together
chat
embedding
image
open-source
Test your Together AI API key.
Validate a Together AI API key and see which of the 200+ open-source models your account can run.
Stateless proxy — keys never logged, stored, or persisted. What happens to your key →
Detected
Together AI
What this key does
Together hosts open-source models behind an OpenAI-compatible API: Llama, Mixtral, Qwen, Flux, and many more. Per-token pricing varies by model size.
How to get a Together AI API key
- Sign in at api.together.xyz.
- Open Settings → API Keys.
- Generate a key (64 hex chars).
- Paste it here.
Common errors and fixes
- 401 Unauthorized: Key is invalid, revoked, or pasted with extra whitespace. Generate a new key from the provider console and try again.
- 403 Forbidden: Key is valid but lacks permission for this resource. Check project / org / workspace scope, or that billing is set up for this key.
- 429 Too Many Requests: You hit the per-minute or per-day rate limit. Wait a moment and retry, or upgrade your tier.
- 404 Not Found: The endpoint or model id changed. Check the provider docs for the current path and model identifier.
- 5xx: The provider is having issues. Check their status page before assuming the bug is yours.
Security best practices
- Store keys in an env var or secret manager — never commit them to a repo, even a private one.
- Restrict scope: prefer per-project or per-deployment keys over a single root key shared across services.
- Rotate on a schedule (90 days is a sane default) and immediately on suspected leak.
- Audit usage in the provider console after rotation to confirm the old key has zero traffic.
- Set per-key spend limits where the provider supports them, so a leaked key has a bounded blast radius.
Pricing at a glance
Together prices per million tokens scaled by model size. Llama 3.1 8B is among the cheapest production-grade chat options on the market.
FAQ
- Is Together OpenAI-compatible?
- Yes — base URL https://api.together.xyz/v1.
- Which models can I run?
- 200+ open-source models, including image (Flux) and embedding. Pull /v1/models to see your account's current set.
- Does Together support fine-tuning?
- Yes, via the fine-tuning endpoints.
- Are dedicated endpoints available?
- Yes — you can pin a model to a dedicated GPU for predictable latency.
- Free tier?
- Promotional credits exist but expire.
- Can I run Flux image models?
- Yes, with a separate per-image price.
Test other providers
Related reading
- OpenAI vs Anthropic pricing in 2026A side-by-side breakdown of OpenAI and Anthropic per-token pricing, batch discounts, and prompt-caching savings.
- Free LLM API keys for testing in 2026Which providers offer free credits, how long they last, and how to stretch them for prototyping without a credit card.