From e93a9fb77377dbdaac3238170c62ca320122d334 Mon Sep 17 00:00:00 2001 From: Colin L Date: Wed, 29 Apr 2026 17:37:56 -0700 Subject: [PATCH] fix: update .env.example to a currently-live Nebius model ID zai-org/GLM-4.7-FP8 was retired on Nebius Token Factory. A clean install that copies .env.example boots "healthy" and passes /health, but every real request 404s with "Model not found." This bites anyone setting up the proxy without going through install.sh. Swaps the BIG/MIDDLE/SMALL_MODEL defaults (and the matching key in MODEL_PRICES_JSON, so the observability cost estimator still finds a price entry) to moonshotai/Kimi-K2.5, which is live as of writing. Adds a comment pointing users at GET /v1/models so they can verify model availability themselves. Co-Authored-By: Claude Opus 4.7 (1M context) --- .env.example | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/.env.example b/.env.example index 7dc5ed02..dbb60d4b 100644 --- a/.env.example +++ b/.env.example @@ -4,9 +4,12 @@ IGNORE_CLIENT_API_KEY=true OPENAI_BASE_URL=https://api.tokenfactory.nebius.com/v1 -BIG_MODEL=zai-org/GLM-4.7-FP8 -MIDDLE_MODEL=zai-org/GLM-4.7-FP8 -SMALL_MODEL=zai-org/GLM-4.7-FP8 +# Nebius rotates model availability — verify IDs against +# GET https://api.tokenfactory.nebius.com/v1/models +# before committing. install.sh does this automatically. +BIG_MODEL=moonshotai/Kimi-K2.5 +MIDDLE_MODEL=moonshotai/Kimi-K2.5 +SMALL_MODEL=moonshotai/Kimi-K2.5 VISION_MODEL=Qwen/Qwen2.5-VL-72B-Instruct # Optional: explicit context limits (tokens) for safer max_tokens auto-capping BIG_MODEL_CONTEXT_LIMIT=204800 @@ -31,4 +34,4 @@ OBSERVABILITY_DB_PATH=/app/data/observability.sqlite3 OBSERVABILITY_QUEUE_SIZE=1000 # Keep tool argument storage off unless you explicitly need deeper debugging. OBSERVABILITY_STORE_TOOL_ARGS=false -MODEL_PRICES_JSON='{"zai-org/GLM-4.7-FP8":{"input_per_1m":0.30,"output_per_1m":1.20,"advertised_tok_s":36.8,"currency":"USD"},"Qwen/Qwen2.5-VL-72B-Instruct":{"input_per_1m":0.30,"output_per_1m":1.20,"advertised_tok_s":36.8,"currency":"USD"}}' +MODEL_PRICES_JSON='{"moonshotai/Kimi-K2.5":{"input_per_1m":0.30,"output_per_1m":1.20,"advertised_tok_s":36.8,"currency":"USD"},"Qwen/Qwen2.5-VL-72B-Instruct":{"input_per_1m":0.30,"output_per_1m":1.20,"advertised_tok_s":36.8,"currency":"USD"}}'