# Together AI

> The AI Native Cloud

- **Canonical URI:** https://www.vioscale.ai/software/together-ai
- **Category:** MLOps & LLMOps Tools
- **Homepage:** https://together.ai
- **Also known as:** together-ai
- **Profile claimed by vendor:** no
- **Last updated:** 2026-08-03T22:51:53.157Z

## Vioscale score

**71.1 / 100**, confidence 47% (low).

Composite of weighted, independently-sourced signals (no user reviews, no vendor payment).

| Signal | Score | Weight | Contribution | Evidence present |
|---|--:|--:|--:|:--:|
| price_level | 80 | 10 | 800 | ✓ |
| reliability | 50 | 12 | 600 | ✓ |
| capabilities | 74.7 | 32 | 2391.1 | ✓ |
| integrations | 0 | 18 | 0 | - |
| security_posture | 70 | 12 | 840 | ✓ |
| pricing_transparency | 75 | 16 | 1200 | ✓ |

## Pricing

_As of 2026-08-03, [verify at source](https://together.ai). Independently observed._

from $0.30/mo · Usage-based

> Usage-based pricing for inference starting at $0.03 per 1M input tokens (MiniMax M3), scaling to $3.00+ per 1M tokens for frontier models. Dedicated and provisioned throughput available with custom pricing.

| Plan | Price | Free | Commitment |
|---|---|:--:|---|
| Serverless Inference | Pay-per-token. Input pricing from $0.03-$3.00 per 1M tokens (varies by model) | - | - |
| Batch Inference | Batch API pricing (example: $1.20/1M tokens for MiniMax M3) | - | - |
| Provisioned Throughput | Contact sales | - | - |
| Dedicated Model Inference | Contact sales | - | - |
| Dedicated Container Inference | Contact sales | - | - |

### Serverless Inference

High-performance inference as APIs. Most teams start here.

- Multiple model options
- Chat
- Vision
- Image
- Audio
- Video
- Transcribe
- Embeddings
- Rerank
- Moderation

### Batch Inference

Inference for batch workloads

### Provisioned Throughput (Contact sales)

Token-based capacity with SLAs

### Dedicated Model Inference (Contact sales)

Inference on custom hardware

### Dedicated Container Inference (Contact sales)

Inference for custom models

### Add-ons

- **GPU Clusters**
- **Fine-Tuning**
- **Evaluations**
- **Managed Storage**

## About

A research-driven AI cloud infrastructure provider with a purpose-built GPU platform for training, fine-tuning, and running frontier-class AI models.

_Independently observed._

## Platform & deployment

- **Platforms:** Web
- **Deployment:** Cloud / SaaS

## Capabilities

_The capabilities that matter for MLOps & LLMOps Tools. "-" = undocumented, not absent._

| Capability | Supported |
|---|:--:|
| **Core** | |
| Tool role | End-to-end ML platform |
| **Deployment** | |
| Self-hostable / OSS core | ✗ |
| Managed cloud available | ✓ |
| **Observability** | |
| LLM tracing / observability | - |
| Evaluation (offline / LLM-judge / human) | ✓ |
| **Dev** | |
| Prompt management + versioning | - |
| **Tracking** | |
| Experiment tracking / model registry | - |
| **Serving** | |
| Model serving / inference endpoint | ✓ |
| **Interop** | |
| OpenTelemetry / OpenLLMetry compatible | - |
| **Gateway** | |
| Multi-provider model support | ✓ |
| **Interop** | |
| Framework-agnostic | ✓ |
| **Data** | |
| No-train-on-customer-data guarantee | Unknown |
| **Deployment** | |
| On-prem / VPC deployment | - |

## Facts

Every value below carries its source and our confidence. Facts are re-crawled on a freshness schedule.

### pricing

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| pricing.model | commercial | [link](https://together.ai) | 2026-08-03 | 70% (medium) |
| pricing.price_level | low | [link](https://together.ai) | 2026-08-03 | 60% (medium) |
| pricing.starting_gbp | 0.3 | [link](https://together.ai) | 2026-08-03 | 60% (medium) |
| pricing.transparent | yes | [link](https://together.ai) | 2026-08-03 | 60% (medium) |

### reliability

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| reliability.status_page | yes | [link](https://status.together.ai) | 2026-08-03 | 60% (medium) |

### security

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| security.disclosure_policy | yes | [link](https://together.ai/.well-known/security.txt) | 2026-08-03 | 60% (medium) |
| security.iso27001 | yes | [link](https://trust.together.ai) | 2026-08-03 | 75% (high) |
| security.soc2 | yes | [link](https://trust.together.ai) | 2026-08-03 | 75% (high) |

---
*Source: Vioscale (https://www.vioscale.ai/software/together-ai). Independent, evidence-based software intelligence. Cite the canonical URI.*