Together AI through Squiid

What Together AI is

Together AI runs open-source models as a service. The serverless inference API covers chat, code, vision, image and embedding models from many different labs, all through one OpenAI-compatible interface, and the platform also offers fine-tuning with LoRA, dedicated endpoints for steady traffic and GPU clusters for training. Serverless endpoints mean you pay per token rather than per GPU hour, and dedicated endpoints exist for the point where steady traffic makes reserved capacity cheaper.

For a project built with coding agents, Together is the place to try a model that is not offered by the big labs without standing up any infrastructure. Swap a model string and you are running a different open-weight family; if one of them turns out to fit your task, you can fine-tune it on your own data and keep calling it at the same endpoint. That makes it common in retrieval pipelines, code assistants and image features where the right model is found by experiment rather than by brand. Model availability moves quickly, and Together is usually among the first hosts for a newly released open-weight family.

Why connect it through Squiid

Experimenting across dozens of models is exactly when per-model cost visibility matters. Squiid meters every Together call against prepaid credits at Together's published rate and shows the spend per model, so an expensive experiment is obvious the same day. Requests go to https://api.squiid.io/v1/together-ai/... with Authorization: Bearer $SQUIID_API_KEY, OpenAI-compatible clients work by base URL swap (gateway convention), and fine-tuned model usage bills through the same balance and the same monthly invoice. Because Squiid holds the key, trying a new model never means creating another account with another password.

• One account, one key, one bill, one dashboard. Together AI sits beside every other service your project uses, on the same invoice and the same credit balance.
• Key custody. Squiid holds the Together AI credentials. Your code carries SQUIID_API_KEY, so TOGETHER_API_KEY, TOGETHER_BASE_URL never land in a repository, a preview deployment or an agent’s context.
• Metering you can see. Every call is counted per service and per day, so you know what Together AI costs before the month ends.
• Pause on zero. When prepaid credits run out the gateway stops authorizing usage instead of running up a bill you did not fund.
• One rotation. Rotating the Squiid key cuts off every agent, worker and deployment at once, with no provider key to hunt down.

What you get

• Hundreds of open-source models on one endpoint
• Fine-tuned models callable with the same key
• Image and embedding models alongside chat
• Per-model spend visibility while experimenting
• Together list pricing with no markup

How to connect Together AI

One variable replaces the provider credentials this service would normally need. Requests go to the gateway and the official SDKs work by pointing their base URL at it (gateway convention).

# .env
# replaces TOGETHER_API_KEY, TOGETHER_BASE_URL
SQUIID_API_KEY=sq_live_xxxxxxxxxxxxxxxxxxxxxxxx

# every request: https://api.squiid.io/v1/together-ai/...
# header:       Authorization: Bearer $SQUIID_API_KEY

Pricing through Squiid

Together AI charges per token by model, per image for image models and per GPU hour for dedicated capacity, at the provider's listed price. Squiid passes that through at par: one dollar of prepaid credit is one dollar of Together AI usage, with no markup and no per-request margin.

Together AI has no subscription attached on Squiid today. If a plan is required for a feature you need, it passes through at the provider’s listed price with no Squiid fee.

Squiid adds no markup to provider prices. There is a free plan at $0 a month with a 15% fee when you top up credits, Solo at $19.97 a month with a top-up fee that starts at 8% and falls to 3.5% as your spend grows, Team from $29.97 a seat a month with the same ladder one point lower, and Custom with a rate of 3% or less. Credits are prepaid, so Together AI usage stops when the balance reaches zero rather than producing an invoice you did not fund. Auto top-up with a cap keeps production running without handing anyone an open-ended card.

If you leave

Nothing to move: Together AI is usage-metered, so leaving means creating your own Together AI key and pointing the client at it. Squiid never owns your code, your schema or your domain, and the gateway speaks Together AI's own API, so the client change is a base URL. The handover page lists what happens for every provider in the catalogue.

Works with every coding agent

Together AI through Squiid is just an HTTP call with a bearer token, so every agentic coding tool can use it with the single key already in your environment:

• Claude Code
• Cursor
• ChatGPT
• Codex
• Grok
• Gemini CLI
• GitHub Copilot
• Windsurf
• Perplexity
• Devin
• Replit
• v0
• Lovable
• Cline

Vibe coding a feature on Together AI usually means asking for it in plain language and letting the agent write the integration. Because the key is Squiid’s rather than the provider’s, it can do that without ever holding a credential that could be leaked, logged or committed.