Priority 1Provider: Gemini Ai StudioModel: gemini-3.5-flashEndpoint: https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContentRPM: 15 RPM | RPD: 1,500 RPD | TPM: 250KTokens: ~6M/day | ~180M/month | Quality: 9.5/10 - Frontier-----------------------------------------------------------------Priority 2Provider: Groq - DefaultModel: llama-3.3-70b-versatileEndpoint: https://api.groq.com/openai/v1/chat/completionsRPM: 100 RPM | RPD: 14,400 RPDTokens: ~14M/day | ~420M/month | Quality: 8.5/10 - Ultra Fast-----------------------------------------------------------------Priority 3Provider: OpenRouterModel: nvidia/nemotron-3-ultra-550b-a55b:freeEndpoint: https://openrouter.ai/api/v1/chat/completionsRPM: 20 RPM | RPD: 50 free / 1,000 with $10Tokens: 200K/day free / 4M with $10 | Quality: 9.8/10 - SMARTEST 550B-----------------------------------------------------------------Priority 4Provider: OpenRouterModel: openai/gpt-oss-120b:freeEndpoint: https://openrouter.ai/api/v1/chat/completionsRPM: 20 RPM | RPD: 50 / 1,000Tokens: 200K / 4M | Quality: 9.3/10 - Best Reasoning-----------------------------------------------------------------Priority 5Provider: OpenRouterModel: poolside/laguna-m.1:freeEndpoint: https://openrouter.ai/api/v1/chat/completionsRPM: 20 RPM | RPD: 50 / 1,000Tokens: 200K / 4M | Quality: 9.2/10 - Best Coding-----------------------------------------------------------------Priority 6Provider: OpenRouterModel: google/gemma-4-31b-it:freeEndpoint: https://openrouter.ai/api/v1/chat/completionsRPM: 20 RPM | RPD: 50 / 1,000Tokens: 200K / 4M | Quality: 8.8/10 - Vision-----------------------------------------------------------------Priority 7Provider: OpenRouterModel: meta-llama/llama-3.3-70b-instruct:freeEndpoint: https://openrouter.ai/api/v1/chat/completionsRPM: 20 RPM | RPD: 50 / 1,000Tokens: 200K / 4M | Quality: 8.5/10 - Stable-----------------------------------------------------------------Priority 8Provider: OpenRouterModel: qwen/qwen3-next-80b-a3b-instruct:freeEndpoint: https://openrouter.ai/api/v1/chat/completionsRPM: 20 RPM | RPD: 50 / 1,000Tokens: 200K / 4M | Quality: 8.7/10-----------------------------------------------------------------Priority 9Provider: OpenRouterModel: openai/gpt-oss-20b:freeEndpoint: https://openrouter.ai/api/v1/chat/completionsRPM: 20 RPM | RPD: 50 / 1,000Tokens: 200K / 4M | Quality: 8.0/10-----------------------------------------------------------------Priority 10Provider: MistralModel: mistral-small-latestEndpoint: https://api.mistral.ai/v1/chat/completionsRPM: - | RPD: 1B/month capTokens: ~33M/day | 1B/month | Quality: 8.2/10 - Biggest Quota-----------------------------------------------------------------Priority 11Provider: SambaNovaModel: Meta-Llama-3.3-70B-InstructEndpoint: https://api.sambanova.ai/v1/chat/completionsRPM: 2 RPM | RPD: ~500Tokens: ~1M/day | ~30M/month | Quality: 8.5/10-----------------------------------------------------------------Priority 12Provider: Hugging Face RouterModel: meta-llama/Llama-3.3-70B-InstructEndpoint: https://router.huggingface.co/v1/chat/completionsRPM: Low | RPD: ~1k RPDTokens: ~2M/day | Quality: 8.5/10-----------------------------------------------------------------Priority 13Provider: CloudflareModel: @cf/meta/llama-3.3-70b-instruct-fp8-fastEndpoint: https://api.cloudflare.com/client/v4/accounts/2f34d7165f1b31846d1731666045897b/ai/v1/chat/completionsRPM: Low | RPD: 10k tokens/dayTokens: 10k/day | Quality: 8.5/10-----------------------------------------------------------------Priority 14Provider: OpenCode ZenModel: big-pickleEndpoint: https://opencode.ai/zen/v1/chat/completionsRPM: 1/sec | RPD: 400 RPD (200 per 5-12h)Tokens: ~800K/day | Quality: 9.0/10 - Stealth Best-----------------------------------------------------------------Priority 15Provider: OpenCode - North MiniModel: north-mini-code-freeEndpoint: https://opencode.ai/zen/v1/chat/completionsTokens: 400 RPD ~800K/day | Quality: 7.8/10-----------------------------------------------------------------Priority 16Provider: OpenCode - DeepSeek V4Model: deepseek-v4-flash-freeEndpoint: https://opencode.ai/zen/v1/chat/completionsTokens: 400 RPD ~800K/day | Quality: 8.0/10-----------------------------------------------------------------Priority 17Provider: OpenCode - Nemotron 3 UltraModel: nemotron-3-ultra-freeEndpoint: https://opencode.ai/zen/v1/chat/completionsTokens: 400 RPD ~800K/day | Quality: 8.5/10-----------------------------------------------------------------Priority 18Provider: OpenCode - MiMo V2.5Model: mimo-v2.5-freeEndpoint: https://opencode.ai/zen/v1/chat/completionsTokens: 400 RPD ~800K/day | Quality: 7.9/10-----------------------------------------------------------------Priority 19Provider: OpenCode - LongCat 2.0Model: longcat-2.0-freeEndpoint: https://opencode.ai/zen/v1/chat/completionsTokens: 400 RPD ~800K/day | Quality: 7.5/10-----------------------------------------------------------------TOTAL FREE: ~60M/day free (no credit) / ~90M/day with $10 OpenRouter credit