Cloud platform
Nebius Token Factory API pricing: every model, compared
We track 45 Nebius Token Factory prices that other providers also sell. Nebius Token Factory has the lowest listed price for 16 of them; for the rest, the table shows how much more you pay than at the cheapest provider.
Standard list prices in USD. Last price change Oct 3, 2026. How we rank.
LLMs, most widely offered first
Nebius Token Factory LLM prices vs the cheapest provider
| Model | Rank | Cheapest elsewhere | Input / 1M | Output / 1M | Context | Source |
|---|---|---|---|---|---|---|
| gpt-oss-120b | #7 of 18 | W&B Inference (CoreWeave)you pay 304% more here | $0.15 | $0.60 | 131K | Pricing page |
| GLM-5.2 | #4 of 13 | DeepInfrayou pay 85% more here | $1.40 | $4.40 | 1M | Pricing page |
| Llama-3.3-70B-Instruct | #1 of 13 | Nebius Token Factory is cheapest | $0.13 | $0.40 | 131K | Pricing page |
| GLM-5.3 | #4 of 12 | DeepInfrayou pay 28% more here | $1.40 | $4.40 | 1M | Pricing page |
| GLM-5.3-Flash | #1 of 11 | Nebius Token Factory is cheapest | $0.15 | $0.50 | 1M | Pricing page |
| DeepSeek V4 Flash 0731 | #4 of 10 | DeepInfrayou pay 67% more here | $0.14 | $0.28 | 1M | Pricing page |
| Llama-3.1-8B-Instruct | #3 of 10 | Novita AIyou pay 9% more here | $0.02 | $0.06 | 128K | Pricing page |
| Kimi K3 | #3 of 9 | SiliconFlowyou pay 11% more here | $3.00 | $15.00 | 1M | Pricing page |
| DeepSeek V4 Pro 0813 | #3 of 8 | DeepInfrayou pay 22% more here | $1.32 | $3.96 | 979K | Pricing page |
| DeepSeek-R1 | #4 of 8 | SiliconFlowyou pay 30% more here | $0.80 | $2.40 | 128K | Pricing page |
| DeepSeek-V3 | #4 of 8 | SiliconFlowyou pay 71% more here | $0.50 | $1.50 | 128K | Pricing page |
| DeepSeek-V4.1-Flash | #3 of 8 | DeepInfrayou pay 150% more here | $0.30 | $1.20 | 1M | Pricing page |
| Kimi K2.6 | #5 of 8 | W&B Inference (CoreWeave)you pay 28% more here | $0.95 | $4.00 | 262K | Pricing page |
| Kimi K2.7 Code | #4 of 8 | DeepInfrayou pay 26% more here | $0.95 | $4.00 | 262K | Pricing page |
| DeepSeek-V4-Flash | #3 of 7 | DeepInfrayou pay 56% more here | $0.14 | $0.28 | 1M | Pricing page |
| GLM-5.1 | #4 of 7 | DeepInfrayou pay 29% more here | $1.40 | $4.40 | 203K | Pricing page |
| llama-3.1-70b-instruct | #1 of 7 | Nebius Token Factory is cheapest | $0.13 | $0.40 | 128K | Pricing page |
| MiniMax-M3 | #3 of 7 | W&B Inference (CoreWeave)you pay 27% more here | $0.30 | $1.20 | 1M | Pricing page |
| Qwen3 32B | #3 of 7 | DeepInfrayou pay 15% more here | $0.10 | $0.30 | 41K | Pricing page |
| Qwen3.8 27B | #4 of 7 | DeepInfrayou pay 4% more here | $0.45 | $3.00 | 262K | Pricing page |
| DeepSeek V4 Pro | #6 of 6 | DeepInfrayou pay 35% more here | $1.75 | $3.50 | 1M | Pricing page |
| DeepSeek-R1-0528 | #4 of 6 | Lambdayou pay 300% more here | $0.80 | $2.40 | 164K | Pricing page |
| deepseek-r1-distill-llama-70b | #2 of 6 | DeepInfrayou pay 25% more here | $0.25 | $0.75 | 128K | Pricing page |
| Qwen2.5-72B-Instruct | #1 of 6 | Nebius Token Factory is cheapest | $0.13 | $0.40 | 128K | Pricing page |
| Qwen3 235B A22B Instruct 2507 | #3 of 6 | DeepInfrayou pay 46% more here | $0.20 | $0.60 | 262K | Pricing page |
| deepseek-v3-0324 | #4 of 5 | Lambdayou pay 150% more here | $0.50 | $1.50 | 128K | Pricing page |
| Gemma-3-27b-it | #3 of 5 | DeepInfrayou pay 50% more here | $0.10 | $0.30 | 110K | Pricing page |
| Qwen3.5 397B-A17B | #2 of 5 | DeepInfrayou pay 24% more here | $0.60 | $3.60 | 262K | Pricing page |
| Qwq 32B | #3 of 5 | Nscaleyou pay 22% more here | $0.15 | $0.45 | 33K | Pricing page |
| Llama Guard 3 8B | #1 of 4 | Nebius Token Factory is cheapest | $0.02 | $0.06 | 128K | Pricing page |
| llama-3.1-405b-instruct | #1 of 4 | Nebius Token Factory is cheapest | $1.00 | $3.00 | 128K | Pricing page |
| MiniMax-M2.5 | #1 of 4 | Nebius Token Factory is cheapest | $0.30 | $1.20 | 197K | Pricing page |
| mistral-nemo-instruct-2407 | #2 of 4 | DeepInfrayou pay 176% more here | $0.04 | $0.12 | 128K | Pricing page |
| qwen2.5-vl-72b-instruct | #1 of 4 | Nebius Token Factory is cheapest | $0.25 | $0.75 | 32K | Pricing page |
| Qwen3-14B | #1 of 4 | Nebius Token Factory is cheapest | $0.08 | $0.24 | 33K | Pricing page |
| qwen3-next-80b-a3b-thinking | #1 of 4 | Nebius Token Factory is cheapest | $0.15 | $1.20 | 128K | Pricing page |
| Qwen3 30B A3B | #1 of 3 | Nebius Token Factory is cheapest | $0.10 | $0.30 | 33K | Pricing page |
| qwen3-235b-a22b | #2 of 3 | DeepInfrayou pay 11% more here | $0.20 | $0.60 | 262K | Pricing page |
| Qwen3-30B-A3B-Instruct-2507 | #2 of 3 | SiliconFlowyou pay 5% more here | $0.10 | $0.30 | 262K | Pricing page |
| hermes-3-llama-3.1-405b | #2 of 2 | DeepInfrayou pay 50% more here | $1.00 | $3.00 | 128K | Pricing page |
| qwen2-vl-72b-instruct | #1 of 2 | Nebius Token Factory is cheapest | $0.13 | $0.40 | 131K | Pricing page |
| qwen2-vl-7b-instruct | #1 of 2 | Nebius Token Factory is cheapest | $0.02 | $0.06 | 131K | Pricing page |
| qwen2.5-32b-instruct | #1 of 2 | Nebius Token Factory is cheapest | $0.06 | $0.20 | 128K | Pricing page |
| qwen2.5-coder-7b | #1 of 2 | Nebius Token Factory is cheapest | $0.01 | $0.03 | 33K | Pricing page |
| qwen3-4b | #1 of 2 | Nebius Token Factory is cheapest | $0.08 | $0.24 | 33K | Pricing page |
Rank and difference use the blended price (3 input : 1 output tokens). Equal prices share a rank.
Ranked for your volume
gpt-oss-120b monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 W&B Inference (CoreWeave)lowest for your volumePricing page | $0.64 | $0.03 | $0.17 | Not listed | 131,000 |
2 DeepInfraPricing page | $0.71 | $0.037 | $0.17 | Not listed | 131,072 |
3 Novita AIPricing page | $1.00 | $0.05 | $0.25 | Not listed | 131,072 |
4 SiliconFlowPricing page | $1.40 | $0.05 | $0.45 | Not listed | 131,000 |
5 OVHcloud AI EndpointsBilled in EUR: €0.08 input, €0.40 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $1.79 | $0.0894 | $0.4469 | Not listed | 131,000 |
6 BasetenPricing page | $2.00 | $0.10 | $0.50 | $0.10 | 128,072 |
7 Amazon BedrockPricing page | $2.70 | $0.15 | $0.60 | Not listed | 128,000 |
8 Fireworks AIPricing page | $2.70 | $0.15 | $0.60 | $0.015 | 131,072 |
9 Microsoft Azure AI FoundryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
10 Nebius Token FactoryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Ranked #1? Show it on your site
Nebius Token Factory has the lowest blended list price (3 input : 1 output tokens) for these models. The badge states that basis, updates daily and always shows the current rank, whatever it is; ranking is by price only.
<a href="https://aiselect.online/models/llama3-3-70b-instruct"><img src="https://aiselect.online/badge/llama3-3-70b-instruct/nebius.svg" alt="Llama-3.3-70B-Instruct API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/glm-5-3-flash"><img src="https://aiselect.online/badge/glm-5-3-flash/nebius.svg" alt="GLM-5.3-Flash API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/llama-3-1-70b-instruct"><img src="https://aiselect.online/badge/llama-3-1-70b-instruct/nebius.svg" alt="llama-3.1-70b-instruct API price ranking on AISelect" height="20"></a>Compare more
Other providers
Alibaba Cloud Model Studio, Amazon Bedrock, Anthropic, Baseten, Cloudflare Workers AI, Cohere, DeepInfra, DeepSeek, fal, Fireworks AI, FriendliAI, Google Cloud Vertex AI, Google Gemini API, IBM watsonx.ai, Lambda, Microsoft Azure AI Foundry, Mistral AI, Moonshot AI, Novita AI, Nscale, OpenAI, Oracle Cloud Generative AI, OVHcloud AI Endpoints, Perplexity, Replicate, SambaNova, Scaleway, SiliconFlow, Together AI, W&B Inference (CoreWeave), xAI, Z.ai