> Together AI
Together AI is a first-party inference platform spanning serverless models (published per-1M pricing from $0.14 on Llama 3 8B Lite, with batch discounts), fine-tuning, provisioned throughput, and dedicated H100/H200/B200 instances from $3.99/hr. One account covers the full ladder from serverless to reserved capacity.
// pros
- Broad serverless catalog with published per-1M pricing — Llama, Qwen, GLM, DeepSeek, gpt-oss and more, each with a listed batch price.
- Full compute stack under one account: fine-tuning, provisioned throughput (PTU), dedicated GPU instances and hourly GPU clusters.
- Transparent dedicated pricing — H100 from $3.99/hr, H200 $5.99/hr, B200 $8.19/hr — a clear path from serverless to reserved capacity.
- Cached-input discounts on many models (e.g. DeepSeek V4 Pro: $1.32 in, $0.13 cached) reward prompt-heavy workloads.
// cons
- The pricing page lists no free credit as of 2026-09-16 — widely quoted sign-up credits should be confirmed in your console before you budget around them.
- Dedicated and provisioned products are paid from day one; there is no free tier for reserved capacity.
- Serverless unit economics swing hard by model (Llama 3.3 70B $1.04 vs gpt-oss-120B $0.15 per 1M in) — check the model you actually need.
- Batch pricing is per-model, not a global discount — availability varies across the catalog.
A good default for open-weight serverless work that may later need fine-tuning or dedicated GPUs — the same vendor covers all three stages. Start on the cheapest model that meets your quality bar and re-check prices per model, not per brand.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
No free tier
This provider does not offer a free tier as of our last verification (Sep 16, 2026). The cheapest way to try it is pay-as-you-go — input from Free per 1M tokens. If the provider adds a free tier, submit a correction and we’ll re-verify.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Pay-as-you-go | payg | — | Free | Free | Cheapest tracked model rate (OpenRouter-normalized). |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Meta-Llama-3.1-70B-Instruct | Free | Free | 131k |
| DeepSeek Chat | Free | $0.0000 | 164k |
| Qwen2.5 72B Instruct | Free | Free | 33k |
| Mistral Nemo | Free | Free | 131k |
| Gemma 2 27B | $0.0000 | $0.0000 | 8k |
$ Does Together AI have a free tier?
No. Together AI does not offer a meaningful free tier — entry requires payment (pay-as-you-go or a plan). We mark this explicitly rather than showing a misleading zero.
$ How much does Together AI cost per 1M tokens?
The cheapest model we track at Together AI is Free per 1M input tokens and Free per 1M output tokens. This is normalized from Together AI's published pricing — verify with the provider before purchasing, since prices change frequently.
$ Is Together AI safe to use?
Uprouter rates Together AI as low risk. Low risk: first-party platform with published per-model pricing and a documented product ladder (serverless → provisioned → dedicated). No exotic terms; the main caveat is the entry point — the pricing page no longer advertises a free credit, so treat sign-up grants as unverified until they appear in your own console. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
current: unknownNo probes recorded yet.
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Low risk: first-party platform with published per-model pricing and a documented product ladder (serverless → provisioned → dedicated). No exotic terms; the main caveat is the entry point — the pricing page no longer advertises a free credit, so treat sign-up grants as unverified until they appear in your own console.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# Together AI's own API — get a key from their dashboard
curl https://www.together.ai/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama-3-1-70b-instruct",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.