- DeepSeek R1$0.14 in · $0.28 out per 1M
- DeepSeek V4 Flash$0.14 in · $0.28 out per 1M
- DeepSeek V4 Pro$0.14 in · $0.28 out per 1M
DeepSeek V4 Flash FAQ
How much does DeepSeek V4 Flash cost?
DeepSeek V4 Flash is $0.30 per 1M input tokens and $1.20 per 1M output tokens. Cached input is $0.01, which matters a lot for agent work that resends the same context each turn.
Which providers serve DeepSeek V4 Flash?
3 providers: OpenCode Go, CodeBuddy CN, DeepSeek. Through kRouter you can switch between them by changing the route prefix, without changing your tool.
What is DeepSeek V4 Flash'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.
Is there a cheaper alternative to DeepSeek V4 Flash?
Yes — Gemini 2.5 Flash Lite ($0.15/1M in), DeepSeek R1 ($0.14/1M in), DeepSeek V4 Flash ($0.14/1M in), DeepSeek V4 Pro ($0.14/1M in) are cheaper with comparable capabilities. A kRouter combo can send routine turns to one of those and keep DeepSeek V4 Flash for the work that needs it.
Route to DeepSeek V4 Flash 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