# LiteLLM config for inference.coop
# PRODUCTION config: Tinfoil (TEE-protected inference)
# LiteLLM talks plaintext OpenAI to a local Tinfoil proxy (127.0.0.1:3301),
# which verifies the enclave attestation and encrypts request/response bodies
# with EHBP (HPKE) before forwarding to the Tinfoil enclave. Provider key set
# via environment variable TINFOIL_API_KEY.
#
# Pricing (model_info) is per-token, derived from Tinfoil's per-1M rates:
#   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
# Without these, LiteLLM can't price these custom models, so spend shows $0.00
# and the team budget cap is not enforced.
#
# SYNC: the per-model pricing here must mirror the user-facing model list in
# co-op/docs/models.md (and vice-versa). When a rate changes, update BOTH this
# file and models.md — this config is the authoritative source of the numbers;
# models.md is the member-facing mirror.

model_list:
  # DeepSeek V4.1 Flash — default model (replaces V4 Flash, deprecated 2026-09-15)
  - model_name: tinfoil/deepseek-v4-1-flash
    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

  # GPT-OSS 120B — lightweight fallback
  - model_name: tinfoil/gpt-oss-120b
    litellm_params:
      model: openai/gpt-oss-120b
      api_base: http://127.0.0.1:3301/v1
      api_key: os.environ/TINFOIL_API_KEY
    model_info:
      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
    litellm_params:
      model: openai/glm-5-3-flash
      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

  # --- GreenPT (renewable energy) ---
  # OpenAI-compatible, EU-hosted on 100% renewable energy. No TEE proxy needed —
  # LiteLLM talks to GreenPT directly. Pricing from GreenPT /v1/pricing endpoint.
  #   green-r: $0.35 in / $0.95 out per 1M (128k ctx)
  #   green-l: $0.25 in / $0.80 out per 1M (128k ctx)
  - model_name: greenpt/green-r
    litellm_params:
      model: openai/green-r
      api_base: https://api.greenpt.ai/v1
      api_key: os.environ/GREENPT_API_KEY
    model_info:
      input_cost_per_token: 0.00000035
      output_cost_per_token: 0.00000095

  - model_name: greenpt/green-l
    litellm_params:
      model: openai/green-l
      api_base: https://api.greenpt.ai/v1
      api_key: os.environ/GREENPT_API_KEY
    model_info:
      input_cost_per_token: 0.00000025
      output_cost_per_token: 0.00000080

  # GLM-5.3 Flash on GreenPT (note the dotted slug — distinct from Tinfoil's
  # glm-5-3-flash). $0.11 in / $0.44 out / $0.022 cached per 1M.
  - model_name: greenpt/glm-5.3-flash
    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

  # GLM-5.3 (full flagship) on GreenPT — strongest agentic model in the green
  # tier. $1.10 in / $4.40 out per 1M, 1M context.
  - model_name: greenpt/glm-5.3
    litellm_params:
      model: openai/glm-5.3
      api_base: https://api.greenpt.ai/v1
      api_key: os.environ/GREENPT_API_KEY
    model_info:
      input_cost_per_token: 0.0000011
      output_cost_per_token: 0.0000044

  # --- Audio models (Tinfoil, inside the TEE) ---
  # NOT chat models: these power /v1/audio/* routes (STT for dictation, TTS for
  # voice mode). They stay VISIBLE in the API model list so developer members
  # can call them, but the portal filters them out of the chat-facing list
  # (Open WebUI) by their `mode` field, so they never appear as pickable chat
  # options. Pricing per Tinfoil catalog: whisper $0.05/1M in; voxtral-tts
  # listed $0/$0 (verify on invoice — may be beta-free).


  # --- PublicAI (publicly developed / sovereign models) ---
  # OpenAI-compatible gateway for public open models. Apertus is the Swiss AI
  # Initiative's fully-open model (Apache-2.0: weights, code, and training data).
  # Pricing from PublicAI /v1/models (per 1M): 8b $0.10/$0.20, 70b $0.82/$2.92.
  # Member-facing name drops the upstream `swiss-ai/` owner prefix for brevity;
  # the litellm_params.model keeps the full PublicAI id.
  - model_name: publicai/apertus-v1.5-8b
    litellm_params:
      model: openai/swiss-ai/apertus-v1.5-8b
      api_base: https://api.publicai.co/v1
      api_key: os.environ/PUBLICAI_API_KEY
    model_info:
      input_cost_per_token: 0.00000010
      output_cost_per_token: 0.00000020

  - model_name: publicai/apertus-v1.5-70b
    litellm_params:
      model: openai/swiss-ai/apertus-v1.5-70b
      api_base: https://api.publicai.co/v1
      api_key: os.environ/PUBLICAI_API_KEY
    model_info:
      input_cost_per_token: 0.00000082
      output_cost_per_token: 0.00000292

  # --- Audio models (Tinfoil, in-TEE) ---
  # Used for chat dictation (STT) and voice mode (TTS). These are NOT chat
  # models: the member portal's /v1/models filters them out of the chat model
  # list (see AUDIO_MODEL_PREFIXES there) so members don't see them in the
  # picker, but they remain fully callable via /v1/audio/* for API users.
  # whisper-large-v3-turbo: $0.05/1M input tokens. voxtral-tts: listed $0/$0.
  # NOTE: LiteLLM routes audio by the openai/ provider + the endpoint called
  # (/v1/audio/transcriptions or /v1/audio/speech) — there is no
  # "audio_transcription/" provider prefix.
  - model_name: tinfoil/whisper-large-v3-turbo
    litellm_params:
      model: openai/whisper-large-v3-turbo
      api_base: http://127.0.0.1:3301/v1
      api_key: os.environ/TINFOIL_API_KEY
    model_info:
      mode: audio_transcription
      input_cost_per_token: 0.00000005

  - model_name: tinfoil/voxtral-tts
    litellm_params:
      model: openai/voxtral-tts
      api_base: http://127.0.0.1:3301/v1
      api_key: os.environ/TINFOIL_API_KEY
    model_info:
      mode: audio_speech

# Fallback: if DeepSeek is down, use GPT-OSS
# NOTE: DeepSeek V4.1 Flash is a reasoning model — generations routinely run
# longer than 30s. A 30s timeout caused LiteLLM to abandon in-flight DeepSeek
# requests (falling back to GPT-OSS), while Tinfoil still completed and billed
# the abandoned generation. Result: Tinfoil billed ~2x the tokens LiteLLM logged.
# Fix: a generous timeout (180s) so generations complete inside LiteLLM and get
# 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.
router_settings:
  num_retries: 2
  timeout: 180
  retry_policy:
    TimeoutErrorRetries: 0
  fallbacks:
    - tinfoil/deepseek-v4-1-flash:
        - tinfoil/gpt-oss-120b

general_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
  database_url: os.environ/DATABASE_URL
  store_model_in_db: true

litellm_settings:
  salt_key: os.environ/LITELLM_SALT_KEY
  drop_params: true
  num_threads: 4
  request_timeout: 180