Skip to main content
Watch: Stop Building Apps. Build Tools for AI Agents

Open-weight API pricing - last verified

gpt-oss-120b: where to run it and what it costs

10 offers from 10 providers list gpt-oss-120b at a per-token price. The lowest listed input price is $0.05 per 1M input tokens at Novita AI (OpenAI GPT OSS 120B), with output at $0.25. No first-party API row is listed for this model. Prices are as listed on October 18, 2026; they change often and are not a benchmark.

116.8B total, 5.1B active, mixture of experts. Native context 131,072 tokens, per our local-models record (from the HF API).

Every offerBatch pricesQuotesRun it yourselfAll open-weight models

Offers
10
Providers
10
Lowest listed input
$0.05
First-party input
None listed

Per-token prices

Every gpt-oss-120b offer, sorted by input price

Each row is one build as the provider lists it, with its own model ID: dated snapshots, Fast and turbo builds and regional rows are never merged. Sorted by listed input price in USD per 1M input tokens; every price is in that same unit. Not stated means the provider's page does not say.
10 hosted offers for gpt-oss-120b, sorted by listed input price in USD per 1M input tokens
Provider and model IDInputUSD per 1M tokensOutputUSD per 1M tokensCached inputUSD per 1M tokensContext servedas the provider lists itQuantizationStatusSource
Novitaopenai/gpt-oss-120bListed as: OpenAI GPT OSS 120BQuotes for this row$0.05$0.25Not stated128Kfp4Not statednovita.ai
Google Vertex AI (Agent Platform MaaS)gpt-oss-120bQuotes for this row$0.09$0.36Not statedNot statedNot statedPartner models on Agent Platformcloud.google.com
Basetenopenai/gpt-oss-120bListed as: GPT OSS 120BQuotes for this row$0.10$0.50Not stated128kNot statedModel APIsbaseten.co
Together AIopenai/gpt-oss-120bQuotes for this row$0.15$0.60Not stated131,072MXFP4Serverless Inferencetogether.ai
Fireworks AIgpt-oss-120bListed as: OpenAI GPT OSS 120BQuotes for this row$0.15$0.60$0.015Not statedNot statedStandarddocs.fireworks.ai
Groqopenai/gpt-oss-120bQuotes for this row$0.15$0.60Not stated131,072Not statedProductionconsole.groq.com
Amazon BedrockNo API model ID on the pricing pageListed as: gpt-oss-120bQuotes for this row$0.1545$0.618Not statedNot statedNot statedStandard Region: Region: Asia Pacific (Sydney)aws.amazon.com
SambaNovagpt-oss-120bQuotes for this row$0.22$0.59Not stated128k tokensNot statedProductioncloud.sambanova.ai
Cerebrasgpt-oss-120bListed as: GPT OSS 120BQuotes for this row$0.35$0.75Not stated65k / 131kfree / paidNot statedDeveloper Tiercerebras.ai
Cloudflare Workers AI@cf/openai/gpt-oss-120bQuotes for this row$0.35$0.75Not statedNot statedNot statedNot stateddevelopers.cloudflare.com
First-party
The model's own developer selling its API.
Peak-hour price
DeepSeek's listed price during its peak hours; off-peak is half, per its page. Alibaba's busy-hour rows work the same way.
Card shows N% off
A discount tag sits beside the price on the provider's catalog card. The number is the discounted one and may be temporary.
Inferred
Our reading, not the page's words: a name-only model match, a region taken from table order, or a context figure from an unlabelled tag.
Below native
The provider serves a shorter context than the model's native window in our local-models data.
Preview
The provider lists the model as a preview, for evaluation rather than production.

Batch

Batch prices

Listed per-model batch prices, kept apart from the per-token table. Each row keeps its provider's region.
Per-model batch prices in USD per 1M tokens
Provider and model IDBatch inputUSD per 1M tokensBatch outputUSD per 1M tokensQuote
Google Vertex AI (Agent Platform MaaS)gpt-oss-120bPartner models on Agent Platform$0.045$0.18
“gpt-oss-120b Input $0.09 Output $0.36 Batch Input $0.045 Batch Output $0.18”
cloud.google.com
Amazon BedrockNo API model ID on the pricing pageListed as: gpt-oss-120bStandard Region: Region: Asia Pacific (Sydney)$0.0773$0.309
“Batch Region: Region: Asia Pacific (Sydney) OpenAI models Price per 1M input tokens Price per 1M output tokens gpt-oss-20b $ 0.0361 $ 0.1545 gpt-oss-120b $ 0.0773 $ 0.3090”
aws.amazon.com

Vendor-stated

Speed, as the provider states it

Figures from the provider's own page, not measured by us and not comparable across providers.

Groq states 500 tokens per second for openai/gpt-oss-120b.

“GPT OSS 120B openai/gpt-oss-120b 500 $0.15input$0.60output”
Vendor-stated - console.groq.com

Cerebras states 3000 tokens per second for GPT OSS 120B.

“GPT OSS 120B ~3000 tokens/s $0.35/M tokens $0.75/M tokens”
Vendor-stated - cerebras.ai

Evidence

The quote behind every value

Each value is copied from the provider's own page; one quote that backs several values shows once.

Novita

OpenAI GPT OSS 120B

Model ID

“OpenAI GPT OSS 120B openai/gpt-oss-120b”
novita.ai

Variant, Input, Output

“OpenAI GPT OSS 120B 128K $0.05 /Mt $0.25 /Mt”
novita.ai

Context served

“OpenAI GPT OSS 120B 128K”
novita.ai

Quantization

“Provider OpenAI Quantization fp4”
novita.ai

Not stated

  • Cached input: No cached-input price listed for this model on the pricing page.
  • Batch: No per-model batch price listed; the pricing page states batch inference is at an introductory 50% discount for supported models.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Google Vertex AI (Agent Platform MaaS)

gpt-oss-120b

Model ID

“OpenAI's models Show discount options Model Type Price /1M (USD) gpt-oss-120b Input $0.09 Output $0.36”
cloud.google.com

Variant, Input, Output, Batch

“gpt-oss-120b Input $0.09 Output $0.36 Batch Input $0.045 Batch Output $0.18”
cloud.google.com

Status

“Partner models on Agent Platform”
cloud.google.com

Not stated

  • Cached input: No cached-input price listed for this model on the pricing page.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Baseten

GPT OSS 120B

Model ID, Context served

“OpenAI GPT 120B openai/gpt-oss-120b 128k 128k”
docs.baseten.co

Variant, Input, Output

“GPT OSS 120B GPT OSS 120B $0.10 $0.10 - - $0.50”
baseten.co

Input column, Output column

“Price per 1M tokens Model Input Cache Input Output”
baseten.co

Status

“Model APIs Instant access to pre-optimized models running on the Baseten Inference Stack.”
baseten.co

Not stated

  • Cached input: Cache Input column shows "-" for this model.
  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.

Together AI

gpt-oss-120B

Model ID

“OpenAI GPT-OSS 120B openai/gpt-oss-120b 131072 $0.15 - $0.60 MXFP4”
docs.together.ai

Variant, Input, Output

“gpt-oss-120B $0.15 $0.60”
together.ai

Context served

“openai/gpt-oss-120b 131072”
docs.together.ai

Quantization

“openai/gpt-oss-120b 131072 $0.15 - $0.60 MXFP4”
docs.together.ai

Status

“Serverless Inference Most teams start with serverless inference”
together.ai

Not stated

  • Cached input: Cached input column shows "-" for this model.
  • Batch: No per-model batch price listed on the pricing page.

Fireworks AI

OpenAI GPT OSS 120B

Model ID

“app.fireworks.ai/models/fireworks/gpt-oss-120b”
docs.fireworks.ai

Variant, Input, Output, Cached input

“OpenAI GPT OSS 120B $0.15 / $0.015 / $0.60 $0.18 / $0.018 / $0.72”
docs.fireworks.ai

Input column, Output column, Cached input column

“prices are input / cached input / output (USD per 1M tokens), in that order”
docs.fireworks.ai

Status

“In each Standard or Priority cell, prices are input / cached input / output (USD per 1M tokens), in that order”
docs.fireworks.ai

Not stated

  • Batch: No per-model batch price listed; the page states batch inference is billed at 50% of serverless pricing.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Source notes: Priority $0.18 / $0.018 / $0.72.

Groq

openai/gpt-oss-120b

Model ID, Variant

“GPT OSS 120B openai/gpt-oss-120b 500 $0.15input$0.60output”
console.groq.com

Input, Output

“openai/gpt-oss-120b 500 $0.15input$0.60output”
console.groq.com

Context served

“openai/gpt-oss-120b 500 $0.15input$0.60output 250KTPM1KRPM 131,072 65,536”
console.groq.com

Status

“Production Models Note: Production models are intended for use in your production environments.”
console.groq.com

Not stated

  • Cached input: No cached-input price listed for this model on the pricing page.
  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.

Source notes: Vendor-stated speed column: 500 tokens/sec.

Amazon Bedrock

gpt-oss-120b

Variant, Input, Output, Status

“Standard Region: Region: Asia Pacific (Sydney) OpenAI models Price per 1M input tokens Price per 1M output tokens gpt-oss-20b $ 0.0721 $ 0.3090 gpt-oss-120b $ 0.1545 $ 0.6180”
aws.amazon.com

Batch

“Batch Region: Region: Asia Pacific (Sydney) OpenAI models Price per 1M input tokens Price per 1M output tokens gpt-oss-20b $ 0.0361 $ 0.1545 gpt-oss-120b $ 0.0773 $ 0.3090”
aws.amazon.com

Not stated

  • Model ID: No API model ID string on the pricing page.
  • Cached input: No cached-input price listed for this model on the pricing page.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Source notes: The pricing page's default view shows the Asia Pacific (Sydney) table; other regions sit behind a region selector, so US prices are not listed here.

SambaNova

gpt-oss-120b

Model ID, Context served

“OpenAI gpt-oss-120b 128k tokens Text”
docs.sambanova.ai

Variant, Input, Output

“gpt-oss-120b N/A 0.22 USD 0.59 USD”
cloud.sambanova.ai

Input column, Output column

“Model Cached Input Tokens Input (per 1M tokens) Output (per 1M tokens)”
cloud.sambanova.ai

Status

“Production models are intended for use in production environments”
docs.sambanova.ai

Not stated

  • Cached input: Cached input listed as N/A for this model.
  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.

Cerebras

GPT OSS 120B

Model ID

“OpenAI GPT OSS gpt-oss-120b 120 billion 65k / 131k ~3000”
inference-docs.cerebras.ai

Variant, Input, Output

“GPT OSS 120B ~3000 tokens/s $0.35/M tokens $0.75/M tokens”
cerebras.ai

Input column, Output column

“Model Speed Input Output”
cerebras.ai

Context served

“gpt-oss-120b 120 billion 65k / 131k”
inference-docs.cerebras.ai

Context served column

“Model Name Model ID Parameters Context (free / paid) Speed (tokens/s)”
inference-docs.cerebras.ai

Status

“Developer Tier Pricing”
cerebras.ai

Not stated

  • Cached input: No cached-input price listed for this model on the pricing page.
  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Page states shared-inference models are original, unpruned versions but gives no numeric precision.

Source notes: Vendor-stated speed: ~3000 tokens/s.

Cloudflare Workers AI

gpt-oss-120b

Model ID, Input, Output

“@cf/openai/gpt-oss-120b $0.350 per M input tokens $0.750 per M output tokens”
developers.cloudflare.com

Variant

“@cf/openai/gpt-oss-120b $0.350 per M input tokens”
developers.cloudflare.com

Not stated

  • Cached input: No cached-input price listed for this model on the pricing page.
  • Batch: No per-model batch price listed on the pricing page.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Coverage

Not listed on the pages read

  • Amazon Bedrock: gpt-oss prices for US regions are not listed on the pages read; only the Asia Pacific (Sydney) table is in the default view.
  • DeepInfra: gpt-oss-120b, gpt-oss-20b, MiniMax-M3 and Llama 4 Maverick are not listed on the pages read.
  • Fireworks AI: only the headline-model price table is covered; models outside it fall under size-based pricing and are not listed on the pages read.
  • Cerebras: the pay-as-you-go Developer tier lists only GPT OSS 120B and Qwen 3.8 27B; other models are Dedicated Inference by quote.
  • Azure AI Foundry: no gpt-oss, Azure-direct Kimi K3, GLM-5.3 or Mistral Large 3 rows on the pages read.
  • Fireworks AI says batch inference is billed at 50% of serverless pricing, with no per-model batch figure.
  • Novita says batch inference is at an introductory 50% discount for supported models, with no per-model batch prices.
  • Together AI shows a Batch API price toggle but lists no per-model batch figures.
  • Amazon Bedrock says Flex tier and Batch pricing is at 50% discount to Standard tier pricing; per-model batch prices are listed only for gpt-oss, in the Asia Pacific (Sydney) table.

Alternatives

Run gpt-oss-120b yourself, or compare its first-party API

FAQ

How much does the gpt-oss-120b API cost?

Listed input prices run from $0.05 to $0.35 per 1M input tokens across 10 offers on October 18, 2026, and output from $0.25 to $0.75 per 1M output tokens. The lowest listed input price is at Novita AI (OpenAI GPT OSS 120B). No first-party API row is listed.

Which providers serve gpt-oss-120b?

Together AI, Fireworks AI, Groq, Cerebras, Baseten, Novita AI, SambaNova Cloud, Cloudflare Workers AI, Amazon Bedrock and Google Vertex AI. Each lists one build, shown under the provider's own model name.

Do all providers serve gpt-oss-120b's full context window?

gpt-oss-120b's native context is 131,072 tokens in our local-models data. No provider that states a served context lists one clearly below that. Not stated by 4 offers.

Is there a batch price for gpt-oss-120b?

Per-model batch prices are listed by Google Vertex AI (gpt-oss-120b): $0.045 input and $0.18 output per 1M tokens and Amazon Bedrock (gpt-oss-120b): $0.0773 input and $0.309 output per 1M tokens. Fireworks AI says batch inference is billed at 50% of serverless pricing, with no per-model batch figure. Novita says batch inference is at an introductory 50% discount for supported models, with no per-model batch prices. Together AI shows a Batch API price toggle but lists no per-model batch figures. Amazon Bedrock says Flex tier and Batch pricing is at 50% discount to Standard tier pricing; per-model batch prices are listed only for gpt-oss, in the Asia Pacific (Sydney) table.

Sources

Last verified from each provider's own pages (14 sites). This is a directory of listed prices and what each provider states about the model it serves, not a benchmark. Prices change often; check the provider's page before you commit. Speed figures appear only where a provider states them, labelled Vendor-stated.

Newsletter

Know when open-weight API prices move

One email per week. New model releases, price changes and where to run them, and what they mean for what you build.

Read more about gpt-oss-120b

Related

Run open-weight models locally

The self-host alternative: downloads, memory needs and commands for each model.

Open-weight model licenses

Which of these models you may use commercially, and on what terms.

LLM API cost levers

Prompt caching, batch discounts and service tiers by provider.

Free LLM API tiers

Which providers have a standing free tier or credits.

OpenAI-compatible endpoints

Base URLs and limits for switching providers without rewriting code.

LLM gateways and routers

Route one model across several of these providers with fallbacks.

Other open-weight models: DeepSeek V4 Pro, DeepSeek V4.1 Flash, Qwen3.8-27B, Kimi K3, GLM-5.3, MiniMax-M3, gpt-oss-20b, Llama 4 Maverick, Gemma 4 31B, Mistral Large 3, NVIDIA Nemotron 3.5 Super VL 120B-A12B.

Providers on this page: Together AI, Fireworks AI, Groq, Cerebras, Baseten, Novita AI, SambaNova Cloud, Cloudflare Workers AI, Amazon Bedrock, Google Vertex AI.