--- title: "deepseek-v4-flash Retired: Old Name Rerouted, Move to deepseek-flash" description: "DeepSeek retired V4-Flash on Sept 10 and now reroutes the old model name to the new one. Here is the status of deepseek-v4-pro and four steps to migrate." url: https://cdnping.org/en/blog/deepseek-model-name-migration-v4-flash-retired language: en published: 2026-10-19 category: "Service updates" tags: ["DeepSeek","model migration","API","deepseek-flash","changelog"] source: cdnping.org license: Free to quote and summarize with a link to the url above. --- # deepseek-v4-flash Retired: Old Name Rerouted, Move to deepseek-flash deepseek-v4-flash was retired on September 10, 2026, when V4.1-Flash launched. The old name still works for now, but only as a compatibility layer: requests are routed to the new model and billed at Flash pricing. In your code, switch to `deepseek-flash`. Everything below is current as of October 2026 and follows the official documentation. Source links are at the end. ## What exactly happened on September 10? According to [DeepSeek's September 10 announcement](https://api-docs.deepseek.com/news/news260910): - DeepSeek-V4.1-Flash was released. To call it, set the model name to `deepseek-flash`. - V4-Flash and V4-Flash-Vision-Exp were retired. - The two old names, `deepseek-v4-flash` and `deepseek-v4-flash-vision-exp`, are temporarily routed to V4.1-Flash. - The new pricing took effect at 04:00 UTC on September 10. The [pricing page](https://api-docs.deepseek.com/quick_start/pricing) currently says these two old names are "still usable," that the underlying models are retired, and that requests are handled by the V4.1-Flash family and billed at Flash pricing. "Temporarily" comes with no end date, so don't treat the old names as long-term. ## Is deepseek-v4-pro still available? The official statements differ over time here, so read carefully. The September 10 announcement said that from 04:00 UTC on September 14, `deepseek-v4-pro` requests would be routed to V4.1-Flash until V4.1-Pro goes live. The [changelog](https://api-docs.deepseek.com/updates) later states that the V4 Pro API continues to be served after September 14, with billing unchanged. As of October, the pricing page maps `deepseek-v4-pro` to DeepSeek-V4-Pro-0813. There is no officially announced release date for V4.1-Pro. Bottom line: `deepseek-v4-pro` works today, but if you depend on it, check the original source regularly instead of relying on secondhand summaries. That includes this article. ## What is the difference between deepseek-flash and deepseek-v4-flash? | Item | deepseek-v4-flash (old) | deepseek-flash (new) | | --- | --- | --- | | Status | Model retired, name temporarily forwarded | Currently recommended name | | Model actually served | V4.1-Flash family | V4.1-Flash family, follows official updates | | Billing | Flash pricing | Flash pricing | Note that `deepseek-flash` is a name that tracks official updates. The pricing page currently maps it to DeepSeek-V4.1-Flash-1017. The weights were updated once already on October 17, with no change to usage or pricing; see [the V4.1-Flash-1017 update explained](/en/blog/deepseek-v4-1-flash-1017-update). In other words, after you switch to the new name, outputs may change between versions, so run regression tests regularly. ## How do I migrate my code? ### Step 1: Find every hardcoded model name ```bash grep -rnE "deepseek-v4-flash|deepseek-v4-flash-vision-exp|deepseek-v4-pro" \ --include="*.py" --include="*.js" --include="*.ts" --include="*.json" \ --include="*.yaml" --include="*.yml" --include="*.toml" --include="*.env*" . ``` Don't forget CI variables, config tables in databases, and model names entered in third-party tools (editor plugins, Cherry Studio, and the like). grep won't find those. ### Step 2: Replace the names and centralize the config Change `deepseek-v4-flash` to `deepseek-flash`. Change `deepseek-v4-flash-vision-exp` to `deepseek-flash` as well (the pricing page notes that this model supports vision). While you're at it, put the model name in an environment variable so the next rename is a one-line change. If you have a clear need for `deepseek-v4-pro`, keep it; don't switch to Flash by default. ### Step 3: Check which models your account can see ```bash curl -s https://api.deepseek.com/models \ -H "Authorization: Bearer $DEEPSEEK_API_KEY" ``` `deepseek-flash` should appear in the returned list. For the exact response format, refer to the official documentation. ### Step 4: Run regression tests - Fix a representative set of prompts and compare the output before and after the change, checking that the format (JSON structure, tool calls) stays stable. - Check thinking mode: the pricing page says both models support thinking and non-thinking modes, with thinking on by default. If you relied on the default behavior before, set it explicitly. - Compare your bill. The old names are billed at Flash pricing, so costs generally shouldn't go up, but see the [peak and off-peak pricing explainer](/en/blog/deepseek-api-peak-offpeak-pricing) for how time-of-day pricing is calculated. ## How do I avoid being caught off guard by changes like this? Model renames, retirements, and forwarding have happened at every major provider, for example [Gemini's automatic routing after deprecation](/en/blog/gemini-flash-deprecation-auto-routing) and [Codex retiring its old default model](/en/blog/codex-model-retirement-cli-0-163). A few things you can do: 1. Subscribe to cdnping's [site changes tracker at /en/changes](/en/changes). It monitors official changelogs and pricing pages, including DeepSeek's, records additions and deletions line by line, and offers an RSS feed. 2. Use [model monitoring at /en/models](/en/models) and the [DeepSeek API status page](/en/status/deepseek) to check availability. 3. Watch for billing changes on new features, such as [pricing for the Search & Fetch API](/en/blog/deepseek-search-fetch-api-pricing). ## Sources - [DeepSeek September 10 announcement](https://api-docs.deepseek.com/news/news260910) - [DeepSeek API changelog](https://api-docs.deepseek.com/updates) - [DeepSeek models and pricing](https://api-docs.deepseek.com/quick_start/pricing) - [DeepSeek API docs home](https://api-docs.deepseek.com/)