Spec updates
Changelog — what we've updated
We curate the catalog manually — every spec is regularly cross-checked against official provider documentation. This page shows what was reviewed and when.
May 2026
- anthropic/claude-haiku-4.52026-05-25
Fastest Claude — classification, routing, simple agents at mini-tier prices.
- anthropic/claude-opus-4.62026-05-25
Anthropic's premium tier for the hardest reasoning and coding tasks.
- anthropic/claude-sonnet-4.62026-05-25
Anthropic's workhorse: top-tier coding and agentic, fair pricing.
- deepseek/deepseek-v32026-05-25
DeepSeek-V3 — MoE model, impressive coding quality for very little money.
- google/gemini-3-flash2026-05-25
Fast, cheap Gemini — 1M context, fully multimodal.
- google/gemini-3-pro2026-05-25
Google's flagship: 2M token context, native video and audio input.
- google/gemini-3.1-flash-image-preview2026-05-25
Google's multimodal image-generation model — image output straight from the prompt.
- meta/llama-3.3-70b2026-05-25
Meta's open-weight workhorse — cheap and solid for standard tasks.
- mistral/mistral-large-22026-05-25
Mistral's flagship — EU-hosted, strong on multilingual generation.
- openai/gpt-5.42026-05-25
OpenAI's new flagship — agentic workloads and deep reasoning chains.
- openai/gpt-5.4-mini2026-05-25
GPT-5.4's smaller sibling — cheaper, faster, built for volume.
- openai/gpt-image-12026-05-25
OpenAI's current image-generation model — precise prompt following, text-in-image.
- openai/text-embedding-3-large2026-05-25
OpenAI's large embedding model — 3072-dim, very strong semantic search.
- openai/text-embedding-3-small2026-05-25
OpenAI's small embedding model — 1536-dim, very cheap, broadly applicable.
- xai/grok-42026-05-25
xAI's flagship with live X (Twitter) data access and a reasoning mode.