fruitpunch

Review · AI & data

Fireworks AI logoFireworks AI review

Serverless and reserved inference for open-weight models such as DeepSeek, Kimi, GLM and GPT OSS.

By the FruitPunch research desk · Updated November 20, 2026

Quality (40%)
8.1
Ease of use (25%)
8.4
Value (35%)
9.4

Fireworks AI answers the cheapest-per-token question: its pricing page says serverless inference starts from $0.05 per 1M input tokens, the rate for NVIDIA Nemotron 3.5 Lightning 30B A3B, with output at $0.20. It hosts many popular open-weight models, including DeepSeek V4.1 Flash at $0.30 in and $1.20 out, GLM 5.3 Flash at $0.15 in and OpenAI GPT OSS 120B at $0.15 in. Each request can pick a mode: Standard, Priority, Fast for 100+ tokens per second, Batch at 50% off, or Spot at 30% off on best-effort capacity. Cached input is billed at half price or less with no write fee. Billing uses prepaid credits with monthly spend limits and Auto Reload, which suits a small team watching cash. Fireworks does not list a free plan, Spot capacity can drop to zero, and US-only serving costs 50% more on select models. Quality depends on the open model you choose, so test a few before committing.

Who it is for

the lowest per-token price on open models

Price

Pay per token from $0.05 per 1M input tokens; prepaid credits.

Serverless Pay per token · From $0.05 / 1M input tokens
Quoted from the vendor pricing page on November 20, 2026.

Key features

  • Serverless from $0.05 per 1M input tokens on NVIDIA Nemotron 3.5 Lightning 30B A3B
  • Standard, Priority, Fast, Batch and Spot modes on the same endpoint
  • Batch at 50% off and Spot at 30% off Standard
  • Cached input billed at half price or less, with no write fee
  • Monthly spend limits and Auto Reload on prepaid credits

Strengths and weaknesses

  • Strength: Lowest starting price in this comparison at $0.05 per 1M input tokens
  • Strength: Switch between Standard, Batch and Spot per request without changing endpoints
  • Strength: Reserved Throughput adds a 99.9% uptime SLA for steady traffic
  • Weakness: No free plan; usage draws down prepaid credits
  • Weakness: Spot throughput can drop to zero, so you need retry or fallback logic
  • Weakness: US-only serverless costs a 50% premium on select models

Key facts

  • Starting price: $0.05 per 1M input tokens
  • Popular open model: DeepSeek V4.1 Flash, $0.30 in and $1.20 out per 1M tokens
  • Discount modes: Batch 50% off, Spot 30% off
  • Billing: Prepaid credits with spend limits and Auto Reload

Where it ranks

Fireworks AI is No. 5 in our Best LLM API Providers verdict.

Alternatives we scored

Visit fireworks.ai · Questions or corrections: editorial@fruitpunch.ai