# GPT-OSS-20B pricing, and a cache that pays half as well > GPT-OSS-20B pricing on Groq is $0.075 per million input and $0.30 output. Its cached rate is about half input, not the 90% discount you expect. URL: https://getculpa.com/openai-gpt-oss-20b-pricing Last reviewed: 2026-08-01 Rates effective: 2026-07-02 ## Answer GPT-OSS-20B pricing on Groq is $0.075 per million input tokens and $0.30 per million output tokens, with a cached input rate at about half the input price rather than the ninety percent discount hosted frontier models offer. Caching still pays here, just far less. Culpa, a local-first LLM cost, margin, and forecast ledger, prices cached and uncached input separately so the difference is visible. ## Why this happens The advice to cache a repeated prefix is usually stated without a number attached, because on the hosted frontier models the number is always the same: a cached read costs a tenth of an input token. That single figure is what makes caching feel like a free win. Here a cached read costs about half an input token, so the same repeated prefix and the same hit rate return roughly half the saving. The work of restructuring a prompt around a cache breakpoint stays constant while the payoff halves, which changes whether it's worth doing. ## What this usually looks like - A caching project was justified on a 90% discount that doesn't apply to this model. - Nobody has checked what this model's cached rate actually is as a share of input. - The same caching advice is applied across every model in the stack without re-pricing. - Cached token share here has never been measured against the effort spent enabling it. ## Common mistakes - Assuming a cached read costs a tenth of input everywhere. Why it hurts: It's about half here, so a saving forecast built on 90% overstates by roughly fivefold. Do instead: Read the cached rate per model and express it as a share of that model's input rate. - Ranking caching work by prefix size alone. Why it hurts: The saving is prefix size times the discount, and the discount varies more than teams expect. Do instead: Rank by prefix size times discount times hit rate. The order usually changes. - Skipping caching here because the discount is smaller. Why it hurts: Half off a large repeated prefix is still a fifth or more of a total bill. Do instead: Price it. A smaller discount on a big repeated block often beats a big discount on a small one. ## Self-check - Divide this model's cached rate by its input rate. That fraction is your real discount. - Do the same for every other model you run and compare the spread. - Measure what share of your input on this model is a stable repeated prefix. - Multiply prefix share by discount by hit rate to get the saving before doing the work. - Confirm cached tokens are actually billing at the cached rate rather than at full input. ## The same cache, at two different discounts (illustrative) 60 million input tokens a month of which 45 million is a stable repeated prefix, plus 10 million output, on GPT-OSS-20B at real Groq rates. The prefix share and hit rate are modelled. Uncached: (60 x $0.075) + (10 x $0.30) = $4.50 + $3.00 = $7.50 Cached prefix at about half input: (45 x $0.038) + (15 x $0.075) + (10 x $0.30) = $1.71 + $1.13 + $3.00 = $5.84 Saving = $1.66, which is 22% of the total Had the cached rate been 90% off, the prefix would cost 45 x $0.0075 = $0.34 instead of $1.71 That would have saved $3.04, or 41% of the total, nearly twice as much Same prefix, same hit rate, same engineering effort, and the payoff is 22% here against 41% on a ninety-percent cache. The discount is the variable nobody quotes and it decides whether the work is worth scheduling. ## Cost figures Every figure carries its confidence and its source. No figure on this site is provider-reported. - $0.075 / $0.30 per million — GPT-OSS-20B input and output rates on Groq [calculated] Source: Price book row for groq/openai/gpt-oss-20b, $0.000075 and $0.0003 per 1k, effective 2026-07-02, re-verified against Groq's rendered pricing page 2026-08-01. - 22% to 41% — modelled saving on the same prefix at this model's cached discount against a ninety-percent one [estimated] Source: Both endpoints from the teardown arithmetic at real Groq rates. A range because prefix share and hit rate are modelled. ## FAQ Q: How much does GPT-OSS-20B cost on Groq? A: $0.075 per million input tokens and $0.30 per million output, re-verified against Groq's pricing page on 2026-08-01. The cached input rate sits at about half the input price. Q: Why does the cached rate matter so much? A: Because the saving from caching is the prefix share multiplied by the discount. A model discounting cached reads by 90% returns nearly twice what a model discounting by half returns, on identical prompts and identical effort. Q: Is caching still worth it at half off? A: Often, yes. Half off a prefix that makes up three quarters of your input still takes about a fifth off the total. It's smaller than the headline everyone quotes, which is the reason to price it rather than assume it. ## Sources - Groq pricing: https://groq.com/pricing Run the free Cost Leak Scan: https://app.getculpa.com/scan?source=pseo&slug=openai-gpt-oss-20b-pricing&cluster=model_pricing Machine-readable index of every guide: https://getculpa.com/api/pages Human-readable index of every guide: https://getculpa.com/guides Site overview: https://app.getculpa.com/llms.txt Privacy: Culpa runs on your infrastructure. Your prompts and responses never leave it. Culpa counts calls to run your plan, and it fails open, so if it ever breaks your app keeps running.