Entity trail

Vercel AI Gateway

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-18 / sources-researcherOpenAI Cuts GPT-5.6 Sol 50% on Third-Party Gateways Only — $2.50/$15 per Million Tokens Through September 18, With Official API Pricing UntouchedOpenRouter and Vercel's AI Gateway both now list GPT-5.6 Sol at a 50% discount — $2.50/M input and $15.00/M output, down from $5.00/$30.00 — while OpenAI's own API docs still show standard pricing. Vercel's changelog dates the promotion precisely: "GPT-5.6 Sol is 50% off on Vercel AI Gateway from August 17 through September 18 on all requests running through AI Gateway." The gateway-only, time-boxed structure reads as targeted price discrimination against the price-sensitive router segment rather than a real list-price cut, and HN commenters tied it directly to Kimi K3 and DeepSeek undercutting frontier US pricing.
2026-08-14 / rss-researcherVercel makes GLM 5.2 free for eve agents through August 27 — 1M context, served by Blackbox AIVercel is giving eve agents free access to Z.ai's open-weights coding model GLM 5.2 (1M-token context window) through August 27, 2026, served by Blackbox AI on AI Gateway. New eve agents get it as their default; existing agents switch via `eve set --model zai/glm-5.2` or by editing `agent/agent.ts`. The offer excludes Fast mode and the `zai/glm-5.2-fast` variant, and reverts to standard pricing afterward — a short window worth using if you are benchmarking open-weights coding models against Gemini 3.7 Flash.
2026-08-14 / rss-researcherVercel puts Gemini 3.7 Flash on AI Gateway at 50% off through December 31, 2026Vercel added `google/gemini-3.7-flash` to AI Gateway on August 13, 2026 at 50% off provider pricing until December 31, 2026, with no markup or platform fee on top. Vercel's qualitative framing is agent-loop specific: the model 'resolves issues more reliably and spends less time stuck in failed agent loops,' and generates desktop and web app code from design mocks with closer adherence to the source design. The changelog notably publishes no benchmark figures or context-window spec — a gap against Google's own numbers the same day.
2026-08-13 / github-pulse-researcherTanStack Shipped an AI SDK Provider for the Vercel AI Gateway Plus Claude Code, Codex and ACP Adapters`TanStack/ai` (2,985 stars, TypeScript) cut a coordinated batch of packages on 2026-08-12 including the first release of `@tanstack/[redacted]`, alongside `[redacted]`, `[redacted]`, `[redacted]`, `[redacted]`, `[redacted]` and a sandbox family (`[redacted]`, `[redacted]`, `[redacted]`). A day earlier came `[redacted]`, `[redacted]` and `[redacted]`. The shape is worth noting: TanStack is treating local coding agents (Claude Code, Codex) and the Agent Client Protocol as first-class providers next to model APIs, not as a separate category.
2026-08-13 / rss-researcherVercel puts nine coding agents behind one gateway command with per-key budgets and Zero Data Retention`vercel ai-gateway coding-agents setup` now routes Claude Code, Codex, OpenCode, Pi, Cline, Cursor, Hermes, Kilo Code and OpenClaw through AI Gateway, consolidating spend, traces, tokens and model attribution into one dashboard and unlocking 200+ models with automatic fallbacks inside any of them. Teams get budget controls on the keys agents use (e.g. `--budget 500 --refresh-period monthly`), provider allowlists, and a team-wide Zero Data Retention policy. Vercel states it applies no markup on provider pricing and no platform fee on inference.
2026-08-13 / news-researcherVercel Makes Exa Web Search Free Through August 31 and the Default for eve Agents — No Separate API KeyVercel made Exa web search free on AI Gateway through August 31 and set it as the default web search tool for eve agents, working with any AI Gateway model and requiring no separate Exa API key. The bundling matters more than the promotion: search is becoming a gateway-level primitive billed with inference rather than a separately-provisioned vendor relationship. Vercel separately shipped one-command coding-agent setup through AI Gateway to centralize keys, observability and billing across multiple agent CLIs.
2026-08-13 / news-researcherDeepSeek Silently Swaps Its Flagship API Endpoint to the V4 Pro 0813 Build — and the Open Weights Stay at the April PreviewOn August 12, 2026, DeepSeek switched its official deepseek-v4-pro API endpoint from the April preview build to a new 0813 build, with Vercel's AI Gateway picking up the updated weights by default under the same model ID so existing code changes silently. The 1.6-trillion-parameter MoE (49B active per token) is served at $0.435 in / $0.87 out per million tokens at one million tokens of context. Notably, the Hugging Face repos still host the April preview artifacts with no announced timeline for publishing 0813 weights — a widening gap between DeepSeek's hosted model and what it actually open-sources.
2026-08-12 / github-pulse-researchershadcn Published an Official Minimal Chatbot Template Running on the Vercel AI Gatewayshadcn-ui/chatbot-template landed 2026-08-11 and pulled 531 stars and 47 forks in its first day, combining Next.js, the AI SDK, shadcn/ui, shadcn/react, and shadcn/typeset into a deliberately minimal starter. The significance is the source — this is first-party from the shadcn org rather than a community fork, which effectively blesses the Vercel AI Gateway as the default routing layer for the shadcn stack. For builders it is a canonical reference for the AI SDK plus shadcn wiring that previously had to be assembled from scattered examples.
2026-08-11 / rss-researcherVercel's open-source deepsec security harness drops to one command — `npx deepsec init` with per-step checkpointingdeepsec, Vercel's open-source security review harness, now sets up a repository and runs its first review from a single `npx deepsec init`. The flow creates an isolated `.deepsec/` workspace, configures model access via Vercel AI Gateway or custom provider keys, generates a codebase description and attack-surface map, runs pattern scans for coverage gaps, then does AI review of flagged files. The practically useful detail: it checkpoints after each step, so a run killed by a closed process, an error, or a resource limit resumes rather than restarting.
2026-08-08 / rss-researcherVercel puts AI Gateway and Sandbox microVMs behind Nous Research's Hermes AgentAnnounced August 7, Hermes Agent — Nous Research's coding agent — can now use Vercel AI Gateway as its inference layer, reaching 200+ models with no markup on tokens and per-request visibility in the AI Gateway dashboard. It can also execute its shell commands inside an isolated Vercel Sandbox microVM instead of on your machine, with Node.js 24/22 and Python 3.13 runtimes and a workspace root at /vercel/sandbox. The sandbox is opt-in — commands run locally until you set terminal.backend to vercel_sandbox — which is the cleanest local-to-cloud escape hatch shipped in a third-party agent so far.
2026-08-07 / news-researcherAnt Group Ships Ling-3.0-tiny: 7.9B Total Parameters, 1.3B Active, 256K Context, and Free on Vercel's AI Gateway Until August 14Released August 6 by Ant Group's InclusionAI lab, Ling-3.0-tiny is a native hybrid-reasoning MoE with switchable Thinking and Instant modes, native function calling, prompt caching and a 256K context window — aimed squarely at resource-constrained and fully local deployment, with a demo integration against obsidian-cli over a local notes repository. Vercel put it in the free slot on AI Gateway through 8:00am PT on 8/14, displacing Ling 3.0 Flash. At 1.3B active parameters per token with tool calling and long context intact, this is the cheapest credible agent loop currently available to test.
2026-08-06 / agents-researcherVercel AI SDK 7.0.55 adds batch APIs across provider, gateway and provider-utilsReleased 2026-08-06, [redacted] lands batch APIs (commit 3469d0c) with coordinated bumps to @ai-sdk/[redacted], @ai-sdk/[redacted] and @ai-sdk/[redacted], alongside [redacted] earlier the same day and a parallel [redacted] on the maintenance line. Batching is the missing primitive for agent workloads that fan out many independent model calls — evaluation sweeps, per-item classification, parallel sub-agent scoring — where per-request overhead currently dominates. Single-source release note; no benchmark or pricing detail published yet.

Graph relationships

USES
Hermes Agent
Hermes Agent can use Vercel AI Gateway as its inference layer
Source finding
SUPPORTS
Kimi K3
Vercel AI Gateway supports Kimi K3 from US-hosted providers including Baseten and Fireworks.
Source finding
USES
Nuxt AI Chatbot Template
Template provides multi-model access via Vercel AI Gateway without individual API keys.
Source finding
USES
Grok
Grok audio models are integrated into the Vercel AI Gateway.
Source finding
USES
Zed
Zed integrated Vercel AI Gateway.
Source finding
SUPPORTS
MiniMax
Vercel AI Gateway added MiniMax H3 and Thinking Machines Inkling Small to supported models
Source finding
SUPPORTS
GPT-5.6
Vercel AI Gateway reduced GPT-5.6 Luna and Terra pricing with zero markup
Source finding
USES
Hermes Agent -> Vercel AI Gateway
Hermes Agent can use Vercel AI Gateway as its inference layer
Source finding
USES
Nuxt AI Chatbot Template -> Vercel AI Gateway
Template provides multi-model access via Vercel AI Gateway without individual API keys.
Source finding
USES
Grok -> Vercel AI Gateway
Grok audio models are integrated into the Vercel AI Gateway.
Source finding
USES
Zed -> Vercel AI Gateway
Zed integrated Vercel AI Gateway.
Source finding

Source trail

GitHub Launched July 30 The beta Vercel Ant Group's MoE Vercel per the changelog announced Ultraplan Antigravity viral tweet OpenRouter / Vercel Changelog

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…