DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a text and image-input model by DeepSeek, available through the AgentSky API as deepseek/deepseek-flash at $0.21 per million input tokens and $0.84 per million output tokens, with a 1M context window.
DeepSeek V4.1 Flash, available through the canonical deepseek-flash model id.
Run DeepSeek V4.1 Flash with an agent
Each guide pairs this model with a compatible agent and opens the composer with both selected.
- Hermes + DeepSeek V4.1 Flash
- Claude Code + DeepSeek V4.1 Flash
- Codex + DeepSeek V4.1 Flash
- OpenClaw + DeepSeek V4.1 Flash
- pi + DeepSeek V4.1 Flash
- DeepSeek Harness + DeepSeek V4.1 Flash
- Kimi Code + DeepSeek V4.1 Flash
- OpenCode + DeepSeek V4.1 Flash
- Cline + DeepSeek V4.1 Flash
- DeepAgents + DeepSeek V4.1 Flash
- goose + DeepSeek V4.1 Flash
- Grok Build + DeepSeek V4.1 Flash
- Kilo + DeepSeek V4.1 Flash
- MiniMax Code + DeepSeek V4.1 Flash
- Mistral Vibe + DeepSeek V4.1 Flash
- Qwen Code + DeepSeek V4.1 Flash
- OpenHands + DeepSeek V4.1 Flash
Pricing
USD per million tokens, using your plan when signed in.
| Meter | Per 1M tokens |
|---|---|
| Input | |
| Output | |
| Cache read | |
| Cache write |
Use it
Point your client at the gateway and pass this model id. Nothing else changes.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gateway.agentsky.dev/v1",
apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});
const completion = await client.chat.completions.create({
model: "deepseek/deepseek-flash",
messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response