Fireworks AI vs Nebius
Same workloads, both price lists, refreshed daily. On shared line items today: Fireworks AI is cheaper on 1 of 29 shared models (input or output price), Nebius on 13.
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
Nebius
AI cloud from the former Yandex team with H100/H200/B200 clusters in Europe and the US, plus Nebius AI Studio for per-token open-weight inference. Competitive pricing at cluster scale.
- European datacenters
- Both clusters and per-token inference
- Aggressive large-scale pricing
Shared models, priced by both
List prices refreshed 2026-10-08 ยท input $/1M tokens| Model | Fireworks AI in/out | Nebius in/out | Cheaper input |
|---|---|---|---|
| DeepSeek V4 Flash | $0.140 / $0.280 | $0.140 / $0.280 | tie |
| GPT-OSS 120B | $0.150 / $0.600 | $0.150 / $0.600 | tie |
| GLM 5.3 Flash | $0.150 / $0.500 | $0.150 / $0.500 | tie |
| Qwen3 30B A3B | $0.150 / $0.600 | $0.100 / $0.300 | Nebius |
| Mistral Nemo | $0.200 / $0.200 | $0.040 / $0.120 | Nebius |
| Llama-Guard-3-8B | $0.200 / $0.200 | $0.020 / $0.060 | Nebius |
| Qwen3 14B | $0.200 / $0.200 | $0.080 / $0.240 | Nebius |
| Qwen2.5-Coder-7B | $0.200 / $0.200 | $0.010 / $0.030 | Nebius |
| Qwen3-4B | $0.200 / $0.200 | $0.080 / $0.240 | Nebius |
| Qwen3 235B A22B | $0.220 / $0.880 | $0.200 / $0.600 | Nebius |
| MiniMax M3 | $0.300 / $1.20 | $0.300 / $1.20 | tie |
| DeepSeek V4.1 Flash | $0.300 / $1.20 | $0.300 / $1.20 | tie |
| DeepSeek V3 | $0.900 / $0.900 | $0.500 / $1.50 | Nebius |
| Qwen3 Next 80B A3B Thinking | $0.900 / $0.900 | $0.150 / $1.20 | Nebius |
| DeepSeek R1 Distill Llama 70B | $0.900 / $0.900 | $0.250 / $0.750 | Nebius |
| QwQ-32B | $0.900 / $0.900 | $0.150 / $0.450 | Nebius |
| Qwen3 32B | $0.900 / $0.900 | $0.100 / $0.300 | Nebius |
| Gemma 3 27B | $0.900 / $0.900 | $0.100 / $0.300 | Nebius |
| Qwen2.5 VL 72B Instruct | $0.900 / $0.900 | $0.250 / $0.750 | Nebius |
| Qwen2p5-72b | $0.900 / $0.900 | $0.130 / $0.400 | Nebius |
| Qwen2-VL-72B-Instruct | $0.900 / $0.900 | $0.130 / $0.400 | Nebius |
| Kimi K2.6 | $0.950 / $4.00 | $0.950 / $4.00 | tie |
| Kimi K2.7 Code | $0.950 / $4.00 | $0.950 / $4.00 | tie |
| DeepSeek V4 Pro | $1.20 / $1.20 | $1.75 / $3.50 | Fireworks AI |
| GLM-5.2 | $1.40 / $4.40 | $1.40 / $4.40 | tie |
| GLM 5.3 | $1.40 / $4.40 | $1.40 / $4.40 | tie |
| GLM-5.1 | $1.40 / $4.40 | $1.40 / $4.40 | tie |
| DeepSeek R1 | $3.00 / $8.00 | $0.800 / $2.40 | Nebius |
| Kimi K3 | $3.00 / $15.00 | $3.00 / $15.00 | tie |
Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.