Price Per TokenPrice Per Token
Fireworks AIvsSambaNova

Fireworks AI vs SambaNova

Compare pricing across 6 shared models. Fireworks AI offers 206 models, SambaNova offers 8.

8 Ways to Use Fewer Tokens

Get the free PDF guide — practical tips to cut your token usage and API costs. Subscribe to the Price Per Token newsletter and download instantly.

6
Shared Models
3
Fireworks AI Cheaper
2
SambaNova Cheaper
1
Same Price

Price Comparison — Shared Models

Model ↑Fireworks AI Input SambaNova Input Fireworks AI Output SambaNova Output Cheaper
DeepSeek V3.1 $0.560 $0.150 $1.68 $0.750SambaNova
DeepSeek V3.2 $0.560 $3.00 $1.68 $4.50Fireworks AI
Gemma 3 12B $0.200 $0.200 $0.200 $0.350Fireworks AI
GPT-OSS-120b $0.100 $0.140 $0.100 $0.950Fireworks AI
Llama 3.3 70B Instruct $0.900 $0.600 $0.900 $1.20SambaNova
MiniMax M2.5 $0.300 $0.300 $1.20 $1.20Same

Model Coverage

Fireworks AIOnly on Fireworks AI(200)
Chronos Hermes 13B v2$0.200/M
Code Llama 13B$0.200/M
Code Llama 13B Instruct$0.200/M
Code Llama 13B Python$0.200/M
Code Llama 34B$0.900/M
Code Llama 34B Instruct$0.900/M
Code Llama 34B Python$0.900/M
Code Llama 70B$0.900/M
Code Llama 70B Instruct$0.900/M
Code Llama 70B Python$0.900/M
Code Llama 7B$0.200/M
Code Llama 7B Instruct$0.200/M
CodeGemma 2B$0.100/M
CodeGemma 7B$0.200/M
CodeQwen 1.5 7B$0.200/M
Cogito v1 Preview Llama 3B$0.100/M
Cogito v1 Preview Llama 70B$0.900/M
Cogito v1 Preview Llama 8B$0.200/M
Cogito v1 Preview Qwen 14B$0.200/M
Cogito v1 Preview Qwen 32B$0.900/M
Cogito v2.1 671B$0.900/M
DeepSeek Coder 1.3B Base$0.100/M
DeepSeek Coder 33B Instruct$0.900/M
DeepSeek Coder 7B Base$0.200/M
DeepSeek Coder 7B Base v1.5$0.200/M
DeepSeek Coder 7B Instruct v1.5$0.200/M
DeepSeek R1 0528 Qwen3 8B$0.200/M
DeepSeek V3$0.560/M
DeepSeek V3 0324$0.560/M
DeepSeek V3.1 Terminus$0.560/M
Devstral 2 2512$0.900/M
Dolphin 2.6 Mixtral 8x7B$0.500/M
Dolphin 2.9.2 Qwen2 72B$0.900/M
ERNIE 4.5 21B A3B$0.900/M
ERNIE 4.5 300B A47B$0.900/M
FARE 20B$0.900/M
Gemma 2 9B$0.200/M
Gemma 2B$0.100/M
Gemma 3 1B$0.100/M
Gemma 3 27B$0.900/M
Gemma 3 4B$0.200/M
Gemma 4 26B A4B Instruct$0.900/M
Gemma 4 31B Instruct$0.900/M
Gemma 7B$0.200/M
Gemma 7B Instruct$0.200/M
GLM 4.7$0.600/M
GLM 5$1.00/M
GLM 5.1$1.40/M
GLM-4.7-Flash$0.600/M
GPT-OSS-20b$0.100/M
Hermes 2 Pro Mistral 7B$0.200/M
InternVL3 38B$0.900/M
InternVL3 78B$0.900/M
InternVL3 8B$0.200/M
KAT Dev 32B$0.900/M
KAT Dev 72B Exp$0.900/M
Kimi K2 Thinking$0.600/M
Kimi K2.5$0.600/M
Llama 2 13B$0.200/M
Llama 2 13B Chat$0.200/M
Llama 2 70B$0.900/M
Llama 2 7B$0.200/M
Llama 2 7B Chat$0.200/M
Llama 3 70B Instruct$0.900/M
Llama 3 70B Instruct (HF)$0.900/M
Llama 3 8B$0.200/M
Llama 3 8B Instruct$0.200/M
Llama 3 8B Instruct (HF)$0.200/M
Llama 3.1 405B Instruct$0.900/M
Llama 3.1 405B Instruct Long$0.900/M
Llama 3.1 70B Instruct$0.900/M
Llama 3.1 70B Instruct 1B$0.900/M
Llama 3.1 8B Instruct$0.200/M
Llama 3.1 Nemotron 70B Instruct$0.900/M
Llama 3.2 11B Vision Instruct$0.200/M
Llama 3.2 1B$0.100/M
Llama 3.2 1B Instruct$0.100/M
Llama 3.2 3B$0.100/M
Llama 3.2 3B Instruct$0.100/M
Llama 3.2 90B Vision Instruct$0.900/M
MedGemma 27B$0.900/M
meta-llama-llama-guard-2-8b$0.200/M
meta-llama-llama-guard-3-1b$0.100/M
meta-llama-llama-guard-3-8b$0.200/M
meta-llama-llamaguard-7b$0.200/M
MiniMax M2.7$0.300/M
Ministral 3 14B 2512$0.200/M
Ministral 3 3B 2512$0.100/M
Ministral 3 8B 2512$0.200/M
Mistral 7B$0.200/M
Mistral 7B Instruct v0.2$0.200/M
Mistral 7B Instruct v0.3$0.200/M
Mistral 7B OpenOrca$0.200/M
Mistral 7B v0.2$0.200/M
Mistral Small 24B Instruct 2501$0.900/M
Mixtral 8x22B$1.20/M
Mixtral 8x22B Instruct$1.20/M
Mixtral 8x7B$0.500/M
Mixtral 8x7B Instruct$0.500/M
Mixtral 8x7B Instruct (HF)$0.500/M
Molmo 2 4B$0.200/M
Molmo 2 8B$0.200/M
MythoMax 13B$0.200/M
Nemotron 3 Nano 30B A3B$0.900/M
Nemotron 3 Super 120B A12B$0.900/M
Nemotron Nano 12B 2 VL$0.200/M
Nemotron Nano 12B V2$0.200/M
Nemotron Nano 9B V2$0.200/M
Nous Capybara 7B v1.9$0.200/M
Nous Hermes 2 Mixtral 8x7B DPO$0.500/M
Nous Hermes Llama 2 13B$0.200/M
Nous Hermes Llama 2 70B$0.900/M
Nous Hermes Llama 2 7B$0.200/M
openai-gpt-oss-safeguard-120b$0.150/M
openai-gpt-oss-safeguard-20b$0.150/M
OpenChat 3.5 0106$0.200/M
OpenHermes 2 Mistral 7B$0.200/M
OpenHermes 2.5 Mistral 7B$0.200/M
Phind CodeLlama 34B Python v1$0.900/M
Phind CodeLlama 34B v1$0.900/M
Phind CodeLlama 34B v2$0.900/M
Pythia 12B$0.200/M
Qwen 1.5 72B Chat$0.900/M
Qwen2 72B Instruct$0.900/M
Qwen2 7B Instruct$0.200/M
Qwen2 VL 2B Instruct$0.100/M
Qwen2 VL 72B Instruct$0.900/M
Qwen2 VL 7B Instruct$0.200/M
Qwen2.5 0.5B Instruct$0.200/M
Qwen2.5 1.5B Instruct$0.200/M
Qwen2.5 14B$0.200/M
Qwen2.5 14B Instruct$0.200/M
Qwen2.5 32B$0.900/M
Qwen2.5 32B Instruct$0.900/M
Qwen2.5 72B$0.900/M
Qwen2.5 72B Instruct$0.900/M
Qwen2.5 7B$0.200/M
Qwen2.5 7B Instruct$0.200/M
Qwen2.5 Coder 0.5B$0.200/M
Qwen2.5 Coder 0.5B Instruct$0.200/M
Qwen2.5 Coder 1.5B$0.200/M
Qwen2.5 Coder 1.5B Instruct$0.200/M
Qwen2.5 Coder 14B$0.200/M
Qwen2.5 Coder 14B Instruct$0.200/M
Qwen2.5 Coder 32B$0.900/M
Qwen2.5 Coder 32B Instruct$0.900/M
Qwen2.5 Coder 32B Instruct 128K$0.900/M
Qwen2.5 Coder 32B Instruct 32K RoPE$0.900/M
Qwen2.5 Coder 32B Instruct 64K$0.900/M
Qwen2.5 Coder 3B$0.100/M
Qwen2.5 Coder 3B Instruct$0.100/M
Qwen2.5 Coder 7B$0.200/M
Qwen2.5 Coder 7B Instruct$0.200/M
Qwen2.5 Math 72B Instruct$0.900/M
Qwen2.5 VL 32B Instruct$0.900/M
Qwen2.5 VL 3B Instruct$0.100/M
Qwen2.5 VL 72B Instruct$0.900/M
Qwen2.5-VL 7B Instruct$0.200/M
Qwen3 0.6B$0.200/M
Qwen3 1.7B$0.200/M
Qwen3 14B$0.200/M
Qwen3 235B A22B$0.900/M
Qwen3 235B A22B Instruct 2507$0.900/M
Qwen3 235B A22B Thinking 2507$0.900/M
Qwen3 30B A3B$0.900/M
Qwen3 30B A3B Instruct 2507$0.900/M
Qwen3 30B A3B Thinking 2507$0.900/M
Qwen3 32B$0.900/M
Qwen3 4B$0.200/M
Qwen3 4B Instruct 2507$0.200/M
Qwen3 8B$0.200/M
Qwen3 Coder 30B A3B Instruct$0.900/M
Qwen3 Coder 480B A35B (exacto)$0.900/M
Qwen3 Coder 480B Instruct BF16$0.900/M
Qwen3 Next 80B A3B Instruct$0.900/M
Qwen3 Next 80B A3B Thinking$0.900/M
Qwen3 Omni 30B A3B Instruct$0.900/M
Qwen3 VL 235B A22B Instruct$0.900/M
Qwen3 VL 235B A22B Thinking$0.900/M
Qwen3 VL 30B A3B Instruct$0.150/M
Qwen3 VL 30B A3B Thinking$0.150/M
Qwen3 VL 32B Instruct$0.900/M
Qwen3 VL 8B Instruct$0.200/M
Qwen3.5 397B A17B$0.900/M
Qwen3.5 9B$0.200/M
Qwen3.5-122B-A10B$0.900/M
Qwen3.5-27B$0.900/M
Qwen3.5-35B-A3B$0.900/M
QwQ 32B$0.900/M
QwQ 32B Preview$0.900/M
R1 Distill Llama 70B$0.900/M
R1 Distill Llama 8B$0.200/M
R1 Distill Qwen 1.5B$0.200/M
R1 Distill Qwen 14B$0.200/M
R1 Distill Qwen 32B$0.900/M
R1 Distill Qwen 7B$0.200/M
Seed OSS 36B Instruct$0.900/M
Snorkel Mistral PairRM DPO$0.200/M
Toppy M 7B$0.200/M
Zephyr 7B Beta$0.200/M
Shared(6)
6
models available on both
Fireworks AISambaNova
206 total7 total
SambaNovaOnly on SambaNova(1)
Llama 4 Maverick$0.630/M

Full Provider Pricing

Fireworks AI
Fireworks AI Full Pricing
View all 206 models with detailed pricing

Frequently Asked Questions

Fireworks AI is cheaper on 3 out of 6 shared models. SambaNova is cheaper on 2 models. 1 models have the same price.
Fireworks AI and SambaNova share 6 models. Fireworks AI has 200 exclusive models, while SambaNova has 1 exclusive model.
Fireworks AI offers 206 models compared to SambaNova's 8. However, model count alone doesn't determine the better provider — consider pricing, latency, and which specific models you need.

Built by @aellman

Archive
Follow us:
Advertise | Terms of Service | Privacy Policy

2026 68 Ventures, LLC. All rights reserved.