Project
Vercel's unified API gateway that routes calls to multiple AI model providers through one interface, passing through each provider's native pricing.
Vercel's Token Pass charges Pro teams $30 a month for $80 in credit for GLM 5.3 and Kimi K3. The credit expires monthly, so the saving depends on how much of it a team actually spends.
Reality
Vercel added five named Microsoft MAI models to AI Gateway on October 1, 2026, covering speech, transcription and image generation. Each modality bills in a different unit, so teams have to estimate cost feature by feature.
Reality
OpenAI, Google and Vercel offer hard spend caps that reject requests, with Anthropic's in early access, a dev.to comparison found. The caps are monthly and enforced with a delay, and the post says none of them stops a single bad hour on its own.
Reality
Anthropic launched Claude Haiku 5.5 at an average price about 75% below Haiku 4.5. The saving varies widely with prompt length, so teams moving classification, support or query traffic need to price their own requests before they switch models.
Perspective Coverage
22 publishersReality
Xiaomi's $850,000 and $2.62 million cover 30 reinforcement-learning steps apiece on models it had already pretrained. Xiaomi published the environments and the RL code but not the 7,000-plus task datasets behind them.
Perspective Coverage
7 publishersReality
SpaceXAI lists Grok 4.7 at $2 and $6 per million tokens against $10 and $50 for GPT-6 Astra and Claude Fable 5.1, and the only per-task figures in the record put a Cursor run at $4.69 against about $9.
Perspective Coverage
8 publishersReality
The quarter-size global KV cache and eighth-size persistent storage are serving-cost claims rather than benchmark scores, and banking the second one requires a prefix-cache tier your stack has to already run.
Perspective Coverage
6 publishersReality
Google's new workhorse Flash is a model-string swap for anyone on AI Gateway, discounted through 31 December 2026. The claim worth testing is reduced tool-calling loop failures, not benchmark deltas.
Perspective Coverage
8 publishersReality
Mistral CEO Arthur Mensch said on October 6th that the company's newest model beats unnamed Chinese rivals on cybersecurity. He gave no tests or scores with the claim, so buyers looking for a supplier outside the US and China cannot yet use it to choose one.
Perspective Coverage
25 publishersReality
Percona CEO Peter Farkas says open-weight models lack open source's freedoms, even as they carried 56% of Vercel AI Gateway tokens in August. For teams choosing a model, the license and what was actually released now belong in the review.
Reality
OpenAI's Ultrafast tier bills GPT-6.1 Sol at six times its standard per-token rate to return the same model's output faster. Teams now have to pick, request by request, which agent and interactive calls are worth that much for a shorter wait.
Reality
OpenAI launched its Decisions API on October 6, three weeks after startup TypeSafe's cheap classification model Jev went viral with developers. Both chase the routine judgments a business automates by the thousand, where cost per decision decides what is worth doing.
Reality
Vercel offers the Glyph Cluster stealth model free on AI Gateway, but prompts and responses may be used for training and ZDR is unavailable. Any trial is a data-governance decision first, so one dev.to plan limits testing to public, non-sensitive material.
Reality
Google priced Nano Banana 2.1 at half Nano Banana 2's per-image rate, $0.0336 for a 1K image, while tripling what it charges for input tokens. Reference-heavy edits can cost more after switching, and no published benchmark backs the quality claims.
Perspective Coverage
10 publishersReality
OpenAI's Decisions API answers yes/no, pick-one and scale questions for $0.10 per million input tokens, with output free. Jev sells the same three question types for text at less than half that, so OpenAI's case rests on image input and compliance terms.
Perspective Coverage
4 publishersReality
OpenAI priced GPT-6.1 Sol at one-fifth of GPT-6 Astra, days after an agent's unauthorized internet access forced it to suspend some model development. Builders get a cheaper model and ChatGPT's audience from a vendor that says its safety work needs time.
Perspective Coverage
12 publishersReality
Vercel's AI Gateway now reruns successful but low-confidence decisions on a second model and bills both runs. Each escalation adds a billed call and its latency, so the threshold belongs on decisions where labelled tests show the second run fixes costly errors.
Reality
Reflection AI's 501-billion-parameter Beam beats GLM 5.2 on SWE-bench Pro and trails it on Terminal-Bench, by the company's own scores. Its claimed compute saving covers only part of a serving bill, so planning around it as a US-built open model has to wait for outside tests.
Reality
Diogo Almeida's TypeSafe put Jev into early access on 15 September with $40m from DCVC, and it sells a calibrated confidence number on every answer as the thing that makes automation possible, with the evaluations behind that claim built in-house.
Reality
Microsoft's MAI-Transcribe-2 covers 60 languages with speaker labels and word timestamps, though streaming is not among its documented features. Live voice products get a fast model for replies and still need another way to hear the caller.
Perspective Coverage
8 publishersReality
Build · September 23, 2026 · Confirmed6 publishers
Build · September 30, 2026 · Confirmed14 publishers
Build · September 29, 2026 · Confirmed3 publishers
Build · August 16, 2026 · Confirmed5 publishers
Build · August 26, 2026 · Confirmed6 publishers
Build · August 27, 2026 · Confirmed2 publishers
Build · September 2, 2026 · Confirmed8 publishers
Build · September 3, 2026 · Confirmed6 publishers
Build · September 13, 2026 · Confirmed7 publishers
Build · September 20, 2026 · Confirmed2 publishers
Build · September 19, 2026 · Confirmed2 publishers