nebius

Nebius Token Factory

All current catalogue offerings from this provider. Documentation remains authoritative.

Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)

34 offerings

ModelContext / outputCapabilitiesLowest inputProviders
DeepSeek V4 Flashdeepseek-v4-flash · deepseek-flash1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0055fresh
DeepSeek V4 Prodeepseek-v4-pro · deepseek-thinking1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0055fresh
Kimi K2.7 Codekimi-k2.7-code · kimi-k2256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0047fresh
Kimi K2.5kimi-k2.5 · kimi-k2256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0049fresh
GLM 5.2glm-5.2 · glm1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0065fresh
MiniMax-M2.5minimax-m2.5 · minimax223KOutput 204K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0045fresh
Qwen3.5 397B A17Bqwen3.5-397b-a17b256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0026fresh
Qwen 2.5 VL 72B Instructqwen2.5-vl-72b-instruct128KOutput 128K
Tool callingReasoningImage inputJSONOpen weights
$0.25out $0.708fresh
Qwen3 32Bqwen3-32b128KOutput 131K
Tool callingReasoningJSONOpen weights
$0.00out $0.0019fresh
Qwen3 30b A3b Instruct 2507qwen3-30b-a3b-instruct-2507256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.0013fresh
gpt-oss-120bgpt-oss-120b128KOutput 128K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0055fresh
Qwen3 Next 80B A3B Thinkingqwen3-next-80b-a3b-thinking256KOutput 128K
Tool callingReasoningJSONOpen weights
$0.14out $0.6515fresh
Qwen3 235b A22B Instruct 2507qwen3-235b-a22b-instruct-2507256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.0020fresh
GLM-5glm-5 · glm205KOutput 205K
Tool callingReasoningJSONOpen weights
$0.00out $0.0043fresh
Kimi K3kimi-k3 · kimi-k31.05MOutput 1.05M
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0050fresh
Kimi K2.5 Fastkimi-k2.5-fast · kimi-k2256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.50out $2.502fresh
DeepSeek-V3.2-Expdeepseek-v3.2 · deepseek164KOutput 164K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0032fresh
Llama-3.3-70B-Instructllama-3.3-70b-instruct · llama128KOutput 128K
Tool callingReasoningJSONOpen weights
$0.00out $0.0026fresh
Nemotron 3 Super 120B A12Bnemotron-3-super-120b-a12b · nemotron1MOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.0010fresh
MiniMax-M3minimax-m3 · minimax1.05MOutput 1.05M
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0036fresh
Hermes 4 70Bhermes-4-70b128KOutput 128K
Tool callingReasoningJSONOpen weights
$0.13out $0.406fresh
gemma-3-27b-itgemma-3-27b-it256KOutput 128K
Tool callingReasoningImage inputJSONOpen weights
$0.080out $0.168fresh
hermes-4-405bhermes-4-405b128KOutput 128K
Tool callingReasoningJSONOpen weights
$0.30out $1.206fresh
nvidia-nemotron-3-nano-30b-a3bnvidia-nemotron-3-nano-30b-a3b256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.060out $0.243fresh
Qwen3-Embedding-8Bqwen3-embedding-8b · qwen40KOutput 32K
Open weights
$0.00out $0.007fresh
MiniMax-M2.5-fastminimaxai/minimax-m2.5-fast8KOutput 8K
Tool callingReasoningJSONOpen weights
$0.30out $1.201fresh
Llama-3.1-Nemotron-Ultra-253B-v1nvidia/llama-3_1-nemotron-ultra-253b-v1 · nemotron128KOutput 4K
Tool callingJSONOpen weights
$0.60out $1.801fresh
Nemotron 3 Nano Omninemotron-3-nano-omni · nemotron256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.060out $0.243fresh
gpt-oss-120b-fastopenai/gpt-oss-120b-fast8KOutput 8K
Tool callingReasoningJSONOpen weights
$0.10out $0.501fresh
DeepSeek-V3.2-fastdeepseek-ai/deepseek-v3.2-fast8KOutput 8K
Tool callingReasoningJSONOpen weights
$0.40out $2.001fresh
Qwen3.5-397B-A17B-fastqwen/qwen3.5-397b-a17b-fast8KOutput 8K
Tool callingReasoningJSONOpen weights
$0.60out $3.601fresh
Qwen3-Next-80B-A3B-Thinking-fastqwen/qwen3-next-80b-a3b-thinking-fast8KOutput 8K
Tool callingReasoningJSONOpen weights
$0.15out $1.201fresh
Qwen3-235B-A22B-Thinking-2507-fastqwen/qwen3-235b-a22b-thinking-2507-fast8KOutput 8K
Tool callingReasoningJSONOpen weights
$0.50out $2.001fresh
INTELLECT-3primeintellect/intellect-3128KOutput 8K
Tool callingJSONOpen weights
$0.20out $1.101fresh

Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.