Together AI pricing and fine-tuning costs

Where this provider fits

An inference and fine-tuning platform for open and hosted AI models, with serverless and dedicated endpoint options.

What can change the bill

• Token rates differ by model and workload
• Dedicated endpoint economics require utilization assumptions

Who should evaluate this route

• Broad open-model catalog
• Serverless and dedicated deployment choices
• OpenAI-compatible API options

Compare two nearby options

Use the same model, meter, configuration, and workload when comparing channels.

• fal.ai pricing evidenceA developer platform focused on fast inference for image, video, and audio models, with model-level pricing and serverless APIs.
• WaveSpeedAI pricing evidenceAn API platform for image and video generation models with model routes, per-run or per-second pricing, and workflow-oriented endpoints.

Existing query answered

Together AI fine-tuning pricing

Current answer: Together prices fine-tuning per 1M processed training and evaluation tokens, with rates changing by model-size band and method. The public table also states a $4 minimum charge per job. These training meters are separate from inference token prices.

The processed-token total includes training dataset tokens multiplied by epochs plus optional evaluation tokens multiplied by evaluations. Dataset preparation, method eligibility, deployment, inference, and human evaluation remain separate decisions.

Open the current fine-tuning price table · Read the fine-tuning workflow

Recorded price evidence

Checked evidence, not a ranking: fresh rows were checked against the linked first-party source on the shown date. APIDir does not name a cheapest provider unless exact configurations and units match. Recheck before purchasing.

Model price comparisons for this provider

Follow each model page to compare this provider route with other accepted, source-linked offers on matching billing meters.

• GLM-5.2 provider pricingCompare GLM-5.2 API token prices across provider routes with exact model identity, meter, tier, source, and check date.
• GPT Image 2 provider pricingCompare GPT Image 2 API providers by image size, quality, output count, route, first-party source, and per-image price.
• GPT-OSS 120B provider pricingCompare source-linked GPT-OSS 120B input and output token prices across provider routes while keeping infrastructure compute meters separate.
• Kimi API provider pricingCompare Kimi API pricing across provider routes without mixing Kimi versions, token meters, context tiers, or service channels.
• Qwen API provider pricingCompare Qwen API pricing by exact model ID, provider channel, input and output token meter, context, and official source.

Related provider comparisons

Use a named alternative and explicit decision dimensions instead of comparing provider brands in the abstract.

• OpenRouter vs Together AICompare product and route control before choosing a route.