Calculate the cost of using Qwen3-4B from Nebius for your AI applications
Pricing data last updated:
Mode: Chat
Max: 32,768 tokens
Max: 32,768 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
Qwen3-4B is a chat model from Nebius, one of 27 chat models they offer. It is priced at $0.08 per 1M input tokens and $0.24 per 1M output tokens, ranking 196 out of 2292 chat models by cost and cheaper than 91% of models in this category. Qwen3-4B supports function calling. It accepts up to 33K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 32,768 input tokens. The maximum output length is 32,768 tokens.
At $0.08 per 1M input tokens and $0.24 per 1M output tokens, Qwen3-4B ranks 196 out of 2292 chat models by input cost. It is more affordable compared to the median of $0.55 for chat models, and is cheaper than 91% of models in this category.
Qwen3-4B is one of 27 Nebius chat models, with support for function calling.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs Qwen3-4B |
|---|---|---|---|---|
| gpt-4.1-nano | Azure | $0.10 | $0.40 | +25% |
| gpt-4.1-nano-2025-04-14 | Azure | $0.10 | $0.40 | +25% |
| Phi-4-mini-instruct | Azure | $0.07 | $0.30 | -6% |
Similar chat models from other providers
Yes. Qwen3-4B costs $0.08 per 1M input tokens compared to gpt-4.1-nano's $0.10 per 1M input tokens, making it 25% more affordable. Both are chat models and share support for vision, function calling, prompt caching, structured output.
Qwen3-4B input pricing is $0.08 per 1M tokens, which is 85% below the median of $0.55 for chat models. It ranks 196 out of 2292 chat models by input cost, making it cheaper than 91% of models in this category. For output, it costs $0.24 per 1M tokens compared to the median of $1.50.
Among Nebius's 27 chat models, Qwen3-4B ranks 7 by input cost.
The most comparable chat models to Qwen3-4B are: gpt-4.1-nano from Azure ($0.10/1M input tokens); gpt-4.1-nano-2025-04-14 from Azure ($0.10/1M input tokens); Phi-4-mini-instruct from Azure ($0.07/1M input tokens); Phi-4-multimodal-instruct from Azure ($0.08/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
Qwen3-4B is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.08 and generating 1M output tokens costs $0.24.
