inference-bot
d1f57c45d5
num_retries=2 (retries transient connection errors), retry_policy with TimeoutErrorRetries=0 (a timed-out generation is already billed by Tinfoil, so re-hitting it re-bills). Combined with timeout=180, this hedges connection errors without the silent re-billing that caused the Tinfoil spend gap.
76 lines
2.8 KiB
YAML
76 lines
2.8 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 Tinfoil's per-1M rates:
|
|
# deepseek-v4-1-flash: $0.65 in / $1.45 out / $0.13 cached per 1M
|
|
# gpt-oss-120b: $0.15 in / $0.60 out per 1M
|
|
# 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.
|
|
|
|
model_list:
|
|
# DeepSeek V4.1 Flash — default model (replaces V4 Flash, deprecated 2026-09-15)
|
|
- model_name: 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: 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: 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
|
|
|
|
# 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:
|
|
- deepseek-v4-1-flash:
|
|
- 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
|