From 2369c3e848756e90895c1e6c0d543e739c3a6d37 Mon Sep 17 00:00:00 2001
From: inference-bot <bot@inference.coop>
Date: Thu, 24 Sep 2026 10:43:14 -0600
Subject: [PATCH] Add greenpt/glm-5.3-flash (/usr/bin/bash.11//usr/bin/bash.44
 per 1M)

---
 config.yaml | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/config.yaml b/config.yaml
index b74354a..9280c5f 100644
--- a/config.yaml
+++ b/config.yaml
@@ -73,6 +73,18 @@ model_list:
       input_cost_per_token: 0.00000025
       output_cost_per_token: 0.00000080
 
+  # GLM-5.3 Flash on GreenPT (note the dotted slug — distinct from Tinfoil's
+  # glm-5-3-flash). $0.11 in / $0.44 out / $0.022 cached per 1M.
+  - model_name: greenpt/glm-5.3-flash
+    litellm_params:
+      model: openai/glm-5.3-flash
+      api_base: https://api.greenpt.ai/v1
+      api_key: os.environ/GREENPT_API_KEY
+    model_info:
+      input_cost_per_token: 0.00000011
+      output_cost_per_token: 0.00000044
+      cache_read_input_token_cost: 0.000000022
+
 # Fallback: if DeepSeek is down, use GPT-OSS
 # NOTE: DeepSeek V4.1 Flash is a reasoning model — generations routinely run
 # longer than 30s. A 30s timeout caused LiteLLM to abandon in-flight DeepSeek