Fireworks AI vs OpenRouter
Same workloads, both price lists, refreshed daily. On shared line items today: Fireworks AI is cheaper on 5 of 30 shared models (input or output price), OpenRouter on 19.
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
OpenRouter
One API key for 340+ models across every major provider, with automatic failover and pass-through pricing. The fastest way to hedge provider risk or A/B models without new integrations.
- 340+ models, one integration
- Automatic provider failover
- Pass-through pricing, small platform fee
Shared models, priced by both
List prices refreshed 2026-08-23 ยท input $/1M tokens| Model | Fireworks AI in/out | OpenRouter in/out | Cheaper input |
|---|---|---|---|
| GPT-OSS 20B | $0.070 / $0.300 | $0.020 / $0.100 | OpenRouter |
| DeepSeek V4 Flash | $0.140 / $0.280 | $0.050 / $0.101 | OpenRouter |
| GPT-OSS 120B | $0.150 / $0.600 | $0.180 / $0.800 | Fireworks AI |
| Qwen3 30B A3B | $0.150 / $0.600 | $0.120 / $0.500 | OpenRouter |
| Qwen3 Coder 30B A3B Instruct | $0.150 / $0.600 | $0.070 / $0.280 | OpenRouter |
| Qwen3 VL 30B A3B Instruct | $0.150 / $0.600 | $0.130 / $0.520 | OpenRouter |
| Qwen3 VL 30B A3B Thinking | $0.150 / $0.600 | $0.200 / $2.40 | Fireworks AI |
| Mistral Nemo | $0.200 / $0.200 | $0.019 / $0.030 | OpenRouter |
| Mistral-7b | $0.200 / $0.200 | $0.130 / $0.130 | OpenRouter |
| MythoMax 13B | $0.200 / $0.200 | $1.88 / $1.88 | Fireworks AI |
| Qwen3 14B | $0.200 / $0.200 | $0.120 / $0.240 | OpenRouter |
| Qwen3 8B | $0.200 / $0.200 | $0.117 / $0.455 | OpenRouter |
| Qwen3 VL 8B Instruct | $0.200 / $0.200 | $0.117 / $0.455 | OpenRouter |
| Qwen3 235B A22B | $0.220 / $0.880 | $0.071 / $0.100 | OpenRouter |
| GLM-4.5 Air | $0.220 / $0.880 | $0.130 / $0.850 | OpenRouter |
| Qwen3 VL 235B A22B Instruct | $0.220 / $0.880 | $0.210 / $1.90 | OpenRouter |
| Qwen3 235B A22B Thinking 2507 | $0.220 / $0.880 | $0.110 / $0.600 | OpenRouter |
| Qwen3 VL 235B A22B Thinking | $0.220 / $0.880 | $0.400 / $4.00 | Fireworks AI |
| MiniMax M2.1 | $0.300 / $1.20 | $0.270 / $1.20 | OpenRouter |
| MiniMax M2 | $0.300 / $1.20 | $0.255 / $1.02 | OpenRouter |
| MiniMax M2.7 | $0.300 / $1.20 | $0.240 / $0.960 | OpenRouter |
| MiniMax M3 | $0.300 / $1.20 | $0.300 / $1.20 | tie |
| Muse Glimmer 30B | $0.350 / $1.50 | $0.350 / $1.50 | tie |
| Qwen3.7 Plus | $0.400 / $1.60 | $0.320 / $1.28 | OpenRouter |
| GPT-OSS-Safeguard-20b | $0.500 / $0.500 | $0.075 / $0.300 | OpenRouter |
| GLM-4.6 | $0.550 / $2.19 | $0.400 / $1.75 | OpenRouter |
| GLM-4.5 | $0.550 / $2.19 | $0.600 / $2.20 | Fireworks AI |
| DeepSeek V3.2 | $0.560 / $1.68 | $0.280 / $0.400 | OpenRouter |
| DeepSeek V3.1 Terminus | $0.560 / $1.68 | $0.270 / $1.00 | OpenRouter |
| Kimi K2 | $0.600 / $2.50 | $0.570 / $2.30 | OpenRouter |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.