Home / Guides / DeepSeek V4 Flash

Published July 31, 2026 · updated September 26, 2026 · applies to pgup-ai/jbot-review-action v0

The official DeepSeek V4 Flash 0731 can review pull requests through multiple $0 provider routes—or directly through DeepSeek at roughly 11× lower uncached input and 27× lower output list prices than Gemini 3.6 Flash. The exact free route matters: provider catalogs do not all identify the same snapshot, and their capacity and data terms differ.

Free OpenCode setup in three steps

1. Create an OpenCode API key. Sign in to OpenCode Zen, then save the key as the repository secret OPENCODE_API_KEY (Settings → Secrets and variables → Actions).
2. Commit the workflow. Add the file below as .github/workflows/jbot-review.yml. OpenCode's deepseek-v4-flash-free alias is updated to the official model; the explicit pin makes that choice visible.
3. Open a pull request. J-Bot reads the base…head diff and posts diff-anchored findings with a verdict. Blocking findings are checked by a second session before they post.

name: J-Bot Code Review
on:
  pull_request: { types: [opened, reopened, ready_for_review, synchronize] }

concurrency:
  group: jbot-review-${{ github.event.pull_request.number }}
  cancel-in-progress: true

permissions:
  contents: read
  pull-requests: write
  issues: write
  checks: read

jobs:
  review:
    if: github.event.pull_request.draft == false
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7
        with: { fetch-depth: 0 }
      - uses: pgup-ai/jbot-review-action@v0
        with:
          provider: opencode
          model: deepseek-v4-flash-free
          opencode-api-key: ${{ secrets.OPENCODE_API_KEY }}
          github-token: ${{ secrets.GITHUB_TOKEN }}

Six advertised $0 routes

OpenCode, OpenRouter, and DeepSeek are native J-Bot providers; Cline uses its CLI with CLINE_AUTH_JSON. For InferX, Kenari, or UnoRouter, save the provider key as the GitHub Actions secret JBOT_OPENAI_COMPATIBLE_API_KEY, set the base URL as the repository variable JBOT_OPENAI_COMPATIBLE_BASE_URL, and use the explicit model above. Sources checked August 1: OpenCode Zen, Cline's live free-model feed, Cline free-model terms, OpenRouter's free listing, InferX's provider announcement, Kenari's live catalog, and UnoRouter's live ranking.

OpenRouter availability: its public deepseek-v4-flash:free page says “Free,” but the live catalog omitted the slug and the endpoint API reported no serving backends when checked August 1. Treat the route as opportunistic, not reliable capacity.

The official 0731 agent benchmarks

DeepSeek published nine agent and coding-agent results with the official release. These are DeepSeek's reported scores, not J-Bot evaluations:

DeepSeek identifies DSBench-FullStack and DSBench-Hard as internal test sets. For the public code-agent benchmarks, it used the not-yet-released DeepSeek Harness in minimal mode, max effort, temperature=1.0, and top_p=0.95. Read the release notes →

Same agent-performance band, very different price

The overlapping vendor tables put official V4 Flash in Gemini 3.6 Flash's agentic coding range. DeepSeek's reported scores are slightly higher on the two named overlaps—but this is directional, not a controlled head-to-head.

Why the qualification matters: DeepSeek used its own forthcoming harness at max effort; Google's Terminal-Bench result uses the Terminus-2 harness, and Google labels its software-engineering result DeepSWE v1.1. Prices are directly comparable public API list rates checked July 31, 2026. DeepSeek says a future peak window will charge 2× its regular rates, with the effective date still to be announced. Sources: DeepSeek pricing and Google's Gemini 3.6 Flash model card.

Normal reviews versus the published benchmark setup

J-Bot's native-provider default is medium reasoning effort. DeepSeek ran the released code-agent benchmarks at max effort. To ask J-Bot for the closest available effort setting, add this input:

model-options: '{"reasoningEffort":"max"}'

This still does not reproduce DeepSeek's benchmark: its harness has not been released, and J-Bot uses its own review prompts, read-only tools, finding schema, and verification pass. Use max when depth matters more than latency; keep the default medium for everyday PR throughput.

Where the diff goes

• Your runner stays in control. The review runs inside GitHub Actions with read-only repository access; write permissions are used only to post review output.
• The provider you select receives the diff. That is DeepSeek, OpenCode and its upstream, Cline and its upstream, OpenRouter and its upstream, or the OpenAI-compatible base URL you configure.
• Free routes may be feedback routes. OpenCode and Cline state that data from their free models may be used to improve models. Do not send sensitive code unless the selected provider's terms fit your policy.
• Custom-gateway terms differ. Free pricing does not imply zero retention, stable capacity, or a permanent offer. Review each provider's current terms before sending private code.
• Fork PRs cannot read the key. GitHub does not pass repository secrets to pull_request workflows from forks.

FAQ

Related