Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

Nebius API

Open in consoleI need inference
  • 16Models
  • 8Labs
  • 1.05MMax context
  • $0.06/ $0.24From, per 1M in / out

Pricing

ModelLabContextInput / 1MCached / 1MOutput / 1MProviders
Kimi K3.1 Promoonshotai/kimi-k3.1-proMoonshot AI1.05M$2.00$0.20$10.005
Beam 1.0 501B A23Breflection/beam-1.0-501b-a23bReflection AI1.05M$0.25$0.05$1.001
Muse Spark Openmeta/muse-spark-openMeta1.05M$1.25$0.15$4.252
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashDeepSeek1.05M$0.30$0.01$1.209
GLM 5.3 Flashz-ai/glm-5.3-flashZ.ai1.05M$0.15$0.03$0.5012
GLM 5.3z-ai/glm-5.3Z.ai1.05M$1.40$0.26$4.4012
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813DeepSeek1.05M$1.32$0.04$3.966
Qwen3.8 27Bqwen/qwen3.8-27bQwen262K$0.45$0.10$3.008
Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightningNVIDIA1.05M$0.06$0.03$0.242
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731DeepSeek1.05M$0.14$0.01$0.289
Kimi K3moonshotai/kimi-k3Moonshot AI1.05M$3.00$0.30$15.0010
Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55bNVIDIA1.05M$1.00$0.12$3.002
MiniMax M3minimax/minimax-m3MiniMax524K$0.30$0.06$1.203
Kimi K2.6moonshotai/kimi-k2.6Moonshot AI262K$0.95$0.16$4.005
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17bQwen262K$0.60$0.12$3.603
Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507Qwen262K$0.20$0.05$0.601

Nebius's price, USD, as of November 5, 2026. Live prices

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3",
    "messages": [{ "role": "user", "content": "Hello" }],
    "max_tokens": 1024,
    "provider": { "only": ["nebius-chat"] }
  }'

FAQ

How do I send a request to Nebius?

Routing tries providers cheapest first, by input plus output price, so Nebius serves a model where it is the cheapest and otherwise as a fallback. To send a request to Nebius first, name it in provider.only or provider.order as "nebius-chat".

How much does Nebius cost on RouterPlus?

You pay Nebius's own price for the model. Nebius's lowest input price is $0.06 per million tokens (Nemotron 3.5 Lightning) and its lowest output price is $0.24 per million tokens (Nemotron 3.5 Lightning). Prices as of November 5, 2026.

Which models does Nebius serve?

Kimi K3.1 Pro, Beam 1.0 501B A23B, Muse Spark Open, DeepSeek V4.1 Flash, GLM 5.3 Flash, GLM 5.3, DeepSeek V4 Pro 0813, Qwen3.8 27B, Nemotron 3.5 Lightning, DeepSeek V4 Flash 0731, Kimi K3, Nemotron 3 Ultra, MiniMax M3, Kimi K2.6, Qwen3.5 397B A17B and Qwen3 235B A22B Instruct 2507.

Does Nebius keep my prompts?

Nebius declares no prompt retention in its RouterPlus listing, per its published policy.

Route to Nebius with one key

Open in consoleI need inference