Anthropic has introduced mid-conversation system messages for the Claude API, allowing developers to append system instructions mid-conversation without invalidating the prompt cache. The feature is a…
Anthropic's Claude Sonnet 5, priced at $2 per million input tokens through August 31, became the default model for Free and Pro plan users on June 30, intensifying the AI pricing war. The company also…
Arize and Fireworks tested 10 AI models on 40 real agent tasks across 2,400 runs, finding that the open-source model gpt-oss-120b had the lowest cost per successful task at $0.054 despite a 33% pass r…
GitHub Copilot Business and Enterprise users can now see their AI credit consumption per billing cycle, a feature shipped July 20, 2026, that reveals actual usage since the June 1 shift to metered bil…
Agent Swarm measured a 99.2% cost reduction by using a single script instead of 26 individual tool calls, cutting context from ~815,000 tokens to ~6,450 tokens and cost from ~$2.44 to ~$0.02 in a live…
Simon Willison's informal benchmark asking AI models to generate an SVG of a pelican riding a bicycle has become a widely discussed test for large language models. A new experiment tested 1,008 SVGs a…
Kimi K3, a 2.8T parameter model from Moonshot AI, scores an Elo of 1543 on the AA-Briefcase benchmark, second only to Claude Fable 5's 1574, but costs $10.57 per task and averages 56.4 minutes per tas…
Google has deprecated and ignored temperature, top_p, and top_k parameters in its latest Gemini 3.6 Flash and 3.5 Flash-Lite models, joining OpenAI and Anthropic in removing fine-grained sampling cont…
Prompt design can silently multiply an LLM API bill by six times, according to a cost analysis using Claude Sonnet 5 pricing. The analysis shows that output tokens cost roughly 5x more per token than …
OpenAI released GPT-5.6 Sol, Terra, and Luna on July 9 with three API-level breaking changes that require immediate fixes for production tool-calling code. Parallel tool dispatch is now on by default,…
Claude Fable 5 is stylistically closest to Kimi K3 with a blend score of 64.5%, according to a model comparison analysis. The next closest matches are Claude Opus 4.8 at 60.0% and Claude Sonnet 5 at 5…
Ramp has launched Ramp Router, a model-routing system that selects the optimal AI model for each of over 100 use cases, cutting the company's LLM costs by 30% while improving feature speed and accurac…
ENLIL runs up to 9 large language models simultaneously in complete isolation, then synthesizes their independent responses into a single signed output called a Decree. The architecture uses async par…
Moonshot AI released Kimi K3 on July 16, a 2.8-trillion-parameter open-weight model that beats Claude Fable 5 and GPT-5.6 Sol on specific benchmarks, including a Writing Elo score of 2,840 versus Fabl…
Anthropic made Claude Sonnet 5 the default model for all Free and Pro users on June 30 at $2 per million input tokens and $10 per million output, half the price of Opus 4.8, while performing at Opus l…
AWS added Claude Sonnet 5 and the full GPT-5.6 family to its agentic IDE Kiro in July 2026, replacing Amazon Q Developer and enforcing a spec-driven development workflow that requires formal requireme…
A developer's analysis of coding agent costs reveals a 63× price spread across models, from $19/month for Qwen3.5-Flash to $1,200/month for GPT-5.6 Sol, based on a fixed workload of 90M input and 25M …
Anthropic released Claude Sonnet 5 on June 30, 2026, targeting coding, agents, and professional work. A developer recommends isolating the model behind a provider contract using a generic Event type a…
OpenAI launched GPT-5.6 as a three-model family — Sol, Terra, and Luna — with Terra performing above Anthropic's Fable tier at half the output tokens and a quarter of the cost. The model introduces an…
Harvey LAB-AA, a new benchmark from Artificial Analysis evaluating AI agents on real-world legal work across 24 practice areas, shows Claude Fable 5 (max, with Opus 4.8 fallback) leading with a 14.2% …