Home / Changelog

Pricing changelog

We sync from official provider docs via a weekly script, then review rates in a PR before merge. Each model keeps a lastVerified stamp, not a fake live streaming API.

  1. Compare hub expansion: +40 high-intent pairs (frontier/mid, budget, reasoning, host-vs-host Llama/DeepSeek/Qwen/Mixtral, coding, generation migrations).

  2. Catalog to ~120 models: dated GPT-4o/4.1 and o1-mini/preview, Claude 3.5 Sonnet / 2.1, Gemini 2.0 Pro Exp / Gemma 3, DeepSeek R1 family, Grok 2 Vision, Mixtral 8x22B, Groq SpecDec/QwQ, Command R snapshot, Llama 4 Maverick and R1 on Together/Fireworks.

  3. Catalog to 100 models: legacy GPT-4 / Claude 3 Haiku / Gemini 1.5 Flash-8B, DeepSeek VL, Grok Vision Beta, Open Mixtral, Gemma 7B, Command R+ snapshot, Llama 3.2 3B on Together/Fireworks. More host and generation compares.

  4. Week 2: expanded all remaining thin guides with FAQs; +18 models (legacy GPT/Claude/Gemini, DeepSeek Coder, more Groq/Together/Fireworks/Cohere/Mistral). Compare pairs extended for host and generation migrations.

  5. Week expansion: +20 models (legacy GPT-4 Turbo/o1, Gemini 1.5, DeepSeek V3, Grok 2, Mistral Nemo/Pixtral, more Groq/Together/Fireworks/Cohere, Claude 3.5 Haiku). Bridge guides and pricing guide expanded with FAQs.

  6. Catalog refresh: re-verified rates across the board, added GPT-5 Nano, Gemini 2.0 Flash family, DeepSeek Chat/Reasoner, Grok 4 Fast, Mistral Medium 3, more Groq hosts, plus Cohere, Together AI, and Fireworks providers.

  7. Price sync: 7 model(s) updated (deepseek/deepseek-v4-pro, xai/grok-4, xai/grok-3, xai/grok-3-mini, mistral/mistral-small, mistral/codestral, mistral/ministral-8b). Official docs first; LiteLLM only for SPA gaps.

  8. Expanded catalog: o3-mini, Claude Opus 4.6, Gemini 3 Flash / Flash-Lite, Grok 3 family, Codestral, Ministral, Llama 4 Scout, Qwen3 on Groq.

  9. Initial curated catalog: OpenAI, Anthropic, Google, DeepSeek, xAI, Mistral, Groq with lastVerified + sourceUrl.