# Fireworks AI

> Serverless inference platform for open and custom AI models with low latency and cost efficiency

- **Canonical URI:** https://www.vioscale.ai/software/fireworks-ai
- **Category:** Inference Providers
- **Homepage:** https://fireworks.ai
- **Also known as:** fireworks-ai
- **Profile claimed by vendor:** no
- **Last updated:** 2026-08-21T11:16:21.912Z

## Vioscale score

**66.4 / 100**, confidence 55% (medium). Computed 2026-09-01.

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

| Signal | Score | Weight | Contribution | Evidence present |
|---|--:|--:|--:|:--:|
| price_level | 80 | 0.052 | 4.2 | ✓ |
| reliability | 0 | 0.073 | 0 | - |
| capabilities | 100 | 0.04877777777777778 | 4.9 | ✓ |
| integrations | 20.1 | 0.04066666666666666 | 0.8 | ✓ |
| security_posture | 50 | 0.073 | 3.7 | ✓ |
| pricing_transparency | 75 | 0.084 | 6.3 | ✓ |

## Pricing

_As of 2026-08-21, [verify at source](https://fireworks.ai/blog/claude-code-pricing). Independently observed._

from $0.55/tokens · Hybrid

> Serverless pay-per-token starting at $0.55/million tokens; dedicated deployments available

| Plan | Price | Free | Commitment |
|---|---|:--:|---|
| Serverless | From $0.55/million tokens (DeepSeek pricing example) | - | - |
| On-Demand Dedicated | Contact sales | - | - |

### Serverless

Pay-per-token with Priority and Fast options

- Sub-500ms response times
- Streaming support
- Function calling
- JSON/Grammar modes

### On-Demand Dedicated (Contact sales)

Multi-region dedicated deployments with custom throughput

- Dedicated GPU instances
- Multi-region support
- Custom models
- Priority throughput

## About

An AI inference platform that hosts and serves open-source models and fine-tuned versions with serverless or dedicated deployment options, optimized for speed and cost. Supports multiple LLMs, function calling, multimodal capabilities, and integrates with popular development tools.

_Independently observed._

## Platform & deployment

- **Platforms:** CLI, Web
- **Deployment:** Cloud / SaaS, Hybrid, On-premise, Self-hosted

## Integrations (4)

_Independently observed._

- OpenCode
- Cline
- Aider
- External APIs via function calling

## Capabilities

_The capabilities that matter for Inference Providers. "-" = undocumented, not absent._

| Capability | Supported |
|---|:--:|
| **Capabilities** | |
| Compute model | Multi tenant hybrid |
| Zero data retention training opt out enterprise | ✓ |
| Openai compatible rest API schema | ✓ |
| Native function calling and strict json mode | ✓ |
| Multimodal vision and audio in out support | ✓ |
| Streaming server sent events sse token yield | ✓ |
| Massive context window support 100k plus | ✓ |
| Lpu or custom silicon for extreme low latency | ✓ |
| Bring your own weights byow hosting | ✓ |
| Dynamic batching and kv cache management | ✓ |
| SOC2 type ii | ✓ |
| HIPAA baa compliance for medical inference | ✓ |
| Pricing model | Per million tokens |

## 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://fireworks.ai/blog/claude-code-pricing) | 2026-08-21 | 60% (medium) |
| pricing.free_tier | no | [link](https://fireworks.ai/blog/claude-code-pricing) | 2026-08-21 | 60% (medium) |
| pricing.price_level | low | [link](https://fireworks.ai/blog/claude-code-pricing) | 2026-08-21 | 60% (medium) |
| pricing.starting_price | `{"amount":0.55,"currency":"USD"}` | [link](https://fireworks.ai/blog/claude-code-pricing) | 2026-08-21 | 60% (medium) |
| pricing.transparent | yes | [link](https://fireworks.ai/blog/claude-code-pricing) | 2026-08-21 | 60% (medium) |

### integrations

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| integrations.count | 4 | [link](https://fireworks.ai/blog/claude-code-pricing) | 2026-08-21 | 60% (medium) |

### market

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| market.availability | `{"hqCountry":"US","primaryMarkets":["US","EU"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | [link](https://fireworks.ai/blog/claude-code-pricing) | 2026-08-21 | 75% (high) |

### security

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| security.hipaa | yes | [link](https://fireworks.ai/blog/fireworks-ai-achieves-soc-2-type-ii-and-hipaa-compliance) | 2026-08-21 | 75% (high) |
| security.soc2 | yes | [link](https://fireworks.ai/blog/fireworks-ai-achieves-soc-2-type-ii-and-hipaa-compliance) | 2026-08-21 | 75% (high) |

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