Use DeepSeek V4.1 Flash in Zoo Code
Zoo Code runs DeepSeek V4.1 Flash on OceanToken with three settings: a base URL, your key and the model id. Tested on October 18, 2026 with Zoo Code 3.90.0.
Up to 40% off
$0.21 / $0.84 $0.30 / $1.20 per 1M input / output tokens
Cached input: $0.006
Settings
| Setting | Value |
|---|---|
| API Provider | OpenAI Compatible |
| Base URL | https://api.oceantoken.ai/v1 |
| API Key | your OceanToken API key |
| Model | deepseek/deepseek-v4.1-flash |
| Context Window Size | 1,048,576 |
| Max Output Tokens | 32,000 |
| Image Support | On |
| Prompt Caching | Off |
| Strict tool schemas | On |
What it costs
An agent resends a long prompt on every turn, so the cached input price matters as much as the input price. DeepSeek V4.1 Flash caches the repeated part of the prompt on its own: from the second turn of a task it is billed at the cached input price.
About these prices
Frequently asked questions
Does DeepSeek V4.1 Flash work with Zoo Code’s tools?
Yes. It was tested on October 18, 2026 with Zoo Code 3.90.0: tool calls, streaming, image input, reasoning effort and prompt caching.
How much does DeepSeek V4.1 Flash cost in Zoo Code?
Every request Zoo Code makes is billed at the model’s price: $0.21 / $0.84 per 1M input / output tokens. The repeated part of a long prompt is billed at $0.006 per 1M cached input tokens. Each request’s charge is in the console under Logs.
Where do I put my OceanToken key?
Create a key in the OceanToken console and give it a credit limit: an agent sends many requests, and the limit caps what this key can spend. Keep it in an environment variable, never in a file in your repository.
Get API Key DeepSeek V4.1 Flash
Other models tested with Zoo Code
Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Haiku 4.5 · GPT-5.5 · DeepSeek V4 Pro · Qwen3.8 Flash · GLM 5.3
DeepSeek V4.1 Flash in other tools
Keep exploring
DeepSeek V4.1 Flash vs Gemini 3.5 Flash · Qwen3.8 Flash vs DeepSeek V4.1 Flash · MiniMax M3 vs DeepSeek V4.1 Flash