Token Gear by FreshToken · AI gateway

One gateway to the models your business runs on.

One OpenAI-compatible API in front of models served by several providers. The platform picks an eligible provider for each request, applies your keys’ limits and data constraints, and meters every request to the token against prepaid credit.

API base URL https://api.freshtoken.ai/v1
Chat completion
curl https://api.freshtoken.ai/v1/chat/completions \
  -H "Authorization: Bearer $FRESHTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "zai-org/glm-4-flash-250414", "messages": [{"role": "user", "content": "Hello"}]}'

The models on sale, at their current prices

From the live catalog, in US dollars per million tokens. You pay for the tokens each request uses, from prepaid credit.

See all models and prices →
ModelContextInput / 1M tokensOutput / 1M tokens
DeepSeek-V4-Prodeepseek-ai/deepseek-v4-pro1M tokens$1.7876296$3.57525921
DeepSeek-V4-Pro 0813 正式版deepseek-ai/deepseek-v4-pro-08131.02M tokens$0.66$1.98
DeepSeek-V4.1-Flashdeepseek-ai/deepseek-v4.1-flash1M tokens$0.15$0.60
DeepSeek-V4.1-Flash-1017deepseek-ai/deepseek-v4.1-flash-10171.02M tokens$0.14896913$0.59587653
MiniMax-M2.5minimax/minimax-m2.5200K tokens$0.31283518$1.25134072
MiniMax-M3minimax/minimax-m31M tokensfrom $0.31283518from $1.25134072

Signed in, the console’s Models page shows the prices your account pays.

Who Token Gear is for

Three ways in, depending on what you run. Each says what is available now and what is planned.

  • AI SaaS & integrators

    Build on one API

    Ship your product on one OpenAI-compatible API, and keep each request’s cost and record traceable.

    For builders →
  • Enterprise AI governance

    Govern AI use

    One gateway for your teams’ model calls, with keys, budgets, allow-lists and data constraints in one place.

    For enterprises →
  • Operators & cloud providers

    Run a model service

    Offer models from several providers under one price list, with procurement kept apart from what customers pay.

    For operators →

How a request is served

What the gateway does between your code and the model, on every request.

  1. Your application Your code, your SDK

    An OpenAI-compatible client, pointed at one base URL with one sk- key. An Idempotency-Key on each request makes a retry safe.

  2. Token Gear On every request
    1. Checks the key
    2. Applies limits and data constraints
    3. Picks an eligible deployment
    4. Meters tokens and the charge
  3. Providers Deployments of the model
    • Provider A: eligible
    • Provider B: eligible
    • Provider C: not eligible

    If Provider A fails before any output is sent, the request goes to Provider B.

An illustration of one request, not live traffic. The providers are examples; routing is the platform’s, and customers do not choose them. Routing and failover are invite-only for now.

What Token Gear does

Token Gear is offered by invitation, under an offline contract, while we finish testing it with real providers. Nothing here is generally available yet, and each capability says where it stands. How keys and data are handled →

Invite-only

Unified model API

One OpenAI-compatible endpoint for /v1/chat/completions, /v1/completions, /v1/embeddings and a subset of /v1/responses, streamed over SSE. Keep your SDK and change the base URL; an Idempotency-Key on each request keeps a retry from being charged twice.

Compatibility matrix →
Invite-only

Platform-managed routing

For each request the platform picks an eligible deployment of the model — by version, capability, data constraints and cost — and fails over before any output is sent. Customers do not choose or pin providers; each request carries the context it needs.

How requests are served →
Invite-only

Keys, budgets and allow-lists

Per-key budgets, rate limits and model allow-lists, set in the console or the API. Keys are shown once and stored as hashes.

Budgets and limits →
Invite-only

Prepaid metering

The most a request can cost is reserved before it goes upstream and settled to the token when it ends; a retry with the same Idempotency-Key is not charged twice. The console shows usage and charges as they happen.

Retries and billing →

From sign-up to your first request

Every public endpoint lives under /v1.

  1. Sign up

    Create an account, personal or for your organization.

  2. Sign a contract

    Contact FreshToken to sign an offline contract; an administrator then adds your credit. There is no self-service top-up.

  3. Get your API key

    Create a key starting with sk-. It is shown once.

  4. Send a request

    Change your SDK’s base URL. A new Idempotency-Key with each new request is recommended: a retry with the same one is not charged twice.

For model providers (NCPs)

Run models? Supply them through Token Gear.

An NCP is an upstream provider that runs model inference. NCPs running Token Engines supply the capacity behind the API.

Talk to us about joining
  • Each deployment is reviewed and admitted before it serves requests
  • Receive requests already authenticated and within quota
  • Execution, scheduling and GPUs stay yours
  • Procurement prices are kept apart from customers’ prices

Questions, answered

Something else? Write to support@freshtoken.ai.

What is Token Gear?

FreshToken’s AI gateway and model-service platform. It puts models served by several providers behind one OpenAI-compatible API, and handles identity, routing, limits, data constraints and metering along the way.

How do I get access?

Sign up, then contact FreshToken to sign an offline contract. An administrator adds the credit you bought to your account, and you create API keys in the console. There is no self-service top-up or card payment.

How is it different from calling model providers directly?

You hold one key and one balance instead of an account per provider. Token Gear picks an eligible provider for each request, fails over before any output is sent, applies your limits and data constraints, and meters every request to the token.

What is an NCP, and what is a Token Engine?

An NCP is an upstream provider that runs model inference. Each NCP runs a Token Engine: execution state and an inference scheduler (P/D disaggregation, KV cache, batching, DP/EP) on top of its LLM hosting and GPU infrastructure.

Does Token Gear keep my conversation?

Token Gear holds no conversation between requests. Each request carries the context the model needs, as with the OpenAI API, and the platform routes each one on its own, so no conversation is tied to one provider; a reference to something a provider stored earlier is refused rather than guessed. What is kept of a request is under “What happens to my data?”.

How does billing work?

Prepaid credit, bought under an offline contract and metered per token. The most a request can cost is reserved before it goes upstream, and the actual tokens are settled when it ends. Organizations share a balance, and the console shows usage and charges as they happen.

What happens to my data?

Your content is passed to the engine or provider that serves the request and back to you. We keep what is needed to run and bill an account: keys, usage records and balances. We do not store your prompts or responses, with three exceptions: a response is kept for 24 hours (up to 1 MiB) so that a retry with the same Idempotency-Key gets it again; a request flagged for abuse is kept for a short period; and content is kept if your account turns content logging on. See the privacy policy and security and deployment.

Is it compatible with the OpenAI SDKs?

For the endpoints and fields it supports: chat completions, completions, embeddings and a subset of the Responses API, SSE streaming included. Point the SDK’s base URL at Token Gear, and use an sk- key. An Idempotency-Key header on each request is recommended, so that a retry is not charged twice. The compatibility matrix says which tools work.

How does an NCP join?

Write to support@freshtoken.ai. We review the models you host, their prices and evidence, connect your endpoint, and admit each deployment before it serves requests.

Talk to us about access

Sign up, then contact FreshToken to sign an offline contract; an administrator adds your credit.