Skip to main content
ByteSpike accepts a small set of legacy compat names that DeepSeek itself has retired. They’re kept here so existing customer code keeps working through DeepSeek’s official sunset window. New code should not use them. Write your code against these:
Canonical nameWhat you get
deepseek-v4-flashDeepSeek V4 Flash — fast non-thinking mode, default for general chat / completion
deepseek-v4-proDeepSeek V4 Pro — adds the thinking / reasoning mode (set reasoning_effort to control depth)
Both are first-class names: they appear in usage exports, audit logs, billing line items, and the models index without further translation.

Legacy compat (until 2026-07-24)

DeepSeek announced these names will be removed on 2026-07-24. ByteSpike’s gateway will continue to accept them until then, resolving each request to the canonical name below.
Legacy nameResolves toNote
deepseek-chatdeepseek-v4-flashThe most common pre-V4 DeepSeek string
deepseek-reasonerdeepseek-v4-pro (thinking mode)The pre-V4 “reasoner” handle
After 2026-07-24 these names will return a 400 from ByteSpike (matching DeepSeek’s own behavior). Update your code before then.

Names not to use

Earlier DeepSeek lineages — deepseek-coder, deepseek-v2 family handles — have been retired and are no longer accepted by ByteSpike. Requests using them return a 404 with a hint pointing at the V4 line. (Note: deepseek-r1 and deepseek-v3-2 are still served as canonical models — they are not legacy; see the models index.) For other model families, ByteSpike accepts the canonical model ID directly. No alias layer applies; there are no synonyms to memorize. Look up the exact string for each model on its models page.

How to migrate

A one-line code change in most clients:
- "model": "deepseek-chat"
+ "model": "deepseek-v4-flash"
- "model": "deepseek-reasoner"
+ "model": "deepseek-v4-pro"
If you use deepseek-reasoner and depend on the thinking output specifically, also confirm your client sets reasoning_effort (default is medium on V4 Pro).

Next

  • Models index — every canonical model ByteSpike serves, with pricing and protocol coverage
  • Endpoint types — the protocols each model can be called through