Together AI review

Together AI takes first place because it covers the whole route a team follows when serving open-weight models, and prices each step in public. The serverless API lists per-token rates for current models such as GLM-5.3, Kimi K3, DeepSeek V4.1 Flash and gpt-oss-120B, the last at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with cached input rates shown for many models. The same API handles vision, image, audio, video, transcription, embeddings, rerank and moderation, and Together documents it as OpenAI-compatible. When traffic grows, Provisioned Throughput reserves fixed capacity at $0.05 per PTU per minute, and Dedicated Inference puts a model on single-tenant GPUs, with an H100 at $5.49 an hour. Fine-tuning and GPU clusters sit on the same account. The drawbacks: reserved capacity and several GPU types go through sales, and the dedicated H100 rate is higher than DeepInfra's. For most teams that want breadth and a clear upgrade path, it is the safest default.

Who it is for

Developers who want one OpenAI-compatible API for a wide open model catalog, with a clear path from serverless to dedicated capacity.

Price

Pay per token; gpt-oss-120B at $0.15 per 1M input tokens and $0.60 per 1M output tokens; dedicated H100 at $5.49 per GPU hour.

gpt-oss-120B $0.15 $0.60
Quoted from the vendor pricing page on November 7, 2026.

Key features

• Serverless API for chat, vision, image, audio, video, embeddings, rerank and moderation models
• OpenAI-compatible API
• Provisioned Throughput priced in PTUs at $0.05 per PTU minute
• Dedicated single-tenant GPU endpoints with autoscaling and custom model support
• LoRA and full fine-tuning plus post-training on B200 GPUs

Strengths and weaknesses

• Strength: Broad open model catalog on one API across every modality
• Strength: Cached input pricing listed for many models, such as Kimi K3 at $0.30 per 1M
• Strength: Same vendor covers serverless, reserved, dedicated and raw GPU clusters
• Weakness: Provisioned Throughput and some dedicated GPUs are sales-led
• Weakness: Dedicated H100 at $5.49 per hour costs more than DeepInfra's $2.90
• Weakness: The model list changes often, so pinned model IDs need watching

Key facts

• gpt-oss-120B: $0.15 input, $0.60 output per 1M tokens
• Dedicated H100: $5.49 per GPU hour on demand
• Provisioned Throughput: $0.05 per PTU per minute
• API: OpenAI-compatible

Where it ranks

Together AI is No. 1 in our Best AI Inference Platforms verdict and No. 9 in Best LLM APIs.