Latest model releases, feature announcements, and pricing updates. Check back regularly to stay informed about the latest developments in AI models.
Subscribe to the feedJuly 24, 2026
Anthropic ships a flagship built for agentic coding and business workflows at $5/$25 per million tokens, which is half the price of Fable 5. It has a 1M token context window, and it now leads the SWE-Bench Verified leaderboard at 97%.
July 21, 2026
Google ships a stronger agentic workhorse at $1.50/$7.50 per million tokens and a high-throughput Flash-Lite tier at $0.30/$2.50, both with 1M-token context windows.
July 18, 2026
Added Terminal-Bench and HLE benchmarks for more comprehensive model evaluation.
July 18, 2026
Intro pricing extended through August 31, 2026: $2/$10 per million tokens (input/output).
July 16, 2026
Moonshot AI launches its 2.8T-parameter flagship with 1M token context, native vision, and always-on reasoning. Open weights promised for late July.
July 16, 2026
xAI's new flagship pairs strong terminal and coding performance with real-time access to X (Twitter) data, at a mid-tier $2/$6 per million tokens with a 500K context window.
July 15, 2026
Mira Murati's Thinking Machines Lab ships its first model: a 975B open-weights multimodal flagship under Apache 2.0, available on Hugging Face.
July 9, 2026
OpenAI ships three tiers at once: Sol (flagship, $5/$30 per million tokens), Terra (balanced, $2.50/$15), and Luna (budget, $1/$6), all with a 1.05M token context window.
July 9, 2026
Meta's first paid, closed-weights model after the open Llama era: 1M token context, an exceptional 256K max output, and aggressive $1.25/$4.25 pricing aimed at agent workloads.
June 30, 2026
New Sonnet model with autonomous planning, multi-step tool use, and 1M token context. Available at intro pricing.
June 9, 2026
Anthropic launches its most capable reasoning model with 1M token context and state-of-the-art performance on SWE-Bench. Access was paused June 12 under a US export directive and restored July 1.
June 5, 2026
Input price reduced from $15 to $5 per million tokens. Output price halved from $60 to $25.
May 19, 2026
Google's speed tier announced at I/O 2026 punches above its weight: it beats Gemini 3.1 Pro on some coding benchmarks at about 25% lower cost.
April 28, 2026
Mistral released an open-weight, multimodal model for coding and agent work. It has a 256K-token context window and is available through the API or for self-hosting.