Fireworks AI API pricing calculator

OpenAI GPT OSS 120B Pricing Calculator: Input and Output Token Costs

Estimate prompt, response, cached input, and volume costs for OpenAI GPT OSS 120B. Pricing verified 2026-06-25 from the provider source.

Quick estimate

No API key needed. Pick a model, paste your question, choose the answer length, and get a close cost estimate.

1. Choose AI model

$0.15/M input$0.6/M outputCache pricingBatchPriority

2. Your question or prompt

3. How long will the AI answer be?

Optional: paste the AI answer if you already have it

Your estimate will appear here.

Paste a prompt, choose an answer length, and calculate.

Pricing table

Input: $0.15 per 1M tokens

Output: $0.6 per 1M tokens

Cached input: $0.015 per 1M tokens

Context window: Provider-specific tokens

A 2,000 token prompt and 1,000 token answer costs about $0.000900 before tool add-ons.

Fireworks OSS hosted model.

How much does OpenAI GPT OSS 120B cost per 1M input tokens?

OpenAI GPT OSS 120B is seeded at $0.15 per 1M input tokens for the serverless_standard tier.

How much does OpenAI GPT OSS 120B cost per 1M output tokens?

OpenAI GPT OSS 120B is seeded at $0.6 per 1M output tokens.

Does OpenAI GPT OSS 120B support cached input pricing?

Yes. The cached input seed price is $0.015 per 1M tokens.