---
title: "gpt-oss-20b Cost Calculator - Replicate"
description: "Calculate the cost of using gpt-oss-20b from Replicate. Input costs $0.09 and output $0.36 per 1M tokens."
url: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/gpt-oss-20b"
markdown: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/gpt-oss-20b.md"
---

# gpt-oss-20b Cost Calculator - Replicate

> Calculate the cost of using gpt-oss-20b from Replicate. Input costs $0.09 and output $0.36 per 1M tokens.

## Important Links

- [View MCP Gateway](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources/mcp-gateway.md)
- [Features](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/#features)
- [Enterprise](https://www.getmaxim.ai/enterprise)
- [Pricing](https://www.getmaxim.ai/pricing)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://www.getmaxim.ai/book-a-demo)

## About gpt-oss-20b

gpt-oss-20b is a chat model from Replicate, one of 40 chat models they offer. It is priced at $0.09 per 1M input tokens and $0.36 per 1M output tokens, ranking 332 out of 3254 chat models by cost and cheaper than 89% of models in this category. gpt-oss-20b supports function calling.

## Pricing

Published Replicate pricing for gpt-oss-20b.

- **$0.09 / 1M tokens Input.**
- **$0.36 / 1M tokens Output.**

## Technical Specifications

- **Chat Mode.**

## Model Capabilities

gpt-oss-20b supports: Function Calling, System Messages.

## How Pricing Compares

At $0.09 per 1M input tokens and $0.36 per 1M output tokens, gpt-oss-20b ranks 332 out of 3254 chat models by input cost. It is more affordable compared to the median of $0.52 for chat models, and is cheaper than 89% of models in this category.

gpt-oss-20b is one of 40 Replicate chat models, with support for function calling.

| Model | Provider | Input $/1M | Output $/1M | vs gpt-oss-20b |
| --- | --- | --- | --- | --- |
| gpt-4.1-nano | Azure | $0.10 | $0.40 | +11% |
| gpt-4.1-nano-2025-04-14 | Azure | $0.10 | $0.40 | +11% |
| Phi-4-mini-instruct | Azure | $0.07 | $0.30 | -17% |
| Phi-4-multimodal-instruct | Azure | $0.08 | $0.32 | -11% |
| Phi-4-mini-reasoning | Azure | $0.07 | $0.30 | -17% |

## More from Replicate

- [llama-2-13b ($0.10/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/llama-2-13b.md)
- [llama-2-13b-chat ($0.10/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/llama-2-13b-chat.md)
- [gpt-4.1-nano ($0.10/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/gpt-4.1-nano.md)
- [llama-2-7b ($0.05/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/llama-2-7b.md)

## Related Resources

- [Replicate status](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/provider-status/replicate.md)
- [All Replicate pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate.md)

## FAQ

### Is gpt-oss-20b cheaper than gpt-4.1-nano?

Yes. gpt-oss-20b costs $0.09 per 1M input tokens compared to gpt-4.1-nano's $0.10 per 1M input tokens, making it 11% more affordable. Both are chat models and share support for vision, function calling, prompt caching, structured output.

### How does gpt-oss-20b pricing compare to the average chat model?

gpt-oss-20b input pricing is $0.09 per 1M tokens, which is 83% below the median of $0.52 for chat models. It ranks 332 out of 3254 chat models by input cost, making it cheaper than 89% of models in this category. For output, it costs $0.36 per 1M tokens compared to the median of $1.50.

### What makes gpt-oss-20b different from other Replicate models?

Among Replicate's 40 chat models, gpt-oss-20b ranks 9 by input cost.

### What are the best alternatives to gpt-oss-20b?

The most comparable chat models to gpt-oss-20b 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.

### How do I check if Replicate is down?

You can monitor Replicate service health in real time on the Bifrost Replicate Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.

### How do I calculate gpt-oss-20b costs?

gpt-oss-20b 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 $0.09 and generating 1M output tokens costs $0.36.

## Related Resources

- [All Replicate pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate.md)
- [LLM cost calculator](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator.md)
- [Model library](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library.md)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost)
- [Pricing: Bifrost pricing](https://www.getmaxim.ai/pricing)
- [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/enterprise)
- [Book a Demo: Bifrost demo](https://www.getmaxim.ai/book-a-demo)
- [Resources: Bifrost resources](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources.md)

---

*This is a markdown version of [https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/gpt-oss-20b](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/replicate/model/gpt-oss-20b) for AI/LLM consumption.*