From aa9331cff32c5287e463fc8aa87efe3a8435f03e Mon Sep 17 00:00:00 2001 From: Inferencebot Date: Wed, 18 Nov 2026 17:24:39 +0000 Subject: [PATCH] gateway: convert GreenPT and Regolo EUR prices to USD at FX 1.16 (corrected) Previous attempt forgot to multiply by the FX and could match a prefix sibling; reverted and redone with exact model-name anchors. EUR remains the source of truth in comments and docs; model_info now carries EUR x 1.16 USD so member billing covers cost. --- config.yaml | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/config.yaml b/config.yaml index c4a13ee..3f38ff4 100644 --- a/config.yaml +++ b/config.yaml @@ -6,8 +6,9 @@ # via environment variable TINFOIL_API_KEY. # # Pricing (model_info) is per-token, derived from provider per-1M rates: -# EUR->USD FX = 1.16 (policy, applied 2026-11-18; GreenPT/Regolo quote EUR). -# LiteLLM's cost fields are USD; EUR list prices are converted here, never billed raw. +# EUR->USD FX = 1.16 (policy, set 2026-11-18). GreenPT and Regolo quote EUR; +# LiteLLM's cost fields are USD-shaped, so EUR list prices are converted here. +# Never paste EUR numerals into model_info — that under-bills members by the FX gap. # greenpt/deepseek-v4.1-flash: $0.36 in / $1.45 out / $0.04 cached per 1M (1017 snapshot) # 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 @@ -44,9 +45,9 @@ model_list: api_base: https://api.greenpt.ai/v1 api_key: os.environ/GREENPT_API_KEY model_info: - input_cost_per_token: 3.6e-07 - output_cost_per_token: 1.45e-06 - cache_read_input_token_cost: 4e-08 + input_cost_per_token: 4.176e-07 + output_cost_per_token: 1.682e-06 + cache_read_input_token_cost: 4.64e-08 # DeepSeek V4.1 Flash on Tinfoil (TEE) — private counterpart to the default. - model_name: tinfoil/deepseek-v4-1-flash @@ -95,9 +96,9 @@ model_list: api_base: https://api.greenpt.ai/v1 api_key: os.environ/GREENPT_API_KEY model_info: - input_cost_per_token: 1.1e-07 - output_cost_per_token: 4.4e-07 - cache_read_input_token_cost: 2.2e-08 + input_cost_per_token: 1.276e-07 + output_cost_per_token: 5.104e-07 + cache_read_input_token_cost: 2.552e-08 # GLM-5.3 (full flagship) on GreenPT — strongest agentic model in the green # tier. $1.10 in / $4.40 out per 1M, 1M context. @@ -107,9 +108,9 @@ model_list: api_base: https://api.greenpt.ai/v1 api_key: os.environ/GREENPT_API_KEY model_info: - input_cost_per_token: 1.1e-06 - output_cost_per_token: 4.4e-06 - cache_read_input_token_cost: 2.75e-07 + input_cost_per_token: 1.276e-06 + output_cost_per_token: 5.104e-06 + cache_read_input_token_cost: 3.19e-07 # --- Audio models (Tinfoil, inside the TEE) --- # NOT chat models: these power /v1/audio/* routes (STT for dictation, TTS for @@ -164,8 +165,8 @@ model_list: api_key: os.environ/REGOLO_API_KEY model_info: mode: chat - input_cost_per_token: 2e-07 - output_cost_per_token: 7e-07 + input_cost_per_token: 2.32e-07 + output_cost_per_token: 8.12e-07 # Gemma 4 (31B) — Google's dense multimodal Gemma 4. $0.40 in / $0.60 out # per 1M, 100K ctx. @@ -176,8 +177,8 @@ model_list: api_key: os.environ/REGOLO_API_KEY model_info: mode: chat - input_cost_per_token: 4e-07 - output_cost_per_token: 6e-07 + input_cost_per_token: 4.64e-07 + output_cost_per_token: 6.96e-07 - model_name: regolo/qwen-image litellm_params: @@ -307,7 +308,7 @@ model_list: api_key: os.environ/GREENPT_API_KEY model_info: mode: embedding - input_cost_per_token: 2.5e-07 + input_cost_per_token: 2.9e-07 output_cost_per_token: 0 max_input_tokens: 32000 @@ -328,7 +329,7 @@ model_list: api_key: os.environ/GREENPT_API_KEY model_info: mode: embedding - input_cost_per_token: 2e-07 + input_cost_per_token: 2.32e-07 output_cost_per_token: 0 max_input_tokens: 32000