# DeepSeek: DeepSeek V4 Flash 0423

Generate and analyse text with DeepSeek: DeepSeek V4 Flash 0423 from OpenRouter through one Spiral API key. It runs in the background and returns text and structured JSON. Pay as you go, with no subscription.

- Provider: OpenRouter
- Category: LLM
- Runs: In the background
- Returns: text, json
- Released: 2026-04-24
- Tool id: `openrouter` / `deepseek/deepseek-v4-flash`
- Page: https://spiral.ai/tools/openrouter/deepseek/deepseek-v4-flash

## Pricing

Up to $0.000964 per run at the default inputs. $0.117 per 1M input tokens, $0.234 per 1M output tokens.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 225 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `messages` (required) | JSON |  | — | The conversation so far, oldest first. |
| `seed` | number (whole) |  | — |  |
| `stop` | JSON |  | — |  |
| `min_p` | number | 0 to 1 | — |  |
| `tools` | JSON |  | — |  |
| `top_k` | number (whole) | 0 to … | — |  |
| `top_p` | number | 0 to 1 | — |  |
| `logprobs` | true or false |  | — |  |
| `reasoning` | JSON |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| `max_tokens` | number (whole) | 1 to 943717 | — | The most output tokens to generate. |
| `temperature` | number | 0 to 2 | — |  |
| `tool_choice` | JSON |  | — |  |
| `top_logprobs` | number (whole) | 0 to 20 | — |  |
| `response_format` | JSON |  | — |  |
| `presence_penalty` | number | -2 to 2 | — |  |
| `reasoning_effort` | one of | none, high, xhigh | high | How much the model reasons. |
| `frequency_penalty` | number | -2 to 2 | — |  |
| `repetition_penalty` | number | 0 to 2 | — |  |

## How to use DeepSeek: DeepSeek V4 Flash 0423

From your AI agent, the command line or your own code. One Spiral account runs it every way.

### Use Spiral's MCP server

1. **Add Spiral's MCP server**: Any MCP client takes https://api.spiral.ai/mcp with your API key as a Bearer token. In Claude Code:

```bash
claude mcp add spiral --transport http https://api.spiral.ai/mcp \
  --header "Authorization: Bearer $SPIRAL_API_KEY"
```

2. **Ask for DeepSeek: DeepSeek V4 Flash 0423**: Your agent finds it on Spiral, shows the price and runs it.

```
Use DeepSeek: DeepSeek V4 Flash 0423 from OpenRouter on Spiral.
```

### Use the Spiral skill

1. **Send your agent this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

3. **Ask for DeepSeek: DeepSeek V4 Flash 0423**: Your agent finds it on Spiral, shows the price and runs it.

```
Use DeepSeek: DeepSeek V4 Flash 0423 from OpenRouter on Spiral.
```

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

2. **Run DeepSeek: DeepSeek V4 Flash 0423**: Waits for the result and saves the run and its files under .spiral/runs.

```bash
spiral runs create \
  --provider openrouter \
  --model deepseek/deepseek-v4-flash \
  --input '{
    "messages": [
      {
        "role": "system"
      }
    ]
  }' \
  --wait --save
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run DeepSeek: DeepSeek V4 Flash 0423**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "deepseek/deepseek-v4-flash",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=openrouter&model=deepseek%2Fdeepseek-v4-flash

## Use DeepSeek: DeepSeek V4 Flash 0423 in your AI agent

- [Amp](https://spiral.ai/integrations/amp/deepseek-v4-flash-0423)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/deepseek-v4-flash-0423)
- [Claude](https://spiral.ai/integrations/claude-desktop/deepseek-v4-flash-0423)
- [Claude Code](https://spiral.ai/integrations/claude-code/deepseek-v4-flash-0423)
- [Cline](https://spiral.ai/integrations/cline/deepseek-v4-flash-0423)
- [Codex](https://spiral.ai/integrations/codex/deepseek-v4-flash-0423)
- [Cursor](https://spiral.ai/integrations/cursor/deepseek-v4-flash-0423)
- [Devin](https://spiral.ai/integrations/devin/deepseek-v4-flash-0423)
- [dots](https://spiral.ai/integrations/dots/deepseek-v4-flash-0423)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/deepseek-v4-flash-0423)
- [Gemini](https://spiral.ai/integrations/gemini/deepseek-v4-flash-0423)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/deepseek-v4-flash-0423)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/deepseek-v4-flash-0423)
- [goose](https://spiral.ai/integrations/goose/deepseek-v4-flash-0423)
- [Grok](https://spiral.ai/integrations/grok/deepseek-v4-flash-0423)
- [Grok Build](https://spiral.ai/integrations/grok-build/deepseek-v4-flash-0423)
- [Hermes](https://spiral.ai/integrations/hermes/deepseek-v4-flash-0423)
- [Instinct](https://spiral.ai/integrations/instinct/deepseek-v4-flash-0423)
- [Manus](https://spiral.ai/integrations/manus/deepseek-v4-flash-0423)
- [Muse](https://spiral.ai/integrations/muse/deepseek-v4-flash-0423)
- [Muse Code](https://spiral.ai/integrations/muse-code/deepseek-v4-flash-0423)
- [n8n](https://spiral.ai/integrations/n8n/deepseek-v4-flash-0423)
- [Notion](https://spiral.ai/integrations/notion/deepseek-v4-flash-0423)
- [OpenClaw](https://spiral.ai/integrations/openclaw/deepseek-v4-flash-0423)
- [opencode](https://spiral.ai/integrations/opencode/deepseek-v4-flash-0423)
- [Perplexity](https://spiral.ai/integrations/perplexity/deepseek-v4-flash-0423)
- [Raycast](https://spiral.ai/integrations/raycast/deepseek-v4-flash-0423)
- [VS Code](https://spiral.ai/integrations/vscode/deepseek-v4-flash-0423)
- [Windsurf](https://spiral.ai/integrations/windsurf/deepseek-v4-flash-0423)
- [Zapier](https://spiral.ai/integrations/zapier/deepseek-v4-flash-0423)

## Provider

- [OpenRouter](https://spiral.ai/providers/openrouter)

## Related tools

- [DeepSeek: DeepSeek V3.2 Exp](https://spiral.ai/tools/openrouter/deepseek/deepseek-v3.2-exp)
- [DeepSeek: DeepSeek V4 Flash 0731](https://spiral.ai/tools/openrouter/deepseek/deepseek-v4-flash-0731)
- [DeepSeek: DeepSeek V3.2](https://spiral.ai/tools/openrouter/deepseek/deepseek-v3.2)
- [DeepSeek: DeepSeek V4 Flash 0731 (batch)](https://spiral.ai/tools/openrouter/deepseek/deepseek-v4-flash-0731%3Abatch)
- [DeepSeek: DeepSeek V3.1 Terminus](https://spiral.ai/tools/openrouter/deepseek/deepseek-v3.1-terminus)
- [DeepSeek: DeepSeek V4 Flash Vision Exp](https://spiral.ai/tools/openrouter/deepseek/deepseek-v4-flash-vision-exp)

## Common questions

### DeepSeek: DeepSeek V4 Flash 0423

**How much does DeepSeek: DeepSeek V4 Flash 0423 cost?**

Up to $0.000964 per run at the default inputs. $0.117 per 1M input tokens, $0.234 per 1M output tokens. It is paid from your prepaid Spiral balance as you use it, with no subscription.

**How long does DeepSeek: DeepSeek V4 Flash 0423 take to run?**

It runs in the background: the request returns a run id at once, and you poll `GET /v1/runs/{id}` or name a webhook to hear when it finishes. A run can take at most 225 minutes, end to end.

**What input does DeepSeek: DeepSeek V4 Flash 0423 take?**

It needs `messages`. It also takes 17 optional fields: `seed`, `stop`, `min_p` and 14 more. Each field's type, allowed values and default are listed on this page.

**What does DeepSeek: DeepSeek V4 Flash 0423 return?**

A finished run returns text and json output. Each output up to 5 GB is stored as a copy; a larger output comes back as the provider's own link where the provider gives one, and otherwise that output is not delivered and you are not charged for it; a run with nothing delivered fails as too large, without a charge.

**What are the limits of DeepSeek: DeepSeek V4 Flash 0423?**

Longest queue wait: 1 hour; largest inline input: 1 MB; largest input file: 2 GB.

**How do I use DeepSeek: DeepSeek V4 Flash 0423 through an API?**

Send `POST /v1/runs` with `"provider": "openrouter"`, `"model": "deepseek/deepseek-v4-flash"` and its input, using one Spiral API key.

**How do I see what a run of DeepSeek: DeepSeek V4 Flash 0423 will cost before I start it?**

Send the same request to `POST /v1/estimate`: it prices that exact input without running it.

**What happens if a run of DeepSeek: DeepSeek V4 Flash 0423 fails?**

Only for work the provider billed. A run that fails before the provider does billable work is not charged, and its hold goes back to your balance; a failure the provider bills for is charged for the work the provider billed, at the tool's price. Each failed run's error says why it failed and what it was charged.

**Do I need an account with OpenRouter to use DeepSeek: DeepSeek V4 Flash 0423?**

No. Spiral runs it on its own OpenRouter account and charges your Spiral balance.

**Can my AI agent use DeepSeek: DeepSeek V4 Flash 0423?**

Yes. Any agent connected to Spiral's MCP server, CLI or agent skill runs it with the same API key, and there are guides for using it from Amp, ChatGPT, Claude, Claude Code, Cline, Codex, Cursor, Devin, dots, Factory Droid, Gemini, Gemini CLI, Google Antigravity, goose, Grok, Grok Build, Hermes, Instinct, Manus, Muse, Muse Code, n8n, Notion, OpenClaw, opencode, Perplexity, Raycast, VS Code, Windsurf and Zapier.

**Can I cap what an agent spends on DeepSeek: DeepSeek V4 Flash 0423?**

Yes. Give each agent its own API key with a spend cap: a run whose estimate would pass the cap is refused before it starts.

