feat: add Z.AI chat models + 5 new providers (#3)

* feat: add Z.AI chat models (GLM-5, GLM-4.7)

Sync with librefang/librefang#409 — add the two Z.AI chat models
to the standalone model catalog.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add 5 new providers (Stepfun, SiliconFlow, Baichuan, NVIDIA NIM, Writer)

- Stepfun (阶跃星辰): step-3.5-flash, step-3, step-2-mini, step-1o-turbo-vision
- SiliconFlow (硅基流动): inference platform, models discovered at runtime
- Baichuan (百川): Baichuan-4, Baichuan-3 Turbo 128K
- NVIDIA NIM: inference platform, models discovered at runtime
- Writer: Palmyra X5, X4, Med, Fin
- Add global aliases for stepfun, baichuan, writer

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

providers/baichuan.toml

@@ -0,0 +1,35 @@
+# Baichuan (百川智能) — https://platform.baichuan-ai.com
+# Models: 2
+
+[provider]
+id = "baichuan"
+display_name = "Baichuan (百川)"
+api_key_env = "BAICHUAN_API_KEY"
+base_url = "https://api.baichuan-ai.com/v1"
+key_required = true
+
+[[models]]
+id = "Baichuan4"
+display_name = "Baichuan-4"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 14.30
+output_cost_per_m = 14.30
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["baichuan-4", "baichuan4"]
+
+[[models]]
+id = "Baichuan3-Turbo-128k"
+display_name = "Baichuan-3 Turbo 128K"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 7.15
+output_cost_per_m = 7.15
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["baichuan-3-turbo", "baichuan3-turbo"]

providers/nvidia-nim.toml

@@ -0,0 +1,9 @@
+# NVIDIA NIM — https://build.nvidia.com
+# Models: 0 (hosts third-party models, discovered dynamically at runtime)
+
+[provider]
+id = "nvidia-nim"
+display_name = "NVIDIA NIM"
+api_key_env = "NVIDIA_API_KEY"
+base_url = "https://integrate.api.nvidia.com/v1"
+key_required = true

providers/siliconflow.toml

@@ -0,0 +1,9 @@
+# SiliconFlow (硅基流动) — https://siliconflow.cn
+# Models: 0 (hosts third-party models, discovered dynamically at runtime)
+
+[provider]
+id = "siliconflow"
+display_name = "SiliconFlow"
+api_key_env = "SILICONFLOW_API_KEY"
+base_url = "https://api.siliconflow.cn/v1"
+key_required = true

providers/stepfun.toml

@@ -0,0 +1,61 @@
+# Stepfun (阶跃星辰) — https://platform.stepfun.com
+# Models: 4
+
+[provider]
+id = "stepfun"
+display_name = "Stepfun (阶跃星辰)"
+api_key_env = "STEPFUN_API_KEY"
+base_url = "https://api.stepfun.com/v1"
+key_required = true
+
+[[models]]
+id = "step-3.5-flash"
+display_name = "Step 3.5 Flash"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 256000
+input_cost_per_m = 0.10
+output_cost_per_m = 0.30
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["stepfun-flash", "step-flash"]
+
+[[models]]
+id = "step-3"
+display_name = "Step 3"
+tier = "frontier"
+context_window = 65536
+max_output_tokens = 16384
+input_cost_per_m = 0.57
+output_cost_per_m = 1.43
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["stepfun-3"]
+
+[[models]]
+id = "step-2-mini"
+display_name = "Step 2 Mini"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.14
+output_cost_per_m = 0.29
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["stepfun-mini"]
+
+[[models]]
+id = "step-1o-turbo-vision"
+display_name = "Step 1o Turbo Vision"
+tier = "smart"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.36
+output_cost_per_m = 1.14
+supports_tools = false
+supports_vision = true
+supports_streaming = true
+aliases = ["stepfun-vision"]

providers/writer.toml

@@ -0,0 +1,61 @@
+# Writer — https://writer.com
+# Models: 4
+
+[provider]
+id = "writer"
+display_name = "Writer"
+api_key_env = "WRITER_API_KEY"
+base_url = "https://api.writer.com/v1"
+key_required = true
+
+[[models]]
+id = "palmyra-x5"
+display_name = "Palmyra X5"
+tier = "frontier"
+context_window = 1048576
+max_output_tokens = 8192
+input_cost_per_m = 0.60
+output_cost_per_m = 6.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["palmyra-x5", "writer-x5"]
+
+[[models]]
+id = "palmyra-x4"
+display_name = "Palmyra X4"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 4096
+input_cost_per_m = 2.50
+output_cost_per_m = 10.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["palmyra-x4", "writer-x4"]
+
+[[models]]
+id = "palmyra-med"
+display_name = "Palmyra Med"
+tier = "smart"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 5.00
+output_cost_per_m = 12.00
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["palmyra-med", "writer-med"]
+
+[[models]]
+id = "palmyra-fin"
+display_name = "Palmyra Fin"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 4096
+input_cost_per_m = 5.00
+output_cost_per_m = 12.00
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["palmyra-fin", "writer-fin"]

providers/zai.toml

@@ -1,5 +1,5 @@
 # Z.AI — https://api.z.ai (Zhipu domain alias)
-# Models: 0 (uses same models as zhipu, different domain)
+# Models: 2
 
 [provider]
 id = "zai"
@@ -7,3 +7,29 @@ display_name = "Z.AI"
 api_key_env = "ZHIPU_API_KEY"
 base_url = "https://api.z.ai/api/paas/v4"
 key_required = true
+
+[[models]]
+id = "zai/glm-5-20250605"
+display_name = "GLM-5 (Z.AI)"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 1.0
+output_cost_per_m = 3.2
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["zai-glm-5"]
+
+[[models]]
+id = "zai/glm-4.7"
+display_name = "GLM-4.7 (Z.AI)"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.6
+output_cost_per_m = 2.2
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["zai-glm-4.7"]