Fireworks AI vs Together AI

Same workloads, both price lists, refreshed daily. On shared line items today: Fireworks AI is cheaper on 6 of 14 shared models (input or output price), Together AI on 4.

Fireworks AI

Speed-focused open-model inference with FireAttention serving stack, function-calling models and image generation. Strong latency SLAs for production apps.

  • Very low latency serving
  • Function-calling optimized
  • Enterprise SLAs

Visit Fireworks AI

Together AI

High-performance open-weight inference (Llama, DeepSeek, Qwen) on a custom stack, plus fine-tuning and GPU clusters. Consistently among the fastest and cheapest for open models.

  • Top-tier open-model throughput
  • Fine-tuning pipeline
  • Dedicated endpoints and clusters

Visit Together AI

Shared models, priced by both

List prices refreshed 2026-08-23 ยท input $/1M tokens
Model Fireworks AI in/out Together AI in/out Cheaper input
GPT-OSS 20B $0.070 / $0.300 $0.050 / $0.200 Together AI
GPT-OSS 120B $0.150 / $0.600 $0.150 / $0.600 tie
GLM-4.5 Air $0.220 / $0.880 $0.200 / $1.10 Together AI
Qwen3 235B A22B Thinking 2507 $0.220 / $0.880 $0.650 / $3.00 Fireworks AI
Qwen3-Coder-480b-A35b-Instruct $0.450 / $1.80 $2.00 / $2.00 Fireworks AI
GLM-4.6 $0.550 / $2.19 $0.600 / $2.20 Fireworks AI
DeepSeek-V3.1 $0.560 / $1.68 $0.600 / $1.70 Fireworks AI
Kimi K2 $0.600 / $2.50 $1.00 / $3.00 Fireworks AI
GLM-4.7 $0.600 / $2.20 $0.450 / $2.00 Together AI
Kimi K2.5 $0.600 / $3.00 $0.500 / $2.80 Together AI
DeepSeek V3 $0.900 / $0.900 $1.25 / $1.25 Fireworks AI
Qwen3 Next 80B A3B Instruct $0.900 / $0.900 $0.150 / $1.50 Together AI
Qwen3 Next 80B A3B Thinking $0.900 / $0.900 $0.150 / $1.50 Together AI
DeepSeek R1 $3.00 / $8.00 $3.00 / $7.00 tie

Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.