diff --git a/config.yaml b/config.yaml index 127004a..89af7c6 100644 --- a/config.yaml +++ b/config.yaml @@ -329,6 +329,56 @@ model_list: # logged; and a retry_policy that retries transient connection errors (base # num_retries) but NEVER retries timeouts (TimeoutErrorRetries: 0) — a timed-out # generation is already billed by Tinfoil, so re-hitting it re-bills. + + # --- Stable aliases ------------------------------------------------------- + # Version-free names members can pin once and keep using across transitions. + # When we move the underlying model, only the pointer here changes; member + # client configs and the docs do not. Pricing is stated AT the alias, so a + # transition that changes price is visible in the model list and in budgets + # (LiteLLM bills the alias's model_info, not the target's). + # Policy: `-latest` = the default renewable, policy-private route; + # `-tee` = the same family served inside a TEE (attested hardware). + - model_name: deepseek-flash-latest + litellm_params: + model: openai/deepseek-v4.1-flash + 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 + + - model_name: deepseek-flash-tee + litellm_params: + model: openai/deepseek-v4-1-flash + api_base: http://127.0.0.1:3301/v1 + api_key: os.environ/TINFOIL_API_KEY + model_info: + input_cost_per_token: 0.00000065 + output_cost_per_token: 0.00000145 + cache_read_input_token_cost: 0.00000013 + + - model_name: glm-flash-latest + 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 + + # Tinfoil's flash GLM was deprecated 2026-10-09; the TEE route for this family + # is the flagship, so the alias is named glm-tee rather than glm-flash-tee. + - model_name: glm-tee + litellm_params: + 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: 0.00000180 + output_cost_per_token: 0.00000575 + cache_read_input_token_cost: 0.00000045 router_settings: num_retries: 2 timeout: 180