Calculate the cost of using Phi-4-mini-instruct from Wandb for your AI applications
Pricing data last updated:
Mode: Chat
Max: 128,000 tokens
Max: 128,000 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
Phi-4-mini-instruct is a chat model from Wandb, one of 16 chat models they offer. It is priced at $0.0080 per 1M input tokens and $0.04 per 1M output tokens, ranking 1 out of 2688 chat models by cost and cheaper than 100% of models in this category. It accepts up to 128K 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 128,000 input tokens. The maximum output length is 128,000 tokens.
At $0.0080 per 1M input tokens and $0.04 per 1M output tokens, Phi-4-mini-instruct ranks 1 out of 2688 chat models by input cost. It is more affordable compared to the median of $0.50 for chat models, and is cheaper than 100% of models in this category.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs Phi-4-mini-instruct |
|---|---|---|---|---|
| Qwen2.5-Coder-3B-Instruct | Nscale | $0.01 | $0.03 | +25% |
| Qwen2.5-Coder-7B-Instruct | Nscale | $0.01 | $0.03 | +25% |
| Qwen2.5-Coder-7B | Nebius | $0.01 | $0.03 | +25% |
Similar chat models from other providers
Yes. Phi-4-mini-instruct costs $0.0080 per 1M input tokens compared to Qwen2.5-Coder-3B-Instruct's $0.01 per 1M input tokens, making it 25% more affordable. Both are chat models.
Phi-4-mini-instruct input pricing is $0.0080 per 1M tokens, which is 98% below the median of $0.50 for chat models. It ranks 1 out of 2688 chat models by input cost, making it cheaper than 100% of models in this category. For output, it costs $0.04 per 1M tokens compared to the median of $1.44.
Among Wandb's 16 chat models, Phi-4-mini-instruct ranks 1 by input cost.
The most comparable chat models to Phi-4-mini-instruct are: Qwen2.5-Coder-3B-Instruct from Nscale ($0.01/1M input tokens); Qwen2.5-Coder-7B-Instruct from Nscale ($0.01/1M input tokens); Qwen2.5-Coder-7B from Nebius ($0.01/1M input tokens); ling-2.6-flash from OpenRouter ($0.01/1M 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.
Phi-4-mini-instruct 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 $0.0080 and generating 1M output tokens costs $0.04.