vioscaleAI
Inference ProvidersUnclaimed

Fireworks AI

Train and deploy customized open models with serverless or dedicated inference

Visit websiteCompare alternatives
Also known as
fireworks-ai

Available worldwide · Popular in: US

What is Fireworks AI?

Fireworks provides serverless and on-demand inference for open source models and custom trained versions, with tools for model fine-tuning, optimization, and deployment. It supports per-token and per-GPU billing with API compatibility for existing model clients.

Independently observed

Fireworks AI pricing

Plans, per-tier features and add-ons, dated and linked to live pricing. Pricing changes often; always verify at source before you rely on it.

Pricing as of verify at live pricing ↗Independently observed
from $0.01/tokensUsage-based

Usage-based pay-per-token for serverless; managed training at $0.50–$12/1M tokens; dedicated GPU from $0.134–$0.334/minute

Serverless Inference

Usage-based per-token pricing
monthly

Per-token usage-based billing with pre-paid credits and no cold starts

  • Pay per input token
  • Pay per output token
  • Pay per cached token
  • OpenAI and Anthropic compatible API
  • Priority and Fast serving options

Embeddings

$0.008–$0.1 per 1M input tokens
monthly

Embedding model inference with tiered pricing by model size

  • Multiple embedding models
  • Tiered by model size

Managed Training

$0.50–$12 per 1M training tokens depending on model size and method
monthly

Supervised and preference fine-tuning with pricing based on model size and method

  • LoRA SFT
  • LoRA DPO
  • Full Parameter SFT
  • Full Parameter DPO
  • Quantization-aware training

Serverless Training API

Usage-based pricing per 1M tokens for prefill, cached prefill, sample, and train
monthly

LoRA training with usage-based per-token pricing on a shared trainer pool

  • Shared trainer pool
  • No provisioning required
  • No idle costs
  • Cached prefill option

On-Demand Deployments

Contact sales
Contact sales

Dedicated GPU instances billed per minute or hour for custom workloads

  • H100, B200, B300, GB300 GPU options
  • Multi-region support
  • Post-trained model support

What Fireworks AI does

The capabilities that matter for inference providers, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.

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
Independently observed

Platform & deployment

Independently observed
Platforms
  • CLI
  • Web
Deployment
  • Cloud / SaaS
  • Hybrid
  • On-premise

Integrations (6)

Independently observed
api_compatibility
  • OpenAI⇄•
  • Anthropic⇄•
  • OpenCode
  • Cline
  • Aider
  • External APIs via function calling

Security & compliance

Independently observed
  • SOC 2 Type II · Type IIactive · Vanta & Advantage Partners
  • HIPAAactive · Vanta & Advantage Partners

Fireworks AI FAQ

Common questions about Fireworks AI, answered from independent, dated evidence.

What is Fireworks AI?

Fireworks provides serverless and on-demand inference for open source models and custom trained versions, with tools for model fine-tuning, optimization, and deployment. It supports per-token and per-GPU billing with API compatibility for existing model clients. It is indexed under Inference Providers.

Source: https://fireworks.ai/pricing

Is Fireworks AI free?

Fireworks AI offers a free tier, so you can start without paying. Paid plans start at $0.50. Prices are published openly on the vendor's own pricing page. Pricing changes often, so verify at source before relying on it.

Source: https://fireworks.ai/pricing

What platforms does Fireworks AI support?

Fireworks AI supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.

Source: https://fireworks.ai/pricing

Can Fireworks AI be self-hosted?

We have only confirmed a cloud / SaaS deployment for Fireworks AI, so it appears to be vendor-hosted. If a self-hosted option exists we have not found it documented publicly.

Source: https://fireworks.ai/pricing

What does Fireworks AI integrate with?

We have confirmed 6 integrations for Fireworks AI, including OpenCode, Cline, Aider, External APIs via function calling, OpenAI and Anthropic. This is what we could verify from public sources, so the vendor may support others we have not indexed.

Source: https://fireworks.ai/pricing

What security certifications does Fireworks AI have?

We have independently confirmed SOC 2, HIPAA and GDPR for Fireworks AI. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as Fireworks AI not holding them. Always confirm compliance directly before you rely on it.

Source: https://fireworks.ai/blog/fireworks-ai-achieves-soc-2-type-ii-and-hipaa-compliance

Where is Fireworks AI available?

Fireworks AI is available worldwide. Its primary market is the United States.

Source: https://fireworks.ai/pricing

Fireworks AI alternatives

Other inference providers we track, ranked by the same independent score.

All Fireworks AI alternatives, ranked →

Compare Fireworks AI

Side by side against other inference providers, attribute by attribute, with a source on every value.

Independent · unbought · dated

The vioscaleAI score: one lens on the evidence

Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for Fireworks AI, not the verdict.

Balanced composite 61 / 100
medium · 55%
Signal contributions to the composite score
SignalScoreWeightContributionEvidence
Security posture600.127.3✓
Pricing transparency750.054.1✓
Capabilities1000.043.8✓
Price level800.043.3✓
Integrations140.040.6✓
Reliability00.070.0-

Computed . Re-weight it by intent, or see the full method.

All data & sourcesshow ↓

Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.

Content

AttributeValueEvidence
Faq7 itemsmediumsource · 2026-09-10 · 64%

Features

AttributeValueEvidence
CapabilitiesSoc2 type ii: Yes · Compute model: multi_tenant_hybrid · Pricing model: per_million_tokens · Openai compatible rest api schema: Yes · Bring your own weights byow hosting: Yes · Dynamic batching and kv cache management: Yesmediumsource · 2026-10-02 · 60%

Integrations

AttributeValueEvidence
Count2mediumsource · 2026-10-02 · 60%

Market

AttributeValueEvidence
AvailabilityPrimaryMarkets: … · AvailabilityScope: global · AvailableCountries: … · NotAvailableCountries: …mediumsource · 2026-10-02 · 50%

Pricing

AttributeValueEvidence
Modelcommercialmediumsource · 2026-10-02 · 60%
Free tierNomediumsource · 2026-10-02 · 60%
Price levellowmediumsource · 2026-10-02 · 60%
Starting priceAmount: 0.008 · Currency: USDmediumsource · 2026-10-02 · 60%
TransparentYesmediumsource · 2026-10-02 · 60%

Security

AttributeValueEvidence
HipaaYeshighsource · 2026-10-02 · 75%
Soc2Yeshighsource · 2026-10-02 · 75%
CertificationsSOC 2 Type II, HIPAAmediumsource · 2026-10-02 · 60%
Disclosure policyYesmediumsource · 2026-09-06 · 60%
GdprYeshighsource · 2026-09-06 · 75%
Trust centerhttps://fireworks.ai/blog/fireworks-ai-achieves-soc-2-type-ii-and-hipaa-compliancemediumsource · 2026-10-02 · 60%
Still deciding?

Is Fireworks AI the right choice for you?

Tell us the job, the constraints and what you weigh most, and we will rank Fireworks AI against the rest of the inference providers we index, using the same dated evidence weighted your way.

Free to run, no account needed to start. How the evaluation works

For the makers of Fireworks AI

Is this your product?

This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves Fireworks AI up or down: nobody can buy rank here, including you.

Take the badge

Live, always current, and free to use on your own site. It shows Fireworks AI's independent score and links back to this profile.

Fireworks AI, verified on vioscaleAI
HTML
<a href="https://www.vioscale.ai/software/fireworks-ai" target="_blank" rel="noopener">
  <img src="https://www.vioscale.ai/badge/software/fireworks-ai.svg" alt="Fireworks AI, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>
Markdown, for a README →
Markdown
[![Fireworks AI, verified on vioscaleAI](https://www.vioscale.ai/badge/software/fireworks-ai.svg)](https://www.vioscale.ai/software/fireworks-ai)

Claim the profile

Verify you control the domain, then point us at the pages that state the facts about Fireworks AI and add your own description and media. Free, and it does not change the score.

  • Correct anything wrong, with evidence
  • Point our crawler at the pages that matter
  • Write your own description and add media
Claim Fireworks AI

Not the owner? How vendor profiles work