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: