This release includes 2 breaking changes for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+3 more
Summary
AI summaryUpdates Highlights, Pricing, and Models across a mixed release.
Full changelog
DeepSeek V4
This release migrates the server and the hosted endpoint to DeepSeek V4.
Models
deepseek-v4-flash(new default): fast and economical, 1M context, up to 384K outputdeepseek-v4-pro: top capability, 1M context, up to 384K outputdeepseek-chatanddeepseek-reasonerkeep working as aliases that resolve todeepseek-v4-flash(chat = non-thinking, reasoner = thinking). The DeepSeek API retires those two names on 2026-07-24, so the server translates them for you. Upgrading is drop-in.
Highlights
- Default model is now
deepseek-v4-flash. Direct v4 calls are non-thinking by default for fast responses; enable reasoning withthinking: {type: "enabled"}or thedeepseek-reasoneralias. - New
reasoning_effortparameter (high/max) for thinking mode. max_tokensupper bound raised to 384000.- Model fallback now pairs
deepseek-v4-flashwithdeepseek-v4-pro. - The hosted worker endpoint (deepseek-mcp.tahirl.com) is on V4 as well.
Pricing (per 1M tokens)
- v4-flash: $0.0028 cache hit, $0.14 cache miss, $0.28 output
- v4-pro: $0.003625 cache hit, $0.435 cache miss, $0.87 output
Fixed
- Declared
cost_usdandrouted_fromin thedeepseek_chatoutput schema, which strict MCP clients rejected under SDK 1.29 structured-content validation.
Full notes in CHANGELOG.md.
Breaking Changes
- Model names `deepseek-chat` and `deepseek-reasoner` are retired on 2026-07-24; they now alias to `deepseek-v4-flash` (chat) or enable reasoning via `thinking: {type: "enabled"}`.
- Default model changed from previous version to `deepseek-v4-flash`.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About arikusi/deepseek-mcp-server
MCP server for DeepSeek AI with chat, reasoning, multi-turn sessions, function calling, thinking mode, and cost tracking.
Related context
Related tools
Earlier breaking changes
- v1.8.0 Requires Node.js 20 or newer; Node 18 support dropped.
Beta — feedback welcome: [email protected]