[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [DeepSeek V4 Flash 0731](https://spiral.ai/integrations/codex/deepseek-v4-flash-0731)

# How to Use DeepSeek V4 Flash 0731 in Codex

DeepSeek V4 Flash 0731 suits coding and tasks that require several tool-driven steps. Compared with DeepSeek V4 Flash 0423, it improves agent capabilities through additional post-training while keeping the same architecture and size.

|  |  |
| --- | --- |
| Model | DeepSeek V4 Flash 0731 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001601 per run at the default inputs. $0.05642 per 1M input tokens, $0.39 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with DeepSeek V4 Flash 0731 in Codex

- Use DeepSeek V4 Flash 0731 with high reasoning effort to investigate the failing tests in this project. Reproduce one failure, trace its cause, make the smallest justified fix, and report the checks you ran.
- Use DeepSeek V4 Flash 0731 at the highest available reasoning effort to investigate this project's intermittent test failure. Compare plausible causes, add a targeted reproducer, and verify any fix.
- Ask DeepSeek V4 Flash 0731 through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
- Get a second opinion from DeepSeek V4 Flash 0731 on this function, then tell me what the call cost.
- Summarize these release notes with DeepSeek V4 Flash 0731 in five bullet points.

## How to set up DeepSeek V4 Flash 0731 in Codex

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex 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.

### 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
```

### Call the Spiral API

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

2. **Run DeepSeek V4 Flash 0731**: 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-0731",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Codex finds DeepSeek V4 Flash 0731 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## DeepSeek V4 Flash 0731 tools and prices

- [DeepSeek: DeepSeek V4 Flash 0731](https://spiral.ai/tools/openrouter/deepseek/deepseek-v4-flash-0731) (OpenRouter): Up to $0.368053 per run at the default inputs. $0.05759 per 1M input tokens, $0.39 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with DeepSeek V4 Flash 0731 in Codex?

DeepSeek V4 Flash can help turn a failing test or unfamiliar codebase into a focused investigation and proposed patch. Give the agent a concrete acceptance condition and ask it to verify the result against the project.

### Fix a reproducible bug

Give DeepSeek V4 Flash the failure, relevant code, and expected behavior. Ask for a focused patch and a regression check that reproduces the original problem.

### Explain an unfamiliar codebase

Trace a request through supplied source code, identify the main dependencies, and produce a reading guide with references to the relevant functions.

### Answer questions across documentation

Provide the relevant documentation as text and ask DeepSeek V4 Flash to answer specific questions with supporting passages. Require it to flag gaps instead of filling them from memory.

### Check a mathematical argument

Submit the problem, assumptions, and proposed solution. Ask for the first unsupported step, a corrected result, and an independent numerical check where possible.

### Investigate recurring errors

Use supplied error logs and incident notes to build a timeline, separate symptoms from possible causes, and propose checks that distinguish competing explanations.

### Review a proposed software change

Compare a written requirement with the proposed implementation. Ask DeepSeek V4 Flash to identify missing behavior, edge cases, and tests that would settle uncertain findings.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Codex guides](https://spiral.ai/integrations/codex)

## DeepSeek V4 Flash 0731 in other agents

- [Amp](https://spiral.ai/integrations/amp/deepseek-v4-flash-0731)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/deepseek-v4-flash-0731)
- [Claude](https://spiral.ai/integrations/claude-desktop/deepseek-v4-flash-0731)
- [Claude Code](https://spiral.ai/integrations/claude-code/deepseek-v4-flash-0731)
- [Cline](https://spiral.ai/integrations/cline/deepseek-v4-flash-0731)
- [Cursor](https://spiral.ai/integrations/cursor/deepseek-v4-flash-0731)
- [Devin](https://spiral.ai/integrations/devin/deepseek-v4-flash-0731)
- [dots](https://spiral.ai/integrations/dots/deepseek-v4-flash-0731)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/deepseek-v4-flash-0731)
- [Gemini](https://spiral.ai/integrations/gemini/deepseek-v4-flash-0731)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/deepseek-v4-flash-0731)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/deepseek-v4-flash-0731)
- [goose](https://spiral.ai/integrations/goose/deepseek-v4-flash-0731)
- [Grok](https://spiral.ai/integrations/grok/deepseek-v4-flash-0731)
- [Grok Build](https://spiral.ai/integrations/grok-build/deepseek-v4-flash-0731)
- [Hermes](https://spiral.ai/integrations/hermes/deepseek-v4-flash-0731)
- [Instinct](https://spiral.ai/integrations/instinct/deepseek-v4-flash-0731)
- [Manus](https://spiral.ai/integrations/manus/deepseek-v4-flash-0731)
- [Muse](https://spiral.ai/integrations/muse/deepseek-v4-flash-0731)
- [Muse Code](https://spiral.ai/integrations/muse-code/deepseek-v4-flash-0731)
- [n8n](https://spiral.ai/integrations/n8n/deepseek-v4-flash-0731)
- [Notion](https://spiral.ai/integrations/notion/deepseek-v4-flash-0731)
- [OpenClaw](https://spiral.ai/integrations/openclaw/deepseek-v4-flash-0731)
- [opencode](https://spiral.ai/integrations/opencode/deepseek-v4-flash-0731)
- [Perplexity](https://spiral.ai/integrations/perplexity/deepseek-v4-flash-0731)
- [Raycast](https://spiral.ai/integrations/raycast/deepseek-v4-flash-0731)
- [VS Code](https://spiral.ai/integrations/vscode/deepseek-v4-flash-0731)
- [Windsurf](https://spiral.ai/integrations/windsurf/deepseek-v4-flash-0731)
- [Zapier](https://spiral.ai/integrations/zapier/deepseek-v4-flash-0731)

## More Codex guides

- [DeepSeek V4 Flash 0423](https://spiral.ai/integrations/codex/deepseek-v4-flash-0423)
- [DeepSeek V4 Flash 0731 (batch)](https://spiral.ai/integrations/codex/deepseek-v4-flash-0731-batch)
- [DeepSeek V3.2 Exp](https://spiral.ai/integrations/codex/deepseek-v3-2-exp)
- [DeepSeek V4 Flash Latest](https://spiral.ai/integrations/codex/deepseek-v4-flash-latest)
- [DeepSeek V3.2](https://spiral.ai/integrations/codex/deepseek-v3-2)
- [DeepSeek V4 Flash Vision Exp](https://spiral.ai/integrations/codex/deepseek-v4-flash-vision-exp)

## Questions about DeepSeek V4 Flash 0731 in Codex

**Can Codex use DeepSeek V4 Flash 0731?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run DeepSeek V4 Flash 0731 like any built-in tool.

**How much does DeepSeek V4 Flash 0731 cost in Codex?**

Up to $0.001601 per run at the default inputs. $0.05642 per 1M input tokens, $0.39 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need an OpenRouter account to use DeepSeek V4 Flash 0731 in Codex?**

No. Spiral runs DeepSeek V4 Flash 0731 on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up DeepSeek V4 Flash 0731 in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while DeepSeek V4 Flash 0731 runs?**

DeepSeek V4 Flash 0731 runs in the background. Codex starts the run, checks on it and gives you the text, json when it's ready.

**What is DeepSeek V4 Flash good at?**

Coding, reasoning, long text analysis, and everyday agent tasks are its main strengths. Useful jobs include explaining a codebase, answering questions across supplied documentation, and investigating a problem through several steps.

**How much text can DeepSeek V4 Flash work with?**

DeepSeek V4 Flash supports roughly one million tokens of context. Treat that as working space for the task, rather than a promise that one response can be that long.

**Can DeepSeek V4 Flash analyze images?**

The DeepSeek V4 Flash models covered here are text models. Supply written descriptions, extracted text, or tabular values for tasks involving visual material.

**Which reasoning level should I choose?**

High reasoning effort is a practical starting point for everyday agent work. Reserve the highest available effort for difficult debugging or reasoning problems, and ask for a concise final answer.

**Where does DeepSeek V4 Flash need closer review?**

DeepSeek's preview evaluation identifies factual knowledge and the most complex agent workflows as weaker areas than Pro. For those jobs, supply reference material, request evidence for conclusions, and review the result before using it.

