diff --git a/llm-gateway.yaml b/llm-gateway.yaml index 0825e23..38d97a0 100644 --- a/llm-gateway.yaml +++ b/llm-gateway.yaml @@ -59,45 +59,65 @@ providers: models: # ═══ TIER 1: Free (OpenRouter free models, $0) ═══ - - name: "deepseek-v3-free" + - name: "llama-3.3-70b-free" routes: - provider: openrouter - model: "deepseek/deepseek-v3.2-20251201:free" + model: "meta-llama/llama-3.3-70b-instruct:free" - - name: "gemini-2.5-flash-free" + - name: "deepseek-r1-free" routes: - provider: openrouter - model: "google/gemini-2.5-flash:free" - - - name: "gemini-2.0-flash-free" - routes: - - provider: openrouter - model: "google/gemini-2.0-flash-001:free" + model: "deepseek/deepseek-r1-0528:free" - name: "gpt-oss-free" routes: - provider: openrouter model: "openai/gpt-oss-120b:free" - - name: "gpt-5-nano-free" + - name: "gpt-oss-20b-free" routes: - provider: openrouter - model: "openai/gpt-5-nano-2025-08-07:free" + model: "openai/gpt-oss-20b:free" - - name: "grok-4.1-fast-free" + - name: "qwen3-coder-free" routes: - provider: openrouter - model: "x-ai/grok-4.1-fast:free" + model: "qwen/qwen3-coder:free" + + - name: "qwen3-235b-free" + routes: + - provider: openrouter + model: "qwen/qwen3-235b-a22b-thinking-2507" + + - name: "glm-4.5-air-free" + routes: + - provider: openrouter + model: "z-ai/glm-4.5-air:free" + + - name: "nemotron-nano-free" + routes: + - provider: openrouter + model: "nvidia/nemotron-nano-9b-v2:free" - name: "trinity-large-free" routes: - provider: openrouter model: "arcee-ai/trinity-large-preview:free" - - name: "kimi-k2.5-free" + - name: "mistral-small-free" routes: - provider: openrouter - model: "moonshotai/kimi-k2.5-0127:free" + model: "mistralai/mistral-small-3.1-24b-instruct:free" + + - name: "gemma-3-27b-free" + routes: + - provider: openrouter + model: "google/gemma-3-27b-it:free" + + - name: "step-3.5-flash-free" + routes: + - provider: openrouter + model: "stepfun/step-3.5-flash:free" # ═══ TIER 2: Low cost (Groq, Cerebras — free tier with rate limits) ═══ - name: "llama-3.3-70b"