How much does gpt-oss-120b cost per million tokens?

gpt-oss-120b costs $0.037 per million input tokens and $0.17 per million output tokens at list price.

What is the context window of gpt-oss-120b?

gpt-oss-120b accepts up to 131,072 tokens of context and returns up to 117,964 output tokens.

How much do 1,000 chat messages cost with gpt-oss-120b?

About $0.12, assuming 1,000 input + 500 output tokens per message.

Is there a cheaper alternative to gpt-oss-120b?

In the same price range, Qwen Qwen3.7 Flash ($0.03 / $0.13), DeepSeek DeepSeek V4 Flash 0423 ($0.042 / $0.084), Google Gemma 3 4B ($0.05 / $0.1) cost less per token. Quality differs: test on your own prompts.

Where can I buy OpenAI API credits for less?

Discount credit books resell OpenRouter usage below face value within their depth, OpenRouter adds a 5.5% card fee, and OpenAI sells its own credits at face value. The live table on this page ranks them for $100 of usage.

OpenAI · live price

gpt-oss-120b API pricing

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Small and cheap (under $1 per 1M)Tool callingReasoning

Input: $0.037; per 1M tokens
Output: $0.17; per 1M tokens
Cached input: –; per 1M tokens
Context: 131K; 118K max output

List price from OpenRouter, which passes OpenAI's price through without markup. Refreshed hourly. Released August 5, 2025. Model id openai/gpt-oss-120b.

What gpt-oss-120b costs in practice

At list price, before any batch or caching discount.

1,000 chat messages

$0.12

1,000 input + 500 output tokens each

1,000 RAG questions

$0.38

8,000 input + 500 output tokens each

100 coding-agent steps

$0.15

30,000 input + 2,000 output tokens each, no caching

gpt-oss-120b price history

No price change since we started tracking on 2026-10-01. We record prices daily; changes will show here.

gpt-oss-120b price by host

CoreWeave serves it below list price right now. Route to it to pay less on every token.

CoreWeave$0.03 in · $0.17 out · 131K ctx · 99.0% uptime 24h
DeepInfra$0.037 in · $0.17 out · 131K ctx · 99.1% uptime 24h
DekaLLM$0.03 in · $0.18 out · 131K ctx · 99.2% uptime 24h
AkashML$0.037 in · $0.187 out · 131K ctx · 100.0% uptime 24h
Crusoe$0.05 in · $0.25 out · 131K ctx · 99.9% uptime 24h
Novita$0.05 in · $0.25 out · 131K ctx · 99.2% uptime 24h
Mancer 2$0.05 in · $0.3 out · 131K ctx · 99.2% uptime 24h
Google$0.09 in · $0.36 out · 131K ctx · 55.1% uptime 24h
DigitalOcean$0.06 in · $0.42 out · 128K ctx · 100.0% uptime 24h
BaseTen$0.1 in · $0.5 out · 128K ctx · 99.5% uptime 24h
Amazon Bedrock$0.15 in · $0.6 out · 131K ctx · 99.8% uptime 24h
Nebius$0.15 in · $0.6 out · 131K ctx · 96.1% uptime 24h
SiliconFlow$0.15 in · $0.6 out · 131K ctx · 91.3% uptime 24h
Phala$0.15 in · $0.6 out · 131K ctx · 99.3% uptime 24h
Together$0.15 in · $0.6 out · 131K ctx · 98.1% uptime 24h
Groq$0.15 in · $0.6 out · 131K ctx · 99.2% uptime 24h
Parasail$0.1 in · $0.75 out · 131K ctx · 100.0% uptime 24h
Mara$0.15 in · $0.75 out · 131K ctx · 72.3% uptime 24h
SambaNova$0.14 in · $0.95 out · 131K ctx · 99.5% uptime 24h
Cerebras$0.35 in · $0.75 out · 131K ctx · 99.9% uptime 24h

Where to buy OpenAI credits for less

gpt-oss-120b costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:

#	Where you buy	You payYou pay for $100.00 of usage	vs list price	Price source
1	OrbioCardCheapest right now Credits from a discount book, plus a 5% platform fee and card processing, both included in the quote.	$85.10 incl. $2.60 card processing	-14.9%	live quote
2	smaaartCard Credits from a discount book, plus a 5% platform fee on face value. Card processing and taxes shown at checkout.	$95.00 + card processing and tax at checkout (not in this number)	-5.0%	live quote
3	Direct from the labCard Prepaid credits at face value (OpenAI, Anthropic, Google…). Taxes may apply.	$100.00 no top-up fee	list price	face value
4	OpenRouterCrypto 5% on crypto purchases. No markup on model prices.	$105.00 fees included	+5.0%	published fee
5	OpenRouterCard 5.5% on card purchases, $0.80 minimum. No markup on model prices.	$105.50 fees included	+5.5%	published fee

Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare

gpt-oss-120b cost calculator

Enter your monthly tokens to price your own usage.

Model$0.037 in / $0.17 out per 1M tokens · list price, liveInput tokens / month (millions)Output tokens / month (millions)

Usage at list price$3.55/ month(quotes below are for $5.00: purchases run from $5.00 to $10,000.00)

Cheaper alternatives to gpt-oss-120b

Other labs' models in the same price range or the one below, cheaper per token.

Model	Input / 1M	Output / 1M	Blended 3:1	Context
Qwen: Qwen3.7 Flash	$0.03	$0.13	$0.055	1M
DeepSeek: DeepSeek V4 Flash 0423	$0.042	$0.084	$0.052	1.0M
Google: Gemma 3 4B	$0.05	$0.1	$0.063	131K
Mistral: Mistral Small 3	$0.05	$0.08	$0.057	33K
Meta: Llama 3.1 8B Instruct	$0.05	$0.08	$0.057	131K
Mistral: Mistral Nemo	$0.019	$0.03	$0.022	131K

Other OpenAI models

Model	Input / 1M	Output / 1M	Blended 3:1	Context
gpt-oss-20b	$0.018	$0.09	$0.036	131K
GPT-5 Nano	$0.05	$0.4	$0.137	400K
GPT-5 Mini	$0.25	$2	$0.688	400K
GPT-5	$1.25	$10	$3.44	400K
o3 Pro	$20	$80	$35	200K
GPT-5 Pro	$15	$120	$41.25	400K

All OpenAI API prices