From 3397d07ec1b3e1c9b70a89b3653aa830000dcce3 Mon Sep 17 00:00:00 2001 From: Inferencebot Date: Wed, 7 Oct 2026 22:07:40 -0600 Subject: [PATCH] Replace tinfoil/glm-5-3-flash (deprecated 2026-10-09) with tinfoil/glm-5.3 flagship --- config.yaml | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/config.yaml b/config.yaml index bc9f602..2fc409b 100644 --- a/config.yaml +++ b/config.yaml @@ -9,7 +9,7 @@ # greenpt/deepseek-v4.1-flash: $0.22 in / $1.10 out / $0.011 cached per 1M # tinfoil/deepseek-v4-1-flash: $0.65 in / $1.45 out / $0.13 cached per 1M # tinfoil/gpt-oss-120b: $0.15 in / $0.60 out per 1M -# tinfoil/glm-5-3-flash: $0.40 in / $1.25 out / $0.10 cached per 1M +# tinfoil/glm-5.3: $1.80 in / $5.75 out / $0.45 cached per 1M # Without these, LiteLLM can't price these custom models, so spend shows $0.00 # and the team budget cap is not enforced. # @@ -55,16 +55,18 @@ model_list: input_cost_per_token: 0.00000015 output_cost_per_token: 0.00000060 - # GLM-5.3 Flash — fast, efficient MoE model - - model_name: tinfoil/glm-5-3-flash + # GLM-5.3 (full flagship) on Tinfoil (TEE) — replaced tinfoil/glm-5-3-flash + # (Tinfoil deprecated the flash variant 2026-10-09). $1.80 in / $5.75 out / + # $0.45 cached per 1M. Text-only (no vision), reasoning + tool calling. + - model_name: tinfoil/glm-5.3 litellm_params: - model: openai/glm-5-3-flash + model: openai/glm-5-3 api_base: http://127.0.0.1:3301/v1 api_key: os.environ/TINFOIL_API_KEY model_info: - input_cost_per_token: 0.00000040 - output_cost_per_token: 0.00000125 - cache_read_input_token_cost: 0.00000010 + input_cost_per_token: 0.0000018 + output_cost_per_token: 0.00000575 + cache_read_input_token_cost: 0.00000045 # --- GreenPT (renewable energy) --- # OpenAI-compatible, EU-hosted on 100% renewable energy. No TEE proxy needed —