Gateways
Current Answer
No editorial synthesis yet — the evidence below is collected automatically from source labels. A current answer lands here once an editor approves one.
Evidence
AI Gateway can route private model endpoints through the same APIs, agent connections, logs, and reporting as catalog models, with optional catalog-model fallback.
Vercel increased Token Pass credits from $80 to $150 per month at the same $30 team price. The Early Access add-on covers selected models through AI Gateway, with distinct behavior when credits run out.
Vercel’s AI Gateway adds Gemini Decision 1 for classification, routing, and ranking tasks, with input support that varies by API.
Vercel AI Gateway now exposes MiniMax H3 Image generation and editing through one API key, with custom output sizes and an OpenAI-compatible images API.
AI Gateway now exposes DeepSeek Search and Fetch to tool-calling models with one gateway key. Each costs $0.75 per 1,000 billable requests, with model tokens billed separately.
AI Gateway now applies Token Pass credit to standard API keys and OIDC, with fallback to team credits after exhaustion; this changes credential and billing behavior for Pro teams.
Mercor describes using gateway failover, scoped model keys, and narrow agent permissions to handle bursty workloads and internal agents. Its reported batch times fell from over 12 hours to 2–3 hours.
Vercel AI Gateway Virtual Models let agents use a stable task ID while teams change models, routing, and compliance settings centrally. Run evals against a candidate before switching a production task.
AI Gateway Virtual Models now let apps and coding agents use a task ID for centrally managed model settings, routing, and spend tags. They can also set options an agent may not expose directly.
Vercel AI Gateway adds 14 ElevenLabs models across transcription, realtime voice, music, effects, and dialogue under one API key, with shared cost and trace views. Realtime models use semantic VAD, not server VAD.
Interfaze’s stack shows one way to run checkable AI workloads: isolated code execution, provider failover, durable workflows, and version-specific deployments.
Vercel AI Gateway now exposes Mercury 3 to coding agents, pairing diffusion-based generation above 1,000 tokens per second with a 1M-token context window.
Vercel AI Gateway now exposes two Gemini 3.8 TTS models for multilingual speech, separating high-volume generation from prompt-driven voice design.
Vercel AI Gateway now exposes GPT-6 Sol for demanding coding runs and Luna for high-volume work, with unified usage tracking, retries, failover, and routing.
Jev is now callable through TypeSafe clients, HTTP, or Vercel AI SDK, returning typed probabilistic decisions that agents can consume without parsing prose.
Agent requests often repeat most of their input, making KV-cache-aware routing a direct latency and cost lever for hosted coding-agent workloads.
OpenAI replaced opaque feedback-driven inference routing with explicit global optimization plus fast local guards, making latency, capacity, and failure behavior easier to reason about.
GLM 5.3 FlashX brings roughly 200 tokens-per-second serving to Vercel AI Gateway, offering a lower-wait option for coding-agent output and repeated tool loops.
Harbor can run Terminal-Bench and related evals in isolated Vercel microVMs, enabling parallel model comparisons without putting injected credentials inside each sandbox.
A three-engineer team consolidated model routing, long-running agent jobs, and deployment on Vercel while serving 100,000+ users. The case study shows where managed abstractions can remove operational work.
Tailscale tied model access and ephemeral agent sandboxes to network identity, without issuing keys to agents. It is a concrete pattern for combining gateways, access control, and isolated execution.
Tako Search gives any AI Gateway model current web and curated data through one AI SDK tool, without a separate account or key. The free window ends September 30.
DeepSeek V4.1 Flash brings vision, tool use, reasoning, and prompt caching to Vercel AI Gateway, with direct setup paths for Claude Code, Codex, and Cursor.
Vercel AI Gateway adds GPT Image 2.5 Flare for faster iteration and Sunburst for tighter composition control. Both support generation, reference-based edits, and transparent backgrounds.
Vercel AI Gateway now exposes GPT-6 Astra as openai/gpt-6-astra for code and coding-agent integrations, targeting long-running tasks that combine software, browser, and data work.
Vercel AI Gateway now serves the medical-focused Ling 3.0 Flash Sante free through October 4. Use its free-only model ID to prevent requests from converting to paid usage afterward.
GLM-5.3 is half-price through September 8 via a temporary DigitalOcean-only model ID. Keep the standard ID in durable agent configs if you need fallback after the offer.
x402 servers can perform work before payment settlement, leaving a double-spend window. Builders should settle first or accept explicit counterparty risk until stronger schemes mature.
AWS is separating agent payment policy from model execution: AgentCore handles wallets and limits, while WAF meters bot access. The useful pattern is deterministic spend control at the edge.
A wallet-equipped agent crossed paywalls and completed paid email and phone actions under a spending cap. The engineering lesson is to enforce budgets in the wallet, not in prompts.
Claude Fable 5.1 reaches Vercel AI Gateway with ordered fallbacks for classifier refusals, but its 30-day retention policy rules out zero-data-retention workloads.
Vercel’s gateway now exposes a pinned Qwen snapshot aimed at larger coding projects and longer agent runs, with a dated model ID that prevents silent upgrades.
AI Gateway can now cap each user's aggregate spend across attributed API keys and app tokens, giving unattended coding agents a hard cost boundary.
Vercel is halving AI Gateway charges for MiniMax H3 and H3 Max through September 13; existing model IDs receive the discount without code changes.
Gemini 3.5 Transcribe adds batch and live WebSocket transcription to AI Gateway, with automatic language detection, 85+ languages, and custom vocabulary.
Muse Image is available through Vercel AI Gateway for both generation and instruction-based editing, including reference-image guidance through the AI SDK.
Vercel Connect gives agents runtime-minted, task-scoped credentials instead of stored provider tokens, adding per-user identity, revocation, audit logs, and usage visibility.
AI Gateway offers temporary free routes for MiniMax M3 and M2.7, but the -free model IDs hard-fail after September 6; standard IDs preserve provider fallback at normal rates.
Per-task model routing cut the demonstrated coding session’s cost from 44¢ to 14¢ with similar completion time, but builders still need workload-specific evals to validate quality.
GPT-5.6 Sol now costs less across Vercel AI Gateway tiers, with an additional 50% discount through September 18 and no model-ID change for existing agent setups.