feat(models): add deepseek-v4-pro and deepseek-v4-flash by teknium1 · Pull Request #14934 · NousResearch/hermes-agent

teknium1 · 2026-04-24T05:34:59Z

Summary

Adds DeepSeek V4 Pro and V4 Flash to the OpenRouter curated list, Nous Portal fallback list, and the native DeepSeek provider's static catalog.

Changes

OPENROUTER_MODELS: deepseek/deepseek-v4-pro, deepseek/deepseek-v4-flash (load-bearing — picker filters against this)
_PROVIDER_MODELS["nous"]: same two slugs (fallback-only; portal-side add still needed for authed users)
_PROVIDER_MODELS["deepseek"]: bare deepseek-v4-pro, deepseek-v4-flash alongside existing entries
Context length auto-resolves via existing deepseek substring entry (128K) in DEFAULT_CONTEXT_LENGTHS

Validation

	Before	After
DeepSeek V4 in OR picker	no	yes
DeepSeek V4 in Nous fallback	no	yes
DeepSeek V4 on direct API	no	yes
Targeted tests	—	323 passed

- OpenRouter: deepseek/deepseek-v4-pro, deepseek/deepseek-v4-flash - Nous Portal (fallback list): same two slugs - Native DeepSeek provider: bare deepseek-v4-pro, deepseek-v4-flash alongside existing deepseek-chat/deepseek-reasoner Context length resolves via existing 'deepseek' substring entry (128K) in DEFAULT_CONTEXT_LENGTHS.

alt-glitch · 2026-04-24T05:46:15Z

This supersedes #14891 and #14911. Addresses feature request #14902.

…#14934) - OpenRouter: deepseek/deepseek-v4-pro, deepseek/deepseek-v4-flash - Nous Portal (fallback list): same two slugs - Native DeepSeek provider: bare deepseek-v4-pro, deepseek-v4-flash alongside existing deepseek-chat/deepseek-reasoner Context length resolves via existing 'deepseek' substring entry (128K) in DEFAULT_CONTEXT_LENGTHS.

#14934 added deepseek-v4-pro / deepseek-v4-flash to the DeepSeek native provider but the context-window lookup still falls back to the existing "deepseek" substring entry (128K). DeepSeek V4 ships with a 1M context window, so any caller relying on get_model_context_length() for pre-flight token budgeting (compression, context warnings) under-counts by ~8x. Add explicit lowercase entries for the four DeepSeek model ids that ship 1M context: - deepseek-v4-pro - deepseek-v4-flash - deepseek-chat (legacy alias, server-side maps to v4-flash non-thinking) - deepseek-reasoner (legacy alias, server-side maps to v4-flash thinking) Longest-key-first substring matching means these explicit entries also cover the vendor-prefixed forms (deepseek/deepseek-v4-pro on OpenRouter and Nous Portal) without regressing the existing 128K fallback for older / unknown DeepSeek model ids on custom endpoints. Source: https://api-docs.deepseek.com/zh-cn/quick_start/pricing

…#14934) - OpenRouter: deepseek/deepseek-v4-pro, deepseek/deepseek-v4-flash - Nous Portal (fallback list): same two slugs - Native DeepSeek provider: bare deepseek-v4-pro, deepseek-v4-flash alongside existing deepseek-chat/deepseek-reasoner Context length resolves via existing 'deepseek' substring entry (128K) in DEFAULT_CONTEXT_LENGTHS.

NousResearch#14934 added deepseek-v4-pro / deepseek-v4-flash to the DeepSeek native provider but the context-window lookup still falls back to the existing "deepseek" substring entry (128K). DeepSeek V4 ships with a 1M context window, so any caller relying on get_model_context_length() for pre-flight token budgeting (compression, context warnings) under-counts by ~8x. Add explicit lowercase entries for the four DeepSeek model ids that ship 1M context: - deepseek-v4-pro - deepseek-v4-flash - deepseek-chat (legacy alias, server-side maps to v4-flash non-thinking) - deepseek-reasoner (legacy alias, server-side maps to v4-flash thinking) Longest-key-first substring matching means these explicit entries also cover the vendor-prefixed forms (deepseek/deepseek-v4-pro on OpenRouter and Nous Portal) without regressing the existing 128K fallback for older / unknown DeepSeek model ids on custom endpoints. Source: https://api-docs.deepseek.com/zh-cn/quick_start/pricing