BroadRouter

gpt-oss-120b vs gpt-oss-20b API pricing

Updated

gpt-oss-120b's lowest standard price we found is USD 0.03 per 1M input tokens and USD 0.17 per 1M output tokens (CoreWeave Forge). gpt-oss-20b's lowest standard price we found is USD 0.018 per 1M input tokens and USD 0.09 per 1M output tokens (AkashML, promotional). At 3 input tokens per output token, gpt-oss-120b costs 81% more than gpt-oss-20b (USD 0.065 vs USD 0.036 per 1M).

gpt-oss-120b and gpt-oss-20b are often compared as alternatives. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do gpt-oss-120b and gpt-oss-20b differ on price?

gpt-oss-120b and gpt-oss-20b prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

gpt-oss-120b and gpt-oss-20b API prices compared
Pricegpt-oss-120bgpt-oss-20b
Model pageOpenAI GPT OSS 120B
OpenAI · 21 providers
GPT OSS 20B
OpenAI · 10 providers
Cheapest standard price, blended 3:1USD 0.065
USD 0.03 in / USD 0.17 out at CoreWeave Forge
CoreWeave Forge page checked 2026-11-15
USD 0.036 lower promo
USD 0.018 in / USD 0.09 out at AkashML
AkashML page checked 2026-11-15
Cheapest inputUSD 0.03
CoreWeave Forge source
USD 0.018 lower promo
AkashML source
Cheapest cached inputUSD 0.015
Fireworks AI source
USD 0.007 lower
Google Vertex AI source
Cheapest outputUSD 0.17
CoreWeave Forge source
USD 0.09 lower promo
AkashML source
Cheapest non-promotional priceThe cheapest price is not promotional.USD 0.03 / USD 0.13
CoreWeave Forge, USD 0.055 blended source
Maker's own APIOpenAI publishes no paid standard price on its own API that we found.OpenAI publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.10 / USD 0.60
input / output, 21 prices
USD 0.04 / USD 0.19
input / output, 10 prices
Context window131,072 tokens, largest stated; from 128,000 at some providers131,072 tokens, largest stated
Providers with a standard price2110

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do gpt-oss-120b and gpt-oss-20b cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on gpt-oss-120b and gpt-oss-20b
Workloadgpt-oss-120bgpt-oss-20bDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 5.76
CoreWeave Forge
USD 2.75
AkashML
USD 3.01
gpt-oss-20b lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 9.75
CoreWeave Forge
USD 5.02
AkashML
USD 4.73
gpt-oss-20b lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 69.30
CoreWeave Forge
USD 26.73
AkashML
USD 42.57
gpt-oss-20b lower

gpt-oss-20b is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.59× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

gpt-oss-20b is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below gpt-oss-120b's, so the input:output ratio never changes the answer.

Price per 1M tokens of gpt-oss-120b and gpt-oss-20b at different input:output mixes
Input : output tokensgpt-oss-120bgpt-oss-20b
1 : 3 (long answers)USD 0.135
CoreWeave Forge
USD 0.072 lower
AkashML
1 : 1USD 0.10
CoreWeave Forge
USD 0.054 lower
AkashML
3 : 1 (the site’s blend)USD 0.065
CoreWeave Forge
USD 0.036 lower
AkashML
10 : 1 (retrieval, long prompts)USD 0.04273
CoreWeave Forge
USD 0.02455 lower
AkashML
30 : 1 (agents, big contexts)USD 0.03452
CoreWeave Forge
USD 0.02032 lower
AkashML

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do gpt-oss-120b and gpt-oss-20b cost per character in other languages?

Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the gpt-oss (o200k_harmony) tokenizer for gpt-oss-120b (the same one for both, so the gap equals the price gap):

Input cost per 1M characters by language, gpt-oss-120b and gpt-oss-20b
Contentgpt-oss-120bgpt-oss-20b
EnglishUSD 0.0064
CoreWeave Forge
USD 0.0064
CoreWeave Forge
Arabic MSAUSD 0.0096
CoreWeave Forge
USD 0.0096
CoreWeave Forge
Egyptian ArabicUSD 0.0100
CoreWeave Forge
USD 0.0100
CoreWeave Forge
HindiUSD 0.0097
CoreWeave Forge
USD 0.0097
CoreWeave Forge
ChineseUSD 0.023
CoreWeave Forge
USD 0.023
CoreWeave Forge
SpanishUSD 0.0068
CoreWeave Forge
USD 0.0068
CoreWeave Forge
CodeUSD 0.0076
CoreWeave Forge
USD 0.0076
CoreWeave Forge

From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

Check it on your own traffic

More comparisons: gpt-oss-120b vs Llama 3.3 70B · Nemotron 3 Super vs gpt-oss-120b · gpt-oss-120b vs DeepSeek V4.1 Flash · GPT-6 Luna vs gpt-oss-120b · gpt-oss-120b vs Qwen3.8 27B · gpt-oss-120b vs Gemma 4 26B A4B · Gemma 4 26B A4B vs gpt-oss-20b · gpt-oss-20b vs Qwen3.6 35B A3B · every gpt-oss-120b comparison · every gpt-oss-20b comparison · all 662 price comparisons

Questions

Is gpt-oss-120b cheaper than gpt-oss-20b?

No. On a blend of 3 input tokens to 1 output token, gpt-oss-20b costs USD 0.036 per 1M tokens and gpt-oss-120b USD 0.065, at each model's cheapest standard price. For input alone, gpt-oss-20b is cheaper (USD 0.018 against USD 0.03 per 1M); for output alone, gpt-oss-20b is (USD 0.09 against USD 0.17). This compares price only, not quality.

What do gpt-oss-120b and gpt-oss-20b cost per 1M tokens?

gpt-oss-120b: from USD 0.03 input and USD 0.17 output at CoreWeave Forge; median of 21 standard prices USD 0.10 / USD 0.60. gpt-oss-20b: from USD 0.018 input and USD 0.09 output at AkashML (promotional); median of 10 standard prices USD 0.04 / USD 0.19. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both gpt-oss-120b and gpt-oss-20b?

10 providers have a standard price for both: AkashML (USD 0.0745 and USD 0.036 at 3:1), CoreWeave Forge (USD 0.065 and USD 0.055 at 3:1), DeepInfra (USD 0.07025 and USD 0.0575 at 3:1), SiliconFlow (USD 0.15 and USD 0.075 at 3:1), Google Vertex AI (USD 0.1575 and USD 0.115 at 3:1), Featherless (USD 0.2625 and USD 0.0675 at 3:1), Parasail (USD 0.2625 and USD 0.08 at 3:1), Amazon Bedrock (USD 0.2625 and USD 0.1275 at 3:1), Groq (USD 0.2625 and USD 0.1312 at 3:1), Cloudflare Workers AI (USD 0.45 and USD 0.225 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.065 and USD 0.036.

Which is cheaper for a coding agent or a chatbot, gpt-oss-120b or gpt-oss-20b?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 69.30 a month on gpt-oss-120b (CoreWeave Forge) against USD 26.73 on gpt-oss-20b (AkashML), a difference of USD 42.57. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 5.76 a month on gpt-oss-120b (CoreWeave Forge) against USD 2.75 on gpt-oss-20b (AkashML), a difference of USD 3.01. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of gpt-oss-120b and gpt-oss-20b change?

gpt-oss-20b is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below gpt-oss-120b's, so the input:output ratio never changes the answer.

Do gpt-oss-120b and gpt-oss-20b have cached input pricing?

gpt-oss-120b from USD 0.015 per 1M cached input tokens (Fireworks AI; 4 of 21 standard prices list a discount). gpt-oss-20b from USD 0.007 per 1M cached input tokens (Google Vertex AI; 4 of 10 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, gpt-oss-120b or gpt-oss-20b?

Both go up to 131,072 tokens on the providers that state it.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity