Skip to content
➜NextOS

Vercel AI Gateway
in NextOS.

Included with every account: hosted models and web search with nothing to configure. Paste your own AI Gateway key to use it directly, with any of its 200+ models.

Use Vercel AI GatewayGet an API key

01Supported models

Every model
this plugin lists.

  • openai/gpt-oss-120b

    GPT-OSS 120B (open weight)

    131K contexttools

    Included - $0.10 / $0.50 per million tokens.

  • zai/glm-5.3-flash

    GLM 5.3 Flash

    1M contexttools

    Included - $0.15 / $0.50 per million tokens.

  • google/gemini-2.5-flash-lite

    Gemini 2.5 Flash Lite

    1M contexttools

    Included - $0.10 / $0.40 per million tokens. Native web search.

  • deepseek/deepseek-v4-flash

    DeepSeek V4 Flash

    1M contexttools

    Included - $0.13 / $0.26 per million tokens.

  • alibaba/qwen3.7-flash

    Qwen 3.7 Flash

    991K contexttools

    Included - $0.03 / $0.13 per million tokens (base tier).

  • nvidia/nemotron-3-nano-30b-a3b

    Nemotron 3 Nano 30B

    262K contexttools

    Included - $0.05 / $0.20 per million tokens.

  • openai/gpt-5-nano

    GPT-5 Nano

    400K contexttools

    Included - $0.05 / $0.40 per million tokens. Native web search.

  • inclusionai/ling-3.0-flash

    Ling 3.0 Flash

    256K contexttools

    Included - $0.02 / $0.06 per million tokens.

  • poolside/laguna-s-2.1-free

    Laguna S 2.1 (free, general purpose)

    256K contexttools

    Included - reasoning and tool calling, no cost against your plan.

  • inclusionai/ling-3.0-flash-sante

    Ling 3.0 Flash Sante (free, fast)

    256K contexttools

    Included - reasoning and tool calling, no cost against your plan.

  • inclusionai/ling-3.0-flash-fin

    Ling 3.0 Flash Fin (free, finance-tuned)

    256K contexttools

    Included - reasoning and tool calling, no cost against your plan.

  • inclusionai/ling-3.0-flash-vl

    Ling 3.0 Flash VL (free, vision)

    256K contexttools

    Included - reasoning, tool calling and vision, no cost against your plan.

  • google/gemini-2.5-flash

    Gemini 2.5 Flash

    1M contexttools

    $0.30 / $2.50 per million tokens. Native web search.

  • openai/gpt-5.4-mini

    GPT-5.4 Mini

    400K contexttools

    $0.75 / $4.50 per million tokens. Native web search.

  • meta/llama-4-maverick

    Llama 4 Maverick

    128K contexttools

    $0.24 / $0.97 per million tokens.

  • minimax/minimax-m3

    MiniMax M3

    512K contexttools

    $0.30 / $1.20 per million tokens.

02Bring your own key, or hosted

How you
pay for it.

Included on every plan, including Free, with nothing to configure - the account starts here. Paste your own AI Gateway key to use it directly, with any of its 200+ models.

  • Full tool calling - agents can use every app and MCP tool through this provider
  • Provider-hosted web search available as a per-agent option
  • No provider-hosted URL fetch

03Governance

The same controls
as every provider.

  • Restrict which providers and models a team may use at all - an allowed list on the org policy, enforced on every gateway call
  • Set a default model the whole workspace inherits, with per-agent pins for the job that needs a different one
  • Per-org and per-key budgets and rate limits, checked before a call reaches the provider
  • Guardrails (PII redaction, prompt-injection screening) applied to every request and response, regardless of provider
  • A full audit trail of governance and budget events, in the team's activity log

04Over the gateway

One endpoint,
OpenAI-compatible.

gateway — next.os
curl https://www.jonkum.in/api/v1/chat/completions \
  -H "Authorization: Bearer ngk_..." \
  -H "X-Provider-Key: your-vercel-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"vercel/openai/gpt-oss-120b","messages":[{"role":"user","content":"..."}]}'

Omit X-Provider-Key to run on the account's hosted allowance instead, where the plan supports it. See the gateway page for the full API.

05Every other provider

one plane · every provider · your key or ours

Run agents on Vercel AI Gateway.
Governed exactly like every other provider.

Set your defaultSee pricing