inference-bot
54925cae97
A member with API-spend history for tinfoil/nomic-embed-text reported the model 'missing'. It was never removed: it has been admin-team scoped (model_info.team_id) since it was added 2026-10-07 for the co-op's own docs-RAG, and team-scoped models are hidden from every /v1/models listing by design — the member's dashboard row was their own refused call. Tinfoil still serves nomic-embed-text upstream; nothing to restore. What WAS missing is a member-callable embedding model. GreenPT serves qwen3-embedding-8b (id verbatim, type EMBEDDINGS): $0.25/1M input from GreenPT's own /v1/pricing, no output charge, 32K context. Added as a regular model_list entry (no team_id) so any member key can call it via /v1/embeddings; the portal filters mode:embedding out of the chat picker. max_input_tokens declared from the provider's contextWindowTokens. Additive change only: every pre-existing model_info byte-identical, fallbacks and pass-through untouched; boot-proved on a spare port in the container before deploy.
318 lines
15 KiB
YAML
318 lines
15 KiB
YAML
# 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 provider per-1M rates:
|
||
# greenpt/deepseek-v4.1-flash: $0.22 in / $1.10 out / $0.011 cached per 1M
|
||
# 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
|
||
# greenpt/qwen3-embedding-8b: $0.25 in / $0 out per 1M (embeddings, 32K ctx)
|
||
# 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 on GreenPT — DEFAULT model. 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
|
||
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
|
||
|
||
# DeepSeek V4.1 Flash on Tinfoil (TEE) — private counterpart to the default.
|
||
- 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 (full flagship) on Tinfoil (TEE) — replaced tinfoil/glm-5-3-flash
|
||
# (Tinfoil deprecated the flash variant 2026-10-09). $1.80 in / $5.75 out /
|
||
# $0.45 cached per 1M. Text-only (no vision), reasoning + tool calling.
|
||
- model_name: tinfoil/glm-5.3
|
||
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: 0.0000018
|
||
output_cost_per_token: 0.00000575
|
||
cache_read_input_token_cost: 0.00000045
|
||
|
||
# --- GreenPT (renewable energy) ---
|
||
# OpenAI-compatible, EU-hosted on 100% renewable energy. No TEE proxy needed —
|
||
# LiteLLM talks to GreenPT directly.
|
||
# (Removed 2026-10: green-l/green-r — GreenPT now marks them "not recommended".)
|
||
|
||
# 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
|
||
cache_read_input_token_cost: 0.000000275
|
||
|
||
# --- 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).
|
||
|
||
# --- Regolo (EU, zero data retention, 100% renewables) ---
|
||
# Seeweb S.r.l. (Italy). Added 2026-10-16 following member suggestion (#22).
|
||
# apertus-70b: replaced PublicAI (removed 2026-10-16) as our Apertus provider —
|
||
# same open-weights model, ~45% cheaper input, EU ZDR + renewables.
|
||
# qwen3.5-122b: large vision+reasoning MoE (262K ctx). REQUIRES
|
||
# chat_template_kwargs: {enable_thinking: false} — otherwise the reasoning
|
||
# phase consumes the entire token budget and content comes back empty.
|
||
# Qwen-Image: image generation via /v1/images/generations, billed per pixel.
|
||
- model_name: regolo/apertus-70b
|
||
litellm_params:
|
||
model: openai/apertus-70b
|
||
api_base: https://api.regolo.ai/v1
|
||
api_key: os.environ/REGOLO_API_KEY
|
||
model_info:
|
||
mode: chat
|
||
input_cost_per_token: 1.16e-6
|
||
output_cost_per_token: 3.944e-6
|
||
|
||
- model_name: regolo/qwen3.5-122b
|
||
litellm_params:
|
||
model: openai/qwen3.5-122b
|
||
api_base: https://api.regolo.ai/v1
|
||
api_key: os.environ/REGOLO_API_KEY
|
||
chat_template_kwargs: {"enable_thinking": false}
|
||
model_info:
|
||
mode: chat
|
||
input_cost_per_token: 6.96e-7
|
||
output_cost_per_token: 3.944e-6
|
||
|
||
- model_name: regolo/qwen-image
|
||
litellm_params:
|
||
model: openai/Qwen-Image
|
||
api_base: https://api.regolo.ai/v1
|
||
api_key: os.environ/REGOLO_API_KEY
|
||
model_info:
|
||
mode: image_generation
|
||
input_cost_per_pixel: 1.74e-8
|
||
|
||
# --- 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: $0/1M tokens + $0.01 per request.
|
||
# voxtral-tts: $0/1M tokens + $0.002 per request.
|
||
# Tinfoil bills these per REQUEST (its model list carries a `requestPrice`);
|
||
# reading only the two token prices made TTS look free and left STT billed off
|
||
# an older catalog. LiteLLM cannot price per request on the audio paths, so
|
||
# patch_audio_request_cost.py (built in via the Dockerfile) makes the cost
|
||
# calculator honour `input_cost_per_request` below. Re-check that build log
|
||
# line after every LiteLLM upgrade.
|
||
# 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
|
||
# Tinfoil: $0 per token, $0.01 per request. The per-request charge is the
|
||
# whole cost, and the patch is what makes it billable.
|
||
input_cost_per_token: 0
|
||
input_cost_per_request: 0.01
|
||
|
||
- 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
|
||
# Tinfoil: $0 per token, $0.002 per request — see the audio section note.
|
||
#
|
||
# input_cost_per_character: 0 is load-bearing, not decoration. The TTS cost
|
||
# branch (cost_per_token, cost_metric == "cost_per_character") raises
|
||
# ValueError("cost for tts call is None") when there is no character price,
|
||
# and that raise aborts the whole cost calculation — so the spend write is
|
||
# skipped and speech bills nothing, whatever input_cost_per_request says.
|
||
# Declaring the zero lets the path complete; the patch then adds the
|
||
# per-request charge.
|
||
input_cost_per_character: 0
|
||
input_cost_per_request: 0.002
|
||
|
||
# --- Embedding model (Tinfoil, in-TEE) ---
|
||
# nomic-embed-text — 768-dim text embeddings for RAG/semantic search.
|
||
# NOT a chat model: it powers /v1/embeddings only. Scoped to the admin
|
||
# account's team (model_info.team_id) so member keys cannot call it — it is
|
||
# an operator resource for the co-op's own docs-RAG, not a member-facing
|
||
# model. The portal also filters it out of the chat-facing /v1/models list by
|
||
# its `mode: embedding`. Pricing per Tinfoil catalog: $0.05/1M input, $0 out.
|
||
- model_name: tinfoil/nomic-embed-text
|
||
litellm_params:
|
||
model: openai/nomic-embed-text
|
||
api_base: http://127.0.0.1:3301/v1
|
||
api_key: os.environ/TINFOIL_API_KEY
|
||
model_info:
|
||
mode: embedding
|
||
team_id: cdfdf422-633f-4432-8893-cffee82a8325
|
||
input_cost_per_token: 0.00000005
|
||
output_cost_per_token: 0.0
|
||
|
||
# --- Embedding model (GreenPT, member-facing) ---
|
||
# qwen3-embedding-8b — text embeddings via /v1/embeddings, callable by any
|
||
# member key (NOT team-scoped, unlike nomic above). Added 2026-11-06 after a
|
||
# member asked for an embedding model: the private (Tinfoil) embedding is an
|
||
# operator-only docs-RAG resource, so this fills the member-facing gap on
|
||
# renewable EU hosting. The portal filters mode:embedding out of the chat
|
||
# picker, so it is API-only — same shape as the audio models above.
|
||
# Pricing per GreenPT /v1/pricing: $0.25/1M input, no output charge
|
||
# (embeddings return vectors; GreenPT lists maxOutputTokens null), 32K
|
||
# context. max_input_tokens declared from the provider's contextWindowTokens
|
||
# so clients don't invent a larger one (the null-caps defect).
|
||
- model_name: greenpt/qwen3-embedding-8b
|
||
litellm_params:
|
||
model: openai/qwen3-embedding-8b
|
||
api_base: https://api.greenpt.ai/v1
|
||
api_key: os.environ/GREENPT_API_KEY
|
||
model_info:
|
||
mode: embedding
|
||
input_cost_per_token: 0.00000025
|
||
output_cost_per_token: 0.0
|
||
max_input_tokens: 32000
|
||
|
||
# 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:
|
||
- greenpt/deepseek-v4.1-flash:
|
||
- tinfoil/deepseek-v4-1-flash
|
||
- 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
|
||
|
||
# --- Metis (GreenPT) — decision model, not a chat model ---
|
||
# Metis is a *decision* endpoint, not a chat completion: it takes a `state`
|
||
# plus up to 32 typed questions and returns PROBABILITIES / choices / scores.
|
||
# It generates no text (output_tokens is always 0), so it cannot be a
|
||
# model_list entry — LiteLLM's chat pipeline has nothing to parse. It is
|
||
# exposed as a pass-through route instead, and members call it with their
|
||
# normal co-op API key (auth: true), never the provider key.
|
||
#
|
||
# GreenPT-hosted (policy-based privacy, EU, 100% renewable), same
|
||
# GREENPT_API_KEY the green chat models already use.
|
||
# Price: $0.12 per 1M *input* tokens; output is free.
|
||
#
|
||
# METERING: exact, from the token count GreenPT reports back. Metis is not a
|
||
# model_list entry (LiteLLM's chat pipeline has nothing to parse), so it is
|
||
# priced through the coop_passthrough_cost_per_token map below, keyed by this
|
||
# route's path: a call's cost is usage.input_tokens × the rate. patch_
|
||
# passthrough_token_cost.py (built in via the Dockerfile) reads
|
||
# usage.input_tokens from the Metis response body at logging time and writes
|
||
# the exact figure to member spend. cost_per_request on the route is now only
|
||
# a fallback: it applies if a response ever arrives without a usable token
|
||
# count, so a call is never silently free. Keep the two in sync.
|
||
#
|
||
# Routes here (matched by prefix) may be called by ANY authenticated member
|
||
# key. LiteLLM's own gate for auth=true pass-through routes
|
||
# (`allowed_passthrough_routes`) is an Enterprise-only field, so on this
|
||
# community-edition proxy it can never be granted to member keys — the only
|
||
# other option, auth:false, would expose the route publicly and forward the
|
||
# co-op's GreenPT key to anonymous callers. This list is consumed at build
|
||
# time by patch_passthrough_key_access.py; authentication is unchanged (the
|
||
# endpoint still requires a valid key).
|
||
coop_passthrough_open_to_keys:
|
||
- "/v1/systemone"
|
||
# Exact per-input-token pricing (USD per token) for pass-through routes that
|
||
# report their own usage in the RESPONSE BODY — the shape the x-litellm-*
|
||
# response-header contract does not cover. Keyed by the gateway route path
|
||
# (an upstream target URL also matches). Any route listed here is billed from
|
||
# usage.input_tokens × the rate instead of its flat cost_per_request; a route
|
||
# not listed is unchanged. Consumed at build time by
|
||
# patch_passthrough_token_cost.py.
|
||
coop_passthrough_cost_per_token:
|
||
# Metis (GreenPT): $0.12 per 1M input tokens, output always free.
|
||
"/v1/systemone": 0.00000012
|
||
pass_through_endpoints:
|
||
- path: "/v1/systemone"
|
||
target: "https://api.greenpt.ai/v1/systemone"
|
||
headers:
|
||
Authorization: "Bearer os.environ/GREENPT_API_KEY"
|
||
Content-Type: "application/json"
|
||
auth: true
|
||
methods: ["POST"]
|
||
timeout: 60
|
||
# Fallback only — the exact token cost above is what bills in practice.
|
||
cost_per_request: 0.0001
|
||
|
||
litellm_settings:
|
||
salt_key: os.environ/LITELLM_SALT_KEY
|
||
drop_params: true
|
||
num_threads: 4
|
||
request_timeout: 180
|