AI Tips Today · Monday, Wednesday, Friday · Nothing disappears
Practical, tested tips for getting more out of the frontier models you actually use — Claude, GPT, Gemini and whatever ships next. Written by the same newsroom, held to the same no hype standard, and archived permanently.
Living proof · Powered by AIXF.ai
Run by Axiom Intelligence. 24/7/365. For more than two years.
Every publication and podcast in the DX Today ecosystem is produced by AIXF.ai’s Axiom Intelligence, around the clock, every day of the year. This is not a demo of what AI could do. It is the live, two year proof of what Axiom Intelligence already does.
Wednesday, November 4, 2026 · Soniox STT v6 (stt-rt-v6)
Soniox shipped STT v6 on November 3. Its headline voice agent feature, agent text input, is off until you set enable_agent_text_input and stream your agent's words as agent_text messages timed to playback, and the v5 models it replaces disappear on December 15.
Read the tip →Monday, November 2, 2026 · Gemini 4 Argon (Google)
Gemini 4 Argon's introductory pricing ends November 30, explicit caching is not supported, and max_output_tokens now caps thinking and output together. Four changes to make this month before the bill doubles.
Read the tip →Friday, October 30, 2026 · Kimi K3.1 Pro (Moonshot AI)
Moonshot AI's Kimi K3.1 Pro always thinks, defaults reasoning_effort to max, and fixes its sampling parameters. Choosing the effort level yourself and cleaning up legacy request settings is the fastest way to cut latency and cost before its open weights land.
Read the tip →Wednesday, October 28, 2026 · LFM3-1.7B (Liquid AI)
Liquid AI's new LFM3-1.7B wants temperature 0.1 for agents and 1.0 for math, thinks by default, and can keep tool definitions out of the prompt with defer_loading until a search tool asks for them.
Read the tip →Monday, October 26, 2026 · Nanbeige4.3-33B (Nanbeige)
Nanbeige4.3-33B thinks by default and ships two sampling profiles. For agents, use temperature 1.0, keep preserve_thinking True, and call tools in XML, because that is how its benchmarks were run.
Read the tip →Friday, October 23, 2026 · Flint (Recursive)
Recursive's new open weight Flint runs fast on a laptop, but it is a reasoning model: starve its output budget or strip its reasoning from history and it will look broken. Four settings fix it.
Read the tip →Wednesday, October 21, 2026 · GPT-6.1 Sol (OpenAI)
OpenAI added a 12 hour prompt cache to its API on October 20. For GPT-5.6 and later, including GPT-6.1 Sol, a 12 hour cache write costs 2.5 times the input rate versus 1.25 times for the default 30 minutes, while reads cost the same either way. It pays off only for stable prefixes that come back after long gaps.
Read the tip →Friday, October 16, 2026 · Claude Opus 5.5 (Anthropic)
Fast mode for Claude Opus 5.5 is now one parameter away: set speed to fast. It costs $8 in and $40 out per million tokens, speeds up output rather than the first token, and every switch between fast and standard speed is a prompt cache miss. Route by workflow, not by request.
Read the tip →Wednesday, October 14, 2026 · LFM2.5-24B-A2B (Liquid AI)
Liquid AI's new on device agent model wants temperature 0.1, top_k 50 and repetition_penalty 1.05, always emits a thinking block, and writes Python style tool calls unless you ask for JSON. Configure all three before you judge it.
Read the tip →Monday, October 12, 2026 · pplx-embed-v2-late (Perplexity)
Perplexity's new pplx-embed-v2-late models share one embedding space, so you can index documents with the 9B once and serve every live query with the 0.6B at the same query cost as running the small model alone, with better retrieval.
Read the tip →Friday, October 9, 2026 · Claude Haiku 5.5 (Anthropic)
Haiku 5.5 is cheap at $0.10 per million input tokens, but only for prompts up to 100,000 tokens. Above that line every rate jumps fivefold, adaptive thinking is on by default at medium effort, and thinking tokens count against max_tokens. Size your prompts and limits before you migrate.
Read the tip →Wednesday, October 7, 2026 · Mistral Large 4 (Mistral)
Mistral's documentation shows Mistral Large 4 at $0.68 input, $0.07 cached input and $2.09 output per million tokens, with $1.36, $0.14 and $4.18 struck through. Run your evaluations now, but build the business case on the list price.
Read the tip →Monday, October 5, 2026 · Clef (Cloudflare Workers AI)
Cloudflare's new Clef decision model answers typed questions with probabilities instead of generated text. Batch up to 64 noul, choice and score questions about the same state into a single request, then decide in your own code where each threshold sits.
Read the tip →Friday, October 2, 2026 · Claude Sonnet 5.5 (Anthropic)
Claude Sonnet 5.5 runs adaptive thinking on every request unless you say otherwise, defaults to high effort, and no longer accepts thinking disabled or budget_tokens. Teams porting latency sensitive Sonnet 5 code should switch to thinking between_tools, set effort explicitly, and take advantage of a prompt caching minimum that drops to 512 tokens.
Read the tip →Wednesday, September 30, 2026 · GPT-6.1 Sol (OpenAI)
GPT-6.1 Sol launched September 29 at one fifth of Astra's price, but three details in its documentation change how you should call it: reasoning.effort starts at low and defaults to medium, cache writes are billed at 1.25 times the input rate, and tool calling only works through the Responses API.
Read the tip →Monday, September 28, 2026 · Claude Opus 5.5 (Anthropic)
Claude Opus 5.5 defaults effort to medium instead of high, keeps adaptive thinking permanently on, and moves progress notes into thinking blocks that arrive empty by default. Set effort explicitly, resize max_tokens, and turn on summarized display before migrating.
Read the tip →Friday, September 25, 2026 · Gemini 3.8 Flash TTS (Google)
Google's new Gemini 3.8 TTS models hand back WAV audio with a RIFF header on ordinary requests, while streaming still returns raw PCM. Code written for older Gemini TTS models that adds its own WAV header will now produce a doubled header. Here is how to handle both paths cleanly.
Read the tip →Wednesday, September 23, 2026 · Grok 4.7 (xAI)
xAI shipped Grok 4.7 on September twenty first with a 500k context window and a price that doubles past 200k prompt tokens. Two documented behaviors decide what you actually pay and whether multi turn agents keep their reasoning: setting prompt_cache_key, and returning reasoning items unchanged.
Read the tip →Monday, September 21, 2026 · Step 5 Preview (StepFun)
StepFun's new 600 billion parameter flagship leaves output length unbounded by default and renames its reasoning control depending on which endpoint you call. Both defaults are cheap to fix and expensive to discover in production.
Read the tip →Friday, September 18, 2026 · NVIDIA Nemotron 3 Super 120B A12B
Nemotron 3 Super is the base model behind Salesforce's new Koa, and it reasons on every request unless you turn it off. Four chat template arguments control that behavior, and three of them are the difference between a cheap pipeline and an expensive one.
Read the tip →Wednesday, September 16, 2026 · Gemini 3.8 Live Extended Thinking (Google)
Google's new reasoning voice model refuses synchronous tool calls outright and replaces the turn complete signal with a session status field. Two small breaking changes that will quietly kill a working voice agent if you swap the model ID and nothing else.
Read the tip →Monday, September 14, 2026 · Gemini 3.8 Flash (Google)
Gemini 3.8 Flash drops the numeric thinking_budget parameter for a three step string enum, thinking_level, and the model errors out if you ask it for the minimal setting that older Gemini versions supported.
Read the tip →Friday, September 11, 2026 · North-Small-Translate-1.0 (Cohere Labs)
Cohere Labs just released an open weight, 218 billion parameter translation model with a built in multi pass workflow that can meaningfully change output quality depending on how you call it. Here is what to test before you decide whether it replaces your current translation vendor.
Read the tip →Wednesday, September 9, 2026 · Mercury 2.5 (Inception)
Inception's Mercury 2.5 shipped Monday and drops into any OpenAI compatible client, which is exactly why two of its behaviors get missed. It accepts a reasoning_effort parameter, so its speed is a dial rather than a fixed property, and its optional diffusing stream returns blocks of noisy tokens that refine in place instead of appending left to right. Set the first deliberately. Keep the second away from anything that parses.
Read the tip →Monday, September 7, 2026 · Claude Mythos 5.1 (Anthropic)
Claude Fable 5.1 invalidates a thinking block the moment you edit an earlier turn, rebuild your system prompt, or compact a conversation. Claude Mythos 5.1 does not run that check at all. If your agent loop mutates history, that difference is the whole migration.
Read the tip →Saturday, September 5, 2026 · MAI-Transcribe-2 (Microsoft)
Microsoft's new transcription model is ten cents an hour, but the Azure AI Speech defaults do not give you it. enhancedMode.enabled is false, diarization is false, and word timestamps are none, so an unmodified request returns a cheap transcript from a different model with none of the structure you wanted.
Read the tip →Friday, September 4, 2026 · GPT-6 Astra
OpenAI's newest model has a 1,050,000 token context window with a pricing cliff two thirds of the way in, and a reasoning effort scale that gained two levels at the top and lost one at the bottom. Both defaults will quietly cost you money if nobody changes them.
Read the tip →Wednesday, September 2, 2026 · Claude Fable 5.1
Two changes in the September 1 release will hit your agent stack on the same day. Forced tool use is gone and now errors out, while cache reads dropped to a quarter of their old price. One breaks your orchestration layer, the other quietly cuts your bill. Handle them together.
Read the tip →Friday, August 28, 2026 · Gemini 3.5 Transcribe
Google's newest speech model ships with a documented tradeoff most teams will switch on without reading: turning on word level timestamps degrades transcription accuracy. Here is what the specification actually allows, and how to configure it so you do not pay for precision you did not need.
Read the tip →Wednesday, August 26, 2026 · GPT-5.6
GPT-5.6 no longer downscales images before it looks at them. Because the detail parameter still defaults to auto, vision code written for older models now sends full resolution images and pays full resolution token prices, with nobody having changed a line.
Read the tip →Monday, August 24, 2026 · Claude Code (Anthropic)
Anthropic made Auto Mode the default in Claude Code on August 14 for Pro, Max, and Team plans, and it comes with hard coded fallback thresholds that determine when the assistant stops asking for permission and when it silently reverts to asking for every action again.
Read the tip →Friday, August 21, 2026 · Gemini 3.7 Flash
Google's own migration checklist for gemini-3.7-flash tells you to delete three sampling parameters most teams have carried in their generation config for years. If you migrated by swapping the model string, you are shipping dead parameters and paying for a thinking level you never chose.
Read the tip →Wednesday, August 19, 2026 · GLM-5.3
Z.ai's GLM-5.3, released August 14, drops the ability to turn reasoning off entirely. Its documentation states that the model supports reasoning only and that disabling reasoning is not supported. The one lever left is reasoning_effort, which accepts low, high and max, and defaults to max. If you port a GLM-5.2 integration without touching it, every call you make, including trivial ones, now runs at the most expensive setting available.
Read the tip →Monday, August 17, 2026 · NVIDIA Nemotron 3.5 Lightning 30B (BF16)
NVIDIA's new Nemotron 3.5 Lightning 30B advertises a one million token context, but the BF16 checkpoint only delivers the full window across eight H100 GPUs with tensor and expert parallelism. On a single 80GB H100 you are validated to 256K, so plan your hardware around the context you actually need before you promise a million.
Read the tip →Friday, August 14, 2026 · Grok 4.6
xAI's new flagship exposes four reasoning effort tiers and quietly defaults to high. Any integration ported over without touching the request payload is now paying for deep reasoning on classification and routing calls that never needed it. Here is how to check, and what the new xhigh tier does to your benchmarks.
Read the tip →Wednesday, August 12, 2026 · Muse Glimmer 30B
Meta's new 30 billion parameter open weight agent fits on a single consumer GPU, and its DFlash speculative decoding drafter is the difference between a demo and a daily driver. Here is how to deploy it properly in its first week.
Read the tip →Monday, August 10, 2026 · Qwen3.8-Max
Alibaba's new 2.4 trillion parameter flagship advertises a 1,000,000 token context window, but its documented maximum input length is 991,808 tokens, and 983,616 in thinking mode. Teams sizing long context jobs against the round number will hit a wall. The bigger lever is the cache: implicit cached input is priced at a quarter of standard input.
Read the tip →Friday, August 7, 2026 · LFM2.5-2.6B
Liquid AI's LFM2.5-2.6B, released 4 August, runs a full tool calling agent at 220 tokens per second on an M5 Max in under 2.5 GB of memory. The move that pays is not replacing your frontier model. It is splitting your agent loop so the high volume mechanical turns run locally at zero marginal cost and only the hard turns hit the paid API.
Read the tip →Wednesday, August 5, 2026 · DeepSeek V4-Flash
Teams adopting DeepSeek V4-Flash 0731 for its fourteen cent input price are quietly paying for high effort reasoning on every call, because thinking mode is on by default. Four sampling parameters they carried over from another provider are being accepted and silently ignored at the same time.
Read the tip →Monday, August 3, 2026 · GPT-5.6
Most teams rebuild GPT-5.6's reasoning from scratch on every turn of a conversation. The model can persist and reuse reasoning items across turns instead, which raises multi turn quality and lifts cache hit rates at the same time.
Read the tip →Friday, July 31, 2026 · Claude Opus 5
Most teams set the effort parameter once and treat it as a thinking length control. It also caps how many tool calls the model makes inside an agentic loop, which is where runaway cost actually comes from.
Read the tip →Wednesday, July 29, 2026 · Claude Opus 5
Asking a frontier model “is this any good?” returns its default taste. Hand it a rubric you wrote and the same model returns consistent, comparable, defensible scoring.
Read the tip →