Fireworks

Fast, cost-efficient hosting for open-weight models.

Fireworks specialises in optimised, low-cost hosting of open-weight models — Llama, GPT-OSS, DeepSeek, Qwen, Mistral, and dozens of fine-tuned variants — across serverless and dedicated tiers. Globally hosted by default — serverless is not region-pinned. Competitive on price-per-token for high-throughput open-weight workloads where cost matters more than feature parity with closed frontier models.

1 route22 modelsMulti🇺🇸 HQ United States
fireworks.ai

Models on Fireworks

Every model we route through Fireworks. Compare residency, zero retention, training posture, and price at a glance — full data-handling detail per route below.

ModelRegionZero data retentionTrainingContextInputOutput
MultiZero data retentionNo1M$3.00$15.00
MultiZero data retentionNo$2.00$6.00
MultiZero data retentionNo262K$2.00$6.00
MultiZero data retentionNo1M$1.74$3.48
MultiZero data retentionNo1M$1.32$3.96
MultiZero data retentionNo1M$1.40$4.40
MultiZero data retentionNo1M$2.10$6.60
MultiZero data retentionNo1M$0.22$0.66
MultiZero data retentionNo1M$0.22$0.66
MultiZero data retentionNo1M$0.22$0.66
MultiZero data retentionNo512K$0.30$1.20
MultiZero data retentionNo262K$0.95$4.00
MultiZero data retentionNo262K$0.95$4.00
MultiZero data retentionNo262K$1.90$8.00
MultiZero data retentionNo1M$1.00$4.05
MultiZero data retentionNo262K$0.40$1.60
MultiZero data retentionNo197K$0.30$1.20
MultiZero data retentionNo131K$0.15$0.60
MultiZero data retentionNo131K$0.07$0.30
MultiZero data retentionNo131K$0.35$1.50
MultiZero data retentionNo262K$0.05$0.20
MultiZero data retentionNo262K$0.60$2.40

Data handling per route

Fireworks hosts on 1 route. Each route has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

Multi-region

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Subprocessors may read content
no-KYC deposit
deposit available
Transfer mechanism
wallets

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation