Fireworks

HealthyTelemetry updated 32m ago

High-speed AI inference platform optimized for low-latency serving of open-source models, offering OpenAI-compatible API endpoints with custom model deployment and fine-tuning capabilities.

API Base URL

https://api.fireworks.ai/inference/v1

Authentication

api-key

Uptime (24h)

100.0%

Uptime (7d)

100.0%

Supported Regions

us-east-1us-west-2

Latency (TTFT)

Time to first token percentiles

No latency data available

Health History

Uptime over the last 7 days

7-Day Uptime100.00% — Excellent

24-Hour Uptime100.00% — Excellent

Current Status

Healthy

Last Checked

32m ago

Supported Models (4)

Models available through this provider. Select a model to view details.

DeepSeek V4

deepseek-v4

Pricing (per 1M): In: $0.20
Out: $0.80
Rate Limits: 600 RPM
1.0M TPM
Regions: us-east-1us-west-2

Llama 4 Maverick

llama-4-maverick

Pricing (per 1M): In: $0.22
Out: $0.88
Rate Limits: 600 RPM
1.0M TPM
Regions: us-east-1us-west-2

Qwen3 32B

qwen3-32b

Pricing (per 1M): In: $0.20
Out: $0.20
Rate Limits: 600 RPM
1.0M TPM
Regions: us-east-1us-west-2

Llama 3.3 70B Instruct

llama-3-3-70b

Pricing (per 1M): In: $0.90
Out: $0.90
Rate Limits: 600 RPM
1.0M TPM
Regions: us-east-1us-west-2

Model	Pricing (per 1M)	Rate Limits	Regions
DeepSeek V4 deepseek-v4	In: $0.20 Out: $0.80	600 RPM / 1.0M TPM	us-east-1us-west-2
Llama 4 Maverick llama-4-maverick	In: $0.22 Out: $0.88	600 RPM / 1.0M TPM	us-east-1us-west-2
Qwen3 32B qwen3-32b	In: $0.20 Out: $0.20	600 RPM / 1.0M TPM	us-east-1us-west-2
Llama 3.3 70B Instruct llama-3-3-70b	In: $0.90 Out: $0.90	600 RPM / 1.0M TPM	us-east-1us-west-2