diff --git a/CLAUDE.md b/CLAUDE.md
index d432fbb..92d486c 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -41,6 +41,7 @@ lmproto/openai_compatible/     ← Base: model, config, client
 lmproto/openai/                ← OpenAI platform: Responses + chat (extends base)
 lmproto/anthropic/             ← Anthropic Messages: model, config, client
 lmproto/deepseek/openai_compat/ ← Extends base via inheritance + extra fields
+lmproto/deepseek/responses/     ← DeepSeek Responses client (extends OpenAI Responses client; SSE stops at terminal events, no `[DONE]`)
 ```
 
 - **`openai_compatible/model.py`** — tagged chat messages (`SystemChatMessage`, `UserChatMessage`, …), tools, request/response, streaming chunks.
@@ -50,15 +51,15 @@ lmproto/deepseek/openai_compat/ ← Extends base via inheritance + extra fields
 - **`openai/client.py`** — platform `OpenAIClient` (`kind="responses"`): chat completions + `responses` / `get_response` / `delete_response`.
 - **`anthropic/model.py`** — Anthropic Messages request/response + SSE event models.
 - **`anthropic/client.py`** — `AnthropicClient` (`kind="messages"`): `POST /messages` + `GET /models`.
-- **DeepSeek** — `DeepseekOpenAIClient` (`kind="chat_completions"`); models add `reasoning_content`, `prefix`, `ThinkingOptions`. Config default model ids: `deepseek-v4-flash`, `deepseek-v4-pro`.
+- **DeepSeek** — `DeepseekOpenAIClient` (`kind="chat_completions"`); models add `reasoning_content`, `prefix`, `ThinkingOptions`. Config default model ids: `deepseek-v4-flash`, `deepseek-v4-pro`. `DeepseekResponsesClient` (`kind="responses"`) extends the OpenAI Responses client for `convention = "responses"` (SSE stops at terminal events — DeepSeek sends no `[DONE]`).
 
 ### Config (`config/`)
 
-TOML load/store (`ConfigStore`): `[providers]` tagged union presets, `[database]` section. Default path via platformdirs. Providers may set `timeout` as a float or `{ connect, read }` (`HttpTimeoutConfig`); omitted → product defaults (10s connect / 600s read).
+TOML load/store (`ConfigStore`): `[providers]` tagged union presets, `[database]` section. Default path via platformdirs. Providers may set `timeout` as a float or `{ connect, read }` (`HttpTimeoutConfig`); omitted → product defaults (10s connect / 600s read). `DeepseekProvider.convention` (Literal: `""`/`"openai"`/`"anthropic"`/`"responses"`) selects the DeepSeek API surface — `"responses"` → OpenAI Responses; a per-model `ModelConfig.convention` overrides it (empty = inherit).
 
 ### Runtime (`runtime/`)
 
-`create_client(provider)` maps config `Provider` → protocol client by effective preset (model-level `preset`/`url` overrides apply). `normalize_http_timeout` feeds OpenAI-compatible configs and Anthropic. Mapping: `openai` → `OpenAIClient` (agent uses Responses), `openai-compatible` / `deepseek` → chat-completions clients, `anthropic` → `AnthropicClient`.
+`create_client(provider)` maps config `Provider` → protocol client by effective preset (model-level `preset`/`url` overrides apply). `normalize_http_timeout` feeds OpenAI-compatible configs and Anthropic. Mapping: `openai` → `OpenAIClient` (agent uses Responses), `openai-compatible` / `deepseek` → chat-completions clients (deepseek with effective `convention = "responses"` → `DeepseekResponsesClient`), `anthropic` → `AnthropicClient`.
 
 ### Memory (`memory/`)
 
diff --git a/README.md b/README.md
index e5da484..18a5a2b 100644
--- a/README.md
+++ b/README.md
@@ -163,10 +163,20 @@ Supported provider presets today:
 |--------|------------------------|--------|
 | `openai` (default if `preset` omitted) | OpenAI **Responses** (`POST /responses`) | Default models `gpt-5.4` / `gpt-5.4-mini` / `gpt-5.4-nano` when `models` is omitted; optional `provider_tools` (default `web_search`) |
 | `openai-compatible` | Chat Completions | Generic hosts (vLLM, LiteLLM, proxies); requires `url` |
-| `deepseek` | Chat Completions (DeepSeek) | Default models `deepseek-v4-flash` / `deepseek-v4-pro` when `models` is omitted |
+| `deepseek` | Chat Completions (DeepSeek) | Default models `deepseek-v4-flash` / `deepseek-v4-pro` when `models` is omitted; set `convention = "responses"` (provider or per-model) to use the OpenAI **Responses** API (`POST /responses`, currently only `deepseek-v4-flash`) |
 | `anthropic` | Anthropic **Messages** (`POST /messages`) | Native tools/streaming; set `access_key_or_token` (API key) |
 
-Model-level `preset` / `url` overrides on a catalog entry can route a single provider name to a different API (e.g. gateway + Anthropic model).
+Model-level `preset` / `url` overrides on a catalog entry can route a single provider name to a different API (e.g. gateway + Anthropic model). DeepSeek models may also carry a per-model `convention` (empty = inherit the provider-level one), e.g. serve `deepseek-v4-flash` over Responses while `deepseek-v4-pro` stays Chat Completions:
+
+```toml
+[providers.deepseek]
+preset = "deepseek"
+access_key_or_token = "sk-..."
+
+[providers.deepseek.models]
+"deepseek-v4-flash" = { text = true, convention = "responses" }
+"deepseek-v4-pro" = { text = true }
+```
 
 If `[database]` is omitted (or SQLite `url` is unset/empty), chat uses a durable file under the user data dir (e.g. `~/.local/share/plyngent/chat.db` on Linux). Set `url = ":memory:"` for a true in-memory SQLite (CLI warns; no file; useful for tests).
 
diff --git a/doc/plyngent.example.toml b/doc/plyngent.example.toml
index 513eb40..22da683 100644
--- a/doc/plyngent.example.toml
+++ b/doc/plyngent.example.toml
@@ -103,14 +103,21 @@ access_key_or_token = "sk-replace-me"
 # "claude-sonnet-4-20250514" = { text = true }
 # "claude-opus-4-20250514" = { text = true }
 
-# --- DeepSeek (OpenAI-compatible convention) ---
+# --- DeepSeek (OpenAI-compatible convention; optional Responses API) ---
 # Default models if [providers.*.models] is omitted: deepseek-v4-flash, deepseek-v4-pro.
 # [providers.deepseek]
 # preset = "deepseek"
 # access_key_or_token = "sk-replace-me"
 # # url defaults to https://api.deepseek.com when empty
-# extras = { convention = "openai" }
+# # Convention selects the API surface:
+# #   "" / "openai"   → OpenAI-compatible chat completions (default)
+# #   "responses"     → OpenAI Responses API (POST /responses; today only
+# #                     deepseek-v4-flash supports it)
+# #   "anthropic"     → legacy value, ignored (still chat completions)
+# convention = "responses"
+# # Legacy location (parsed but ignored; prefer the typed field above):
+# # extras = { convention = "openai" }
 #
 # [providers.deepseek.models]
-# "deepseek-v4-flash" = { text = true }
+# "deepseek-v4-flash" = { text = true, convention = "responses" }
 # "deepseek-v4-pro" = { text = true }