Nebius AIvsTogether AI

Nebius AI vs Together AI

Compare pricing across 14 shared models. Nebius AI offers 21 models, Together AI offers 120.

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.

14
Shared Models
1
Nebius AI Cheaper
1
Together AI Cheaper
12
Same Price

Price Comparison — Shared Models

Model ↑Nebius AI Input Together AI Input Nebius AI Output Together AI Output Cheaper
DeepSeek V4 Pro $1.32 $1.32 $3.96 $3.96Same
DeepSeek V4.1 Flash $0.300 $0.300 $1.20 $1.20Same
deepseek-deepseek-v4-pro-0813 $1.32 $1.32 $3.96 $3.96Same
deepseek-deepseek-v4.1-flash-1017 $0.180 $0.300 $0.720 $1.20Nebius AI
GLM-5.2 $1.40 $1.40 $4.40 $4.40Same
GLM-5.3 $1.40 $1.40 $4.40 $4.40Same
GLM-5.3 Flash $0.150 $0.150 $0.500 $0.500Same
GPT-OSS-120b $0.150 $0.150 $0.600 $0.600Same
Inkling 2 Small $0.300 $0.300 $1.00 $1.00Same
Kimi K3 $3.00 $3.00 $15.00 $15.00Same
Kimi K3.1 Pro $2.00 $2.00 $10.00 $10.00Same
MiniMax-M3.1 Flash $0.150 $0.150 $0.600 $0.600Same
Muse Spark Open $1.25 $1.25 $4.25 $4.25Same
Nemotron 3.5 Super VL $0.300 $0.150 $0.900 $0.500Together AI

Model Coverage

Shared(14)
14
models available on both
Nebius AITogether AI
21 total117 total
Together AIOnly on Together AI(103)
Gemma 2 27B$0.800/M
Gemma 2B$0.100/M
Gemma 2B$0.100/M
Gemma 7B$0.200/M
GLM 4.5 Air$0.200/M
GLM 4.6$0.600/M
GLM 4.7$0.450/M
GLM 5.1$1.40/M
GPT-OSS-20b$0.050/M
Kimi K2.5$0.500/M
Kimi K2.6$1.20/M
MiniMax M2.7$0.300/M
Mixtral 8x7B$0.900/M
MythoMax 13B$0.300/M
Qwen1.5 0.5B$0.100/M
Qwen2.5 7B$0.300/M
Qwen3.5 9B$0.170/M
Qwen3.7 Plus$0.320/M
QwQ 32B$1.20/M
R1$3.00/M
R1 0528$3.00/M
Toppy M 7B$0.200/M
Trinity Mini$0.045/M

Full Provider Pricing

Frequently Asked Questions

Nebius AI and Together AI are evenly matched on pricing across 14 shared models.
Nebius AI and Together AI share 14 models. Nebius AI has 7 exclusive models, while Together AI has 103 exclusive models.
Together AI offers 120 models compared to Nebius AI's 21. However, model count alone doesn't determine the better provider — consider pricing, latency, and which specific models you need.