From 77e38d81e03cbe8756a920b1f6c0251013117fe1 Mon Sep 17 00:00:00 2001 From: Inferencebot Date: Mon, 16 Nov 2026 15:55:23 +0000 Subject: [PATCH] gateway: serve the DeepSeek V4.1 Flash 1017 snapshot under the existing names GreenPT no longer recommends the base V4.1 Flash release, so the default model now serves the 1017 snapshot. The deployment keeps model_name greenpt/deepseek-v4.1-flash (and the deepseek-flash-green alias): only the upstream pointer and the cost move. openai/deepseek-v4.1-flash -> openai/deepseek-v4.1-flash-1017 $0.22/$1.10/$0.011 per 1M -> $0.36/$1.45/$0.04 per 1M Why not the rename PR #8 proposes: two days of spend logs show 3,014 calls on the prefixed id against 84 on the alias, spread across member keys. A rename turns every one of those into 400 Invalid model name, and member client configs are not visible to us. Keeping the name means members get the new snapshot and price with no config edit. Credit: slomo, who found the deprecation and supplied the rates (co-op/support#7, PR #8). --- config.yaml | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/config.yaml b/config.yaml index 2fb2113..38112b7 100644 --- a/config.yaml +++ b/config.yaml @@ -6,7 +6,7 @@ # via environment variable TINFOIL_API_KEY. # # Pricing (model_info) is per-token, derived from provider per-1M rates: -# greenpt/deepseek-v4.1-flash: $0.22 in / $1.10 out / $0.011 cached per 1M +# 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 # tinfoil/glm-5.3: $1.80 in / $5.75 out / $0.45 cached per 1M @@ -26,20 +26,25 @@ # models.md is the member-facing mirror. model_list: - # DeepSeek V4.1 Flash on GreenPT — DEFAULT model. Same model family as Tinfoil's + # DeepSeek V4.1 Flash on GreenPT — DEFAULT model. SERVES THE 1017 SNAPSHOT + # (17 Oct 2026) as of 2026-11-16, while KEEPING its version-free model_name: members + # pin this id in client configs we cannot see, and renaming would 400 every one of + # them (measured: 3,014 calls in 2 days on this name, 84 on the deepseek-flash-green + # alias). Repointing is the whole change — no member action. + # Same model family as Tinfoil's # deepseek-v4-1-flash, but on renewable energy and NOT marked Experimental by the # provider (Tinfoil's deepseek + glm-flash carry an "Experimental: may be deprecated # with minimal notice" flag). Policy-based privacy (GreenPT) vs TEE (Tinfoil). # €0.22 in / €1.10 out / €0.011 cached per 1M. - model_name: greenpt/deepseek-v4.1-flash litellm_params: - model: openai/deepseek-v4.1-flash + model: openai/deepseek-v4.1-flash-1017 api_base: https://api.greenpt.ai/v1 api_key: os.environ/GREENPT_API_KEY model_info: - input_cost_per_token: 0.00000022 - output_cost_per_token: 0.00000110 - cache_read_input_token_cost: 0.000000011 + input_cost_per_token: 0.00000036 + output_cost_per_token: 0.00000145 + cache_read_input_token_cost: 0.00000004 # DeepSeek V4.1 Flash on Tinfoil (TEE) — private counterpart to the default. - model_name: tinfoil/deepseek-v4-1-flash @@ -342,13 +347,13 @@ model_list: # them at transitions, so pinning one is what makes a config version-free. - model_name: deepseek-flash-green litellm_params: - model: openai/deepseek-v4.1-flash + model: openai/deepseek-v4.1-flash-1017 api_base: https://api.greenpt.ai/v1 api_key: os.environ/GREENPT_API_KEY model_info: - input_cost_per_token: 0.00000022 - output_cost_per_token: 0.00000110 - cache_read_input_token_cost: 0.000000011 + input_cost_per_token: 0.00000036 + output_cost_per_token: 0.00000145 + cache_read_input_token_cost: 0.00000004 - model_name: deepseek-flash-tee litellm_params: