tokenstat
tokenstat
Router

Nebius

Paid list rates under Nebius in the merged catalog. Free and $0 offers are omitted. Router rates are not the same as first-party list prices.

33 models · as of · All models · Plans

Showing 33 of 33

ModelInputOutputContextOffers
DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro
scoresreasoningtools
$1.75$3.501.0M1
GLM 5.2zai-org/GLM-5.2
scoresreasoningtools
$1.40$4.401.0M1
Kimi K3moonshotai/kimi-k3
scoresreasoningtools
$3$151.0M1
MiniMax M3minimax/minimax-m3
scoresreasoningtools
$0.3$1.201.0M1
Kimi K2.7 Codemoonshotai/kimi-k2.7-code
scoresreasoningtools
$0.95$4262K1
Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b
scoresreasoningtools
$0.3$0.91M1
Kimi K2.5moonshotai/Kimi-K2.5
scoresreasoningtools
$0.5$2.50262K1
Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B
scoresreasoningtools
$0.6$3.60262K1
Nemotron Nano 3 Omninvidia/Nemotron-3-Nano-Omni
reasoningtools
$0.06$0.24262K1
Moonshot: Kimi K2.5 Fastmoonshotai/Kimi-K2.5-fast
reasoningtools
$0.5$2.50262K1
GLM-5zai-org/GLM-5
reasoningtools
$1$3.20205K1
MiniMax-M2.5MiniMaxAI/MiniMax-M2.5
reasoningtools
$0.3$1.20205K1
NVIDIA Nemotron 3 Nano 30Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
scorestools
$0.06$0.24128K1
INTELLECT 3cortecs/intellect-3
reasoningtools
$0.2$1.10128K1
Qwen3 Embedding 8BQwen/Qwen3-Embedding-8B
$0.0141K1
Qwen3 235B A22B InstructQwen/Qwen3-235B-A22B-Instruct-2507
reasoningtools
$0.2$0.6262K1
Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507
tools
$0.1$0.3262K1
Qwen3 Next 80B A3B ThinkingQwen/Qwen3-Next-80B-A3B-Thinking
scoresreasoningtools
$0.15$1.20262K1
DeepSeek V3.2deepseek-ai/DeepSeek-V3.2
scoresreasoningtools
$0.3$0.45164K1
OpenAI: GPT OSS 120Bopenai/gpt-oss-120b
scoresreasoningtools
$0.15$0.6131K1
Hermes 4 405Bllmgateway/hermes-4-405b
reasoningtools
$1$3131K1
Hermes 4 70Bcortecs/hermes-4-70b
reasoningtools
$0.13$0.4131K1
Qwen3-235B-A22B-Thinking-2507-fastQwen/Qwen3-235B-A22B-Thinking-2507-fast
reasoningtools
$0.5$28K1
Qwen3-Next-80B-A3B-Thinking-fastQwen/Qwen3-Next-80B-A3B-Thinking-fast
reasoningtools
$0.15$1.208K1
Qwen3.5-397B-A17B-fastQwen/Qwen3.5-397B-A17B-fast
reasoningtools
$0.6$3.608K1
Gemma 3 27Bgoogle/gemma-3-27b-it
scorestools
$0.1$0.3262K1
Qwen3 32BQwen/Qwen3-32B
scoresreasoningtools
$0.1$0.3131K1
Llama 3.3 70B Instructmeta-llama/Llama-3.3-70B-Instruct
scoresreasoningtools
$0.13$0.4131K1
gpt-oss-120b-fastopenai/gpt-oss-120b-fast
reasoningtools
$0.1$0.58K1
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct
tools
$0.25$0.75128K1
Llama-3.1-Nemotron-Ultra-253B-v1nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
reasoningtools
$0.6$1.80128K1
DeepSeek-V3.2-fastdeepseek-ai/DeepSeek-V3.2-fast
reasoningtools
$0.4$28K1
MiniMax-M2.5-fastMiniMaxAI/MiniMax-M2.5-fast
reasoningtools
$0.3$1.208K1

Price this against your own usage

List rates are only half the story. The CLI measures what your coding harnesses actually spent on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash