BroadRouter
Get started

OpenAI GPT OSS 120B API pricing

Updated

Among the 21 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for OpenAI GPT OSS 120B is CoreWeave Forge at USD 0.03 per 1M input tokens and USD 0.17 per 1M output tokens. The median across 21 standard prices is USD 0.10 / USD 0.60. Each price is read from the provider's own pricing page.

OpenAI · slug gpt-oss-120b · up to 131,072 tokens of context · 21 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2025-08-06 (24 archived price points, 1 list-price change): LLM API price history.

Does OpenAI sell OpenAI GPT OSS 120B directly?

OpenAI publishes no price for OpenAI GPT OSS 120B on its own API that we could find, so this page compares hosts only.

OpenAI GPT OSS 120B model facts

Facts from OpenAI's model card for openai/gpt-oss-120b and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

OpenAI GPT OSS 120B: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes. The weights are in a public Hugging Face repository (openai/gpt-oss-120b) with no access gate.Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": false, 22 .safetensors files listed”
LicenceApache 2.0 (apache-2.0)OpenAI model card metadata, checked 2026-11-16
Quote
“license: apache-2.0”
Total parameters117BOpenAI model card, checked 2026-11-16
Quote
“(117B parameters with 5.1B active parameters)”
Active parameters per token5.1BOpenAI model card, checked 2026-11-16
Quote
“(117B parameters with 5.1B active parameters)”
Context lengthNot found on OpenAI's model card when we read it; see the context column in the price tablechecked 2026-11-16
Input and outputText in, text out (the card's task tag is text-generation)OpenAI model card metadata, checked 2026-11-16
Quote
“pipeline_tag: text-generation”
Tool callingYesOpenAI model card, checked 2026-11-16
Quote
“Use the models’ native capabilities for function calling”
First published on Hugging Face (not necessarily the release date)2025-08-04Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2025-08-04T22:33:06.000Z"”

OpenAI GPT OSS 120B price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 6.9× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

OpenAI GPT OSS 120B API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1CoreWeave Forge cheapest
openai/gpt-oss-120b
Notes and source quote
“OpenAI GPT OSS 120B $0.03 $0.17 -”
USD 0.03not publishedUSD 0.17USD 0.065131,072not statedCoreWeave Forge page
checked 2026-11-15
re-checked 2026-11-16
2DeepInfra
openai/gpt-oss-120b
Notes and source quote
“$0.037 in $0.17 out / 1M tokens”
USD 0.037not publishedUSD 0.17USD 0.07025131,072BFLOAT16DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
3AkashML promo
openai/gpt-oss-120b
Notes and source quote

Labelled "Limited Trial" on AkashML.

“Price (per 1M Tokens) Input Output Cache Read GPT OSS 120B $0.037 $0.187 $0.037”
USD 0.037USD 0.037USD 0.187USD 0.0745131,072not statedAkashML page
checked 2026-11-15
re-checked 2026-11-16
4Crusoe Cloud
openai/gpt-oss-120b
Notes and source quote
“GPT-OSS 120B $0.05 $0.25 $0.05”
USD 0.05USD 0.05USD 0.25USD 0.10128,000not statedCrusoe Cloud page
checked 2026-11-15
re-checked 2026-11-16
5Novita AI
openai/gpt-oss-120b
Notes and source quote
“OpenAI GPT OSS 120B 128K $0.05 /Mt $0.25 /Mt”
USD 0.05not publishedUSD 0.25USD 0.10131,072not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
6Venice
openai-gpt-oss-120b
Notes and source quote
“| OpenAI GPT OSS 120B | `openai-gpt-oss-120b` | $0.07 | $0.30 | — | — | Private |”
USD 0.07not publishedUSD 0.30USD 0.1275128,000not statedVenice page
checked 2026-11-15
re-checked 2026-11-16
7SiliconFlow
Notes and source quote

Context shown as 131K. Page lists a cached-input price higher than the input price; recorded as shown.

“gpt-oss-120b 131K $0.05 $0.075 $0.45”
USD 0.05USD 0.075USD 0.45USD 0.15131,072not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
8Google Vertex AI
gpt-oss-120b
Notes and source quote
“gpt-oss-120b Input $0.09 … Output $0.36”
USD 0.09not publishedUSD 0.36USD 0.1575not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
9Baseten
openai/gpt-oss-120b
Notes and source quote
“GPT OSS 120B $0.10 — $0.50”
USD 0.10not publishedUSD 0.50USD 0.20not statednot statedBaseten page
checked 2026-11-14
re-checked 2026-11-16
10DigitalOcean
Notes and source quote
“gpt-oss-120b — Processing modePrompt lengthInputOutput: Standard All prompts$0.10$0.70”
USD 0.10not publishedUSD 0.70USD 0.25not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
11Amazon Bedrock
Notes and source quote

Standard tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“gpt-oss-120b $0.15 $0.60”
USD 0.15not publishedUSD 0.60USD 0.2625not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
12Featherless
openai/gpt-oss-120b
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.15 / CACHED $0.02 / OUTPUT $0.6”
USD 0.15USD 0.02USD 0.60USD 0.2625131,072FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
13Fireworks AI
accounts/fireworks/models/gpt-oss-120b
Notes and source quote

Priced in the serverless pricing table; not shown in the serverless model library filter on 2026-11-14.

“OpenAI GPT OSS 120B | $0.15 / $0.015 / $0.60 | $0.18 / $0.018 / $0.72”
USD 0.15USD 0.015USD 0.60USD 0.2625not statednot statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
14Groq
openai/gpt-oss-120b
Notes and source quote
“$0.15 input$0.60 output | Cached Input $0.075”
USD 0.15USD 0.075USD 0.60USD 0.2625131,072not statedGroq page
checked 2026-11-14
re-checked 2026-11-16
15Microsoft Azure
Notes and source quote

Azure OpenAI page, "Open Source Models" table (no deployment type stated; us-east value in the page data).

“gpt-oss-120b Input: $0.15 | Output: $0.60”
USD 0.15not publishedUSD 0.60USD 0.2625not statednot statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16
16Together AI
Notes and source quote
“gpt-oss-120B $0.15 $0.60”
USD 0.15not publishedUSD 0.60USD 0.2625not statednot statedTogether AI page
checked 2026-11-14
re-checked 2026-11-16
17Parasail
Notes and source quote
“gpt-oss-120b $0.10 $0.75 $0.055”
USD 0.10USD 0.055USD 0.75USD 0.2625not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
18IBM watsonx.ai
gpt-oss-120b
Notes and source quote
“gpt-oss-120b Open AI USD 0.159 per 1M tokens input USD 0.636 per 1M tokens output”
USD 0.159not publishedUSD 0.636USD 0.2782not statednot statedIBM watsonx.ai page
checked 2026-11-15
re-checked 2026-11-16
19SambaNova
gpt-oss-120b
Notes and source quote
“gpt-oss-120b N/A 0.22 USD 0.59 USD”
USD 0.22not publishedUSD 0.59USD 0.3125not statednot statedSambaNova page
checked 2026-11-14
re-checked 2026-11-16
20Cerebras
gpt-oss-120b
Notes and source quote

Developer (pay-as-you-go) tier. Cached input billed at the standard input rate (inference-docs.cerebras.ai/capabilities/prompt-caching). Paid context stated as "131k tokens" (inference-docs.cerebras.ai/models/openai-oss).

“GPT OSS 120B ~3000 tokens/s $0.35/M tokens $0.75/M tokens”
USD 0.35USD 0.35USD 0.75USD 0.45131,072not statedCerebras page
checked 2026-11-14
re-checked 2026-11-16
21Cloudflare Workers AI
@cf/openai/gpt-oss-120b
Notes and source quote

Cloudflare publishes this USD per-token price alongside the neuron price.

“@cf/openai/gpt-oss-120b $0.350 per M input tokens $0.750 per M output tokens”
USD 0.35not publishedUSD 0.75USD 0.45not statednot statedCloudflare Workers AI page
checked 2026-11-14
re-checked 2026-11-16
—Google Vertex AI batch
gpt-oss-120b
Notes and source quote
“gpt-oss-120b Batch Input $0.045 … Batch Output $0.18”
USD 0.045not publishedUSD 0.18USD 0.07875not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
—Amazon Bedrock batch
Notes and source quote

Batch tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“gpt-oss-120b $0.075 $0.30”
USD 0.075not publishedUSD 0.30USD 0.1312not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
—Amazon Bedrock flex / spot
Notes and source quote

Flex tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“gpt-oss-120b $0.075 $0.30”
USD 0.075not publishedUSD 0.30USD 0.1312not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
—Fireworks AI priority
accounts/fireworks/models/gpt-oss-120b
Notes and source quote

Priority mode.

“OpenAI GPT OSS 120B | Priority $0.18 / $0.018 / $0.72”
USD 0.18USD 0.018USD 0.72USD 0.315not statednot statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
—Amazon Bedrock priority
Notes and source quote

Priority tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“gpt-oss-120b $0.2625 $1.05”
USD 0.2625not publishedUSD 1.05USD 0.4594not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
—Parasail fast
Notes and source quote
“gpt-oss-120b (Fast) $0.15 $0.60 —”
USD 0.15not publishedUSD 0.60USD 0.2625not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16

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

What does OpenAI GPT OSS 120B cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on OpenAI GPT OSS 120B, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
CoreWeave ForgeUSD 5.76USD 9.75USD 69.30
DeepInfraUSD 6.39USD 11.43USD 81.90
AkashML (promo)USD 6.70USD 11.68USD 83.43
Crusoe CloudUSD 9.00USD 15.75USD 112.50
Novita AIUSD 9.00USD 15.75USD 112.50
VeniceUSD 11.70USD 21.30USD 153.00
SiliconFlowUSD 13.95USD 20.55USD 168.75
Google Vertex AIUSD 14.58USD 27.00USD 194.40
BasetenUSD 18.00USD 31.50USD 225.00
DigitalOceanUSD 21.60USD 34.50USD 243.00
Amazon BedrockUSD 24.30USD 45.00USD 324.00
FeatherlessUSD 17.28USD 35.64USD 125.10
Fireworks AIUSD 17.01USD 35.28USD 117.45
GroqUSD 20.25USD 39.60USD 209.25
Microsoft AzureUSD 24.30USD 45.00USD 324.00
Together AIUSD 24.30USD 45.00USD 324.00
ParasailUSD 20.07USD 32.01USD 178.65
IBM watsonx.aiUSD 25.76USD 47.70USD 343.44
SambaNovaUSD 30.42USD 61.65USD 449.10
CerebrasUSD 45.00USD 95.25USD 697.50
Cloudflare Workers AIUSD 45.00USD 95.25USD 697.50

For the support chatbot, the cheapest price (CoreWeave Forge, USD 5.76 a month) saves USD 12.24 against the median (USD 18.00). For the coding agent the gap is USD 125.10 a month (64% lower).

Which OpenAI GPT OSS 120B provider is cheapest for your traffic?

CoreWeave Forge has the lowest input price (USD 0.03) and the lowest output price (USD 0.17), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

OpenAI GPT OSS 120B: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
CoreWeave Forge (no cache price)USD 0.065 cheapestUSD 0.065 cheapestUSD 0.065 cheapest
DeepInfra (no cache price)USD 0.07025USD 0.07025USD 0.07025
AkashMLUSD 0.0745USD 0.0745USD 0.0745
Crusoe CloudUSD 0.10USD 0.10USD 0.10
Novita AI (no cache price)USD 0.10USD 0.10USD 0.10
Venice (no cache price)USD 0.1275USD 0.1275USD 0.1275

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 15 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

4 of 21 providers publish a cached-input price below the input price: Featherless (87% off), Fireworks AI (90% off), Groq (50% off), Parasail (45% off). CoreWeave Forge, DeepInfra, Novita AI, Venice, Google Vertex AI and 8 more publish none, so cached tokens there bill at the input price. AkashML, Crusoe Cloud, SiliconFlow and Cerebras list cached prices equal to their input price.

Context windows differ: 131,072 tokens at CoreWeave Forge, DeepInfra, AkashML and 5 more; 128,000 tokens at Crusoe Cloud and Venice. Google Vertex AI, Baseten, DigitalOcean, Amazon Bedrock, Fireworks AI and 6 more do not state one. The cheapest row is not always the one that fits a long prompt.

What does OpenAI GPT OSS 120B cost in other languages?

The same text needs a different number of tokens in each language. With the gpt-oss (o200k_harmony) tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for OpenAI GPT OSS 120B:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.0064CoreWeave Forge
Arabic MSAUSD 0.0096CoreWeave Forge
HindiUSD 0.0097CoreWeave Forge
ChineseUSD 0.023CoreWeave Forge
CodeUSD 0.0076CoreWeave Forge

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Estimate your own bill

The OpenAI models whose cheapest standard price is closest to OpenAI GPT OSS 120B's (USD 0.065 blended):

OpenAI models priced closest to OpenAI GPT OSS 120B
ModelCheapest inputCheapest outputMax contextProviders
GPT OSS Safeguard 20BUSD 0.07USD 0.20131,0723
GPT OSS 20BUSD 0.018USD 0.09131,07210
GPT-5 NanoUSD 0.05USD 0.40—3
GPT-6 LunaUSD 0.10USD 0.501,050,0006
GPT-4o miniUSD 0.15USD 0.60—3
GPT-5.6 LunaUSD 0.20USD 1.201,050,0006

Priced closest from other makers: Qwen3-8B (Qwen, USD 0.06) · Llama 3.2 1B Instruct (Meta, USD 0.0705) · Mistral-Small-24B-Instruct-2501 (Mistral AI, USD 0.0575).

Compare OpenAI GPT OSS 120B with

Also compared: vs GPT OSS 20B · vs Llama 3.3 70B · vs NVIDIA Nemotron 3 Super 120B A12B · vs GPT-6 Luna · vs DeepSeek V4.1 Flash · vs Qwen3.8 27B · vs Gemma 4 26B A4B.

Every OpenAI GPT OSS 120B price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the OpenAI GPT OSS 120B API cost per token?

From USD 0.03 per 1M input tokens (USD 0.00000003 per token) and USD 0.17 per 1M output tokens (USD 0.00000017 per token) at the lowest standard prices we found. The median of 21 standard prices is USD 0.10 input and USD 0.60 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for OpenAI GPT OSS 120B?

Among the 21 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is CoreWeave Forge, ranked on a blend of 3 input tokens to 1 output token (USD 0.065 per 1M). For input alone the lowest price is USD 0.03 (CoreWeave Forge); for output alone, USD 0.17 (CoreWeave Forge and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does OpenAI sell OpenAI GPT OSS 120B on its own API?

OpenAI publishes no price for OpenAI GPT OSS 120B on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is CoreWeave Forge at USD 0.03 / USD 0.17 per 1M tokens.

Does OpenAI GPT OSS 120B have cached input pricing?

8 of 21 standard prices include one. The lowest is USD 0.015 per 1M at Fireworks AI; the median is USD 0.0525. Providers without one bill cached input at the input price. What cached input means.

What is the OpenAI GPT OSS 120B context window?

Up to 131,072 tokens. 2 standard prices come with less, down to 128,000 tokens (Crusoe Cloud and Venice). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on OpenAI GPT OSS 120B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 69.30 a month at CoreWeave Forge, USD 194.40 at the median price and USD 697.50 at Cloudflare Workers AI. Try your own numbers.

Is there a batch, flex or priority price for OpenAI GPT OSS 120B?

Yes: batch from Google Vertex AI at USD 0.045 / USD 0.18; flex / spot from Amazon Bedrock at USD 0.075 / USD 0.30; priority from Fireworks AI at USD 0.18 / USD 0.72; fast from Parasail at USD 0.15 / USD 0.60 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is OpenAI GPT OSS 120B free to use through an API?

No provider in our data lists a free price for OpenAI GPT OSS 120B as of 2026-11-15. Groq's Free plan publishes limits for openai/gpt-oss-120b: 30 requests a minute, 8,000 tokens a minute and 1,000 requests a day (source, checked 2026-11-14). Cerebras's Free Trial publishes limits for gpt-oss-120b: 5 requests a minute and 30,000 tokens a minute (source, checked 2026-11-14). 5 USD in Free Trial credits after adding a verified payment method; they expire 30 days after they are granted. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is OpenAI GPT OSS 120B open source, with open weights, and what is its licence?

OpenAI publishes the weights on Hugging Face as openai/gpt-oss-120b, in a public repository with no access gate. The licence, as the OpenAI model card metadata states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from OpenAI's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

How many parameters does OpenAI GPT OSS 120B have?

Total parameters, as the OpenAI model card states them: 117B. Active parameters per token: 5.1B. (checked 2026-11-16; BroadNet did not verify these figures.)

Does OpenAI GPT OSS 120B support tool calling?

Yes, according to the OpenAI model card: “Use the models’ native capabilities for function calling” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.

How do I call OpenAI GPT OSS 120B with the OpenAI SDK?

BroadNet does not serve OpenAI GPT OSS 120B. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: DeepInfra (https://api.deepinfra.com/v1/openai, model openai/gpt-oss-120b), Fireworks AI (https://api.fireworks.ai/inference/v1, model accounts/fireworks/models/gpt-oss-120b), Groq (https://api.groq.com/openai/v1, model openai/gpt-oss-120b) and Together AI (https://api.together.ai/v1). Each provider page quotes the provider's docs with a check date.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity