AI & Models · Integration
Together AI
Add Together AI to your product for your customers, and give your AI agents governed access to it.
Together AI serves open models behind one API, so what you work with is the catalogue of hosted models, the chat and completion calls made against them, and fine-tuning jobs with the files they train on. The catch is the catalogue itself. Which open weights are hosted, under what name and at what context length, changes as the ecosystem does, so a model identifier compiled into your product can be renamed or retired while a customer depends on it. The model therefore belongs in configuration, read at runtime, with a fallback chosen before an incident rather than during one. Fine-tuning is long-running, so a job is submitted and its state polled instead of awaited. Each customer's key stays with fastn per tenant, and fastn tracks what the platform serves.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own Together AI account so inference spend lands on whoever caused it.
Read the hosted model catalogue at runtime, so a rename or a retirement is a config change rather than a hotfix.
Run chat and completion calls with the model and context length a customer picked for their workload.
Submit a fine-tuning job and poll its state, so your product follows a long training run without holding a request open.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent chooses from the models a customer has actually enabled rather than one your code assumed.
An agent reports where a fine-tuning job has got to and which base model it started from.
An agent runs the same prompt against two hosted models within the permissions granted, and reports the difference.
Example prompt
Has my fine-tuning job finished yet, and which hosted model was it trained on top of?
Set up Together AI in 4 steps
- 01Enable the Together AI connector from your fastn dashboard.
- 02Have each customer authorise their own Together AI account, so calls run under their credentials rather than a shared key.
- 03Decide which models, requests and outputs your product needs, map those fields, then enable the actions and triggers you want.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the Together AI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Together AI integration without building it. Your customers connect their own Together AI account inside your product and work their models, requests and outputs there, with no per-customer code on your side.
- Handle the part that actually costs time: per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Together AI update is not your on-call problem.
- One integration serves your product and your agents. The same governed Together AI connection powers in-product features and gives AI agents scoped, audited access, so you give your product and your agents a model call each customer pays for themselves without wiring it twice.
Used by these teams
Compare with
Hugging Face
Replicate
OpenAIOften used alongside
Tools the same teams tend to run next to Together AI, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeTogether AI integration FAQ
How do I add a Together AI integration to my product?
Enable the Together AI connector in your fastn dashboard, then let each customer authenticate their own Together AI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Together AI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Together AI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Together AI account and only ever sees their own models, requests and outputs. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Together AI integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent chooses from the models a customer has actually enabled rather than one your code assumed.
Who maintains the Together AI integration?
fastn does. When Together AI changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Whose Together AI API key and quota does each call use?
Each customer authorises their own Together AI account, so usage, rate limits and cost land on the customer that caused them. You are not metering a shared key and re-billing it, and one heavy customer cannot exhaust another's quota.
Are inputs and outputs auditable?
Yes. Every call is logged per tenant with the call, the input and the result, so an output can be traced back to what produced it. That matters more here than in most integrations, because a generated answer or an extracted field cannot be reconstructed from the request alone.
What can I build with the Together AI integration?
A common starting point: let each customer connect their own Together AI account so inference spend lands on whoever caused it. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Together AI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Together AI does not change your per-connector cost. You can start free with 3 connected accounts.
Add Together AI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.