veqen
Sign in Start free

Nebius API pricing

62 Nebius models: text, embeddings, from price book 2026-10-22.

Billing rules Veqen applies

  • Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.

Also recognized as: nebius_ai (framework, gateway and OpenTelemetry names).

Reconcile your bill

Nebius doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.

Prices come from Nebius's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.

Text 58 models

ModelInputOutputCached inputBatch inputContextStatus
Qwen/Qwen2.5-Coder-7B$0.01$0.03——32.8K
Qwen/Qwen2-VL-7B-Instruct$0.02$0.06——131.1K
meta-llama/Llama-Guard-3-8B$0.02$0.06——128K
meta-llama/Meta-Llama-3.1-8B-Instruct$0.02$0.06——128K
mistralai/Mistral-Nemo-Instruct-2407$0.04$0.12——128K
Qwen/Qwen2.5-32B-Instruct$0.06$0.20——128K
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B$0.06$0.24——262.1K
nvidia/Nemotron-3-Nano-Omni$0.06$0.24——262.1K
nvidia/Nemotron-3_5-Lightning$0.06$0.24——1M
Qwen/Qwen3-14B$0.08$0.24——32.8K
Qwen/Qwen3-4B$0.08$0.24——32.8K
Qwen/Qwen3-30B-A3B$0.10$0.30——32.8K
Qwen/Qwen3-30B-A3B-Instruct-2507$0.10$0.30——262.1K
Qwen/Qwen3-32B$0.10$0.30——41K
google/gemma-3-27b-it$0.10$0.30——110K
nvidia/Cosmos3-Super-Reasoner$0.10$0.30——262.1K
nvidia/Llama-3.3-Nemotron-Super-49B-v1$0.10$0.40——131.1K
NousResearch/Hermes-4-70B$0.13$0.40——131.1K
Qwen/Qwen2-VL-72B-Instruct$0.13$0.40——131.1K
Qwen/Qwen2.5-72B-Instruct$0.13$0.40——128K
meta-llama/Llama-3.3-70B-Instruct$0.13$0.40——131.1K
meta-llama/Meta-Llama-3.1-70B-Instruct$0.13$0.40——128K
deepseek-ai/DeepSeek-V4-Flash$0.14$0.28——1M
deepseek-ai/DeepSeek-V4-Flash-0731$0.14$0.28——1M
Qwen/QwQ-32B$0.15$0.45——32.8K
Qwen/Qwen3-Next-80B-A3B-Thinking$0.15$1.20——128K
openai/gpt-oss-120b$0.15$0.60——131.1K
zai-org/GLM-5.3-Flash$0.15$0.50——1M
Qwen/Qwen3-235B-A22B$0.20$0.60——262.1K
Qwen/Qwen3-235B-A22B-Instruct-2507$0.20$0.60——262.1K
Qwen/Qwen2.5-VL-72B-Instruct$0.25$0.75——32K
deepseek-ai/DeepSeek-R1-Distill-Llama-70B$0.25$0.75——128K
reflection/beam$0.25$1.00——1M
MiniMaxAI/MiniMax-M2.5$0.30$1.20——196.6K
MiniMaxAI/MiniMax-M3$0.30$1.20——1M
deepseek-ai/DeepSeek-V4.1-Flash$0.30$1.20——1M
nvidia/nemotron-3-super-120b-a12b$0.30$0.90——262.1K
Qwen/Qwen3.8-27B$0.45$3.00——262.1K
deepseek-ai/DeepSeek-V3$0.50$1.50——128K
deepseek-ai/DeepSeek-V3-0324$0.50$1.50——128K
Qwen/Qwen3.5-397B-A17B$0.60$3.60——262.1K
nvidia/Llama-3.1-Nemotron-Ultra-253B-v1$0.60$1.80——128K
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1$0.60$1.80——131.1K
openbmb/MiniCPM-V-4_5$0.658$1.11——32K
deepseek-ai/DeepSeek-R1$0.80$2.40——128K
deepseek-ai/DeepSeek-R1-0528$0.80$2.40——164K
moonshotai/Kimi-K2.6$0.95$4.00——262.1K
moonshotai/Kimi-K2.7-Code$0.95$4.00——262.1K
NousResearch/Hermes-3-Llama-3.1-405B$1.00$3.00——128K
NousResearch/Hermes-4-405B$1.00$3.00——131.1K
meta-llama/Meta-Llama-3.1-405B-Instruct$1.00$3.00——128K
nvidia/Nemotron-3-Ultra-550b-a55b$1.00$3.00——1M
deepseek-ai/DeepSeek-V4-Pro-0813$1.32$3.96——979K
zai-org/GLM-5.1$1.40$4.40——202.8K
zai-org/GLM-5.2$1.40$4.40——1M
zai-org/GLM-5.3$1.40$4.40——1M
deepseek-ai/DeepSeek-V4-Pro$1.75$3.50——1M
moonshotai/Kimi-K3$3.00$15.00——1M

Embeddings 4 models

ModelPriceStatus
BAAI/bge-en-icl$0.01 per 1M tokens
BAAI/bge-multilingual-gemma2$0.01 per 1M tokens
Qwen/Qwen3-Embedding-8B$0.01 per 1M tokens
intfloat/e5-mistral-7b-instruct$0.01 per 1M tokens