Together AI Prices, limits and access
Cloud platform where developers run open AI models via API, fine-tune them and rent dedicated GPUs.
Visit site (opens in a new tab)
At a Glance
Together AI is an AI tool for Agent & RAG frameworks (category: Development & Code). Free access: No free plan published. Paid from $0.03 (Serverless Inference (Pay-as-you-go)). Documented: 5 plans with prices and limits.
- Category
- Agent & RAG frameworks
- Paid from
- $0.03 / After consumption (Serverless Inference (Pay-as-you-go))
- Free Option
- No free plan published
- Plans
- 5
- Sources
- 3 verified sources
Category: Development & Code · Agent & RAG frameworks
Features
Together AI is a cloud for open models: inference via API (application programming interface), fine-tuning, and rented GPUs (graphics processing units). Serverless bills by tokens; Batch costs half of real-time inference. Cached inputs are cheaper.
Dedicated Inference isolates GPUs. Clusters and Provisioned Throughput (PTU) reserve capacity. Together publishes prices in US dollars; the pricing page names no EU region. The full token and GPU list is in the pricing overview.
- Run, fine-tune, and host open models on rented GPUs
- Serverless inference plus a Batch API at half the real-time rate
- Dedicated single-tenant GPUs with autoscaling for custom models
- Reserved GPU clusters (H100, H200, and others) and provisioned throughput
- Image, video, audio, transcription, embeddings, rerank, and moderation besides text
- Fine-tuning (LoRA or full), code sandbox, and shared filesystem
Prices and plans
US prices only
| Tier | Price | Period | What you get |
|---|---|---|---|
| Serverless Inference (Pay-as-you-go) | $0.03 | After consumption | Examples per 1M tokens (input/output): gpt-oss-20B USD 0.05 / 0.20; LFM2.5-8B-A1B USD 0.03 / 0.12; gpt-oss-120B USD 0.15 / 0.60; Llama 3.3 70B USD 1.04 / 1.04; Qwen3.7-Max USD 1.25 / 3.75; Kimi K3 USD 3.00 / 15.00 Cached input is cheaper, e.g. Kimi K3 at USD 0.30 instead of USD 3.00 One model is listed at USD 0.00: Ternary Bonsai 27B Batch API at half the real-time inference price Further modalities: image, video, audio, transcription, embeddings, rerank, moderation |
| Dedicated Inference | $5.49 / $8.99 | Per GPU and hour, on-demand | Single-tenant GPU instances with guaranteed performance Support for custom models, autoscaling H200, B300, GB200 NVL72 and GB300 NVL72 on request only; reserved capacity on request only |
| GPU Clusters | $3.99 / $5.99 / $8.19 | Per GPU and hour, on-demand | Reserved H100: USD 3.69 (7-30 days), 3.45 (31-90 days), 3.19 (91-180 days) Reserved H200: USD 4.99 / 4.15 / 3.99 Reserved B200: USD 7.99 / 7.79 / 6.79 181+ days and GB200/GB300/B300 on request |
| Provisioned Throughput (PTU) | $0.05 | Per PTU and per minute | Reserved capacity in throughput units; tokens per minute delivered depends on the model MiniMax M3: 166,667 input TPM, 833,333 cached TPM, 41,667 output TPM per PTU Kimi K3: 16,667 / 166,667 / 3,333 TPM per PTU GLM-5.2: 35,714 / 192,308 / 11,364 TPM per PTU |
| Fine-tuning, Sandbox and Storage | $0.48 | After consumption | Supervised fine-tuning per 1M tokens: up to 16B USD 0.48 (LoRA) / 0.54 (full); 17B-69B 1.50 / 1.65; 70-100B 2.90 / 3.20 Direct preference optimization per 1M tokens: up to 16B USD 1.20 / 1.35; 17B-69B 3.75 / 4.12; 70-100B 7.25 / 8.00 Minimum charge per fine-tuning job: USD 4.00 Code Sandbox: USD 0.0446 per vCPU-hour, USD 0.0149 per GiB RAM-hour Code Interpreter: USD 0.03 per 60-minute session Shared filesystem: USD 0.16 per GiB per month |
Prices as stated by the provider, usually plus statutory VAT. The final price depends on your country and is shown by the provider.
Prices last checked: 2026-10-09
What does Together AI cost?
API for developers
The API is billed by usage. What it costs you depends on how much you use it.
Calculate it yourself
Independent price alert from AI Compare Ninja
Limits
- Together AI is a US vendor and publishes prices in US dollars.
- The pricing page names no EU data region.
- According to the privacy policy, the vendor does not use customer data to train its own models without explicit opt-in and consent.
- Data may be processed outside the user's country.
- In Zero Data Retention mode, the vendor says inputs and outputs are not stored and are not used for model training, product improvement, or other secondary purposes.
More tools in this category
How we compare
We compare free access, paid entry, plan limits, features and the listed official sources. Unsourced figures stay marked as not published.
Only confirmed entries appear in the catalog. Prices, plans and limits come from listed official vendor pages. Missing figures stay marked as not published. Search results are ordered by Task match by default; category and task lists are alphabetical. Both can be switched to Free access first; neither is a quality ranking. The vendor page always wins.
Edited and checked by the AI Compare Ninja team
Sources
All details regarding plans, limits, and features are based on official vendor documentation and the primary sources verified below.
- together.ai/pricing
- docs.together.ai/docs/billing-credits
- together.ai/privacy
FAQ
Is Together AI available for free?
No. No free access is published on the vendor's own pages.
Where is the vendor of Together AI based?
Together Computer, Inc. is based in the USA. Regardless of that location, data processing and privacy terms are governed by the vendor's own contract.
How is Together AI billed?
Together AI is a US vendor; the website and console are reachable from Europe without restriction. For data residency, the vendor names no EU region on the pricing page. As a US infrastructure provider, Together AI bills exclusively in US dollars; there is no euro or CHF price.
What is “Together Computer, Inc.” on my bank or card statement?
According to our catalog data, Together Computer, Inc. is the company behind Together AI, so a charge under this name may come from a subscription or purchase at Together AI. The exact wording on a bank or card statement is set by the vendor and its payment provider; it can differ and is not recorded here. The invoices in your Together AI account help to match the charge; for an unknown charge, contact your bank.
How much does Together AI cost?
The cheapest paid plan of Together AI is Serverless Inference (Pay-as-you-go) at $0.03. 5 plans are documented in total, each with its price and limits.
Is Together AI currently available?
Together AI is active.
Spotted an outdated figure? Vendor pages change without notice. Report an error
Together AI and related names are trademarks or identifiers of their respective owners (Together Computer, Inc.). They are named solely for descriptive purposes in an independent comparison. AI Compare Ninja has no business relationship, partnership or affiliation with Together Computer, Inc.