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

Open-weight API pricing - last verified

gpt-oss-20b: where to run it and what it costs

4 offers from 4 providers list gpt-oss-20b at a per-token price. The lowest listed input price is $0.07 per 1M input tokens at Google Vertex AI (gpt-oss-20b), 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.

20.9B total, 3.6B 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
4
Providers
4
Lowest listed input
$0.07
First-party input
None listed

Per-token prices

Every gpt-oss-20b 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.
4 hosted offers for gpt-oss-20b, 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
Google Vertex AI (Agent Platform MaaS)gpt-oss-20bQuotes for this row$0.07$0.25$0.007Not statedNot statedPartner models on Agent Platformcloud.google.com
Amazon BedrockNo API model ID on the pricing pageListed as: gpt-oss-20bQuotes for this row$0.0721$0.309Not statedNot statedNot statedStandard Region: Region: Asia Pacific (Sydney)aws.amazon.com
Groqopenai/gpt-oss-20bQuotes for this row$0.075$0.30Not stated131,072Not statedProductionconsole.groq.com
Cloudflare Workers AI@cf/openai/gpt-oss-20bQuotes for this row$0.20$0.30Not 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-20bPartner models on Agent Platform$0.035$0.125
“gpt-oss-20b Input $0.07 Output $0.25 Cache Hit $0.007 Batch Input $0.035 Batch Output $0.125”
cloud.google.com
Amazon BedrockNo API model ID on the pricing pageListed as: gpt-oss-20bStandard Region: Region: Asia Pacific (Sydney)$0.0361$0.1545
“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”
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 1000 tokens per second for openai/gpt-oss-20b.

“GPT OSS 20B openai/gpt-oss-20b 1000 $0.075input$0.30output”
Vendor-stated - console.groq.com

Evidence

The quote behind every value

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

Google Vertex AI (Agent Platform MaaS)

gpt-oss-20b

Model ID, Variant, Input, Output, Batch

“gpt-oss-20b Input $0.07 Output $0.25 Cache Hit $0.007 Batch Input $0.035 Batch Output $0.125”
cloud.google.com

Cached input

“gpt-oss-20b Input $0.07 Output $0.25 Cache Hit $0.007”
cloud.google.com

Status

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

Not stated

  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Amazon Bedrock

gpt-oss-20b

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”
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”
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 only the Asia Pacific (Sydney) table.

Groq

openai/gpt-oss-20b

Model ID, Variant

“GPT OSS 20B openai/gpt-oss-20b 1000 $0.075input$0.30output”
console.groq.com

Input, Output

“openai/gpt-oss-20b 1000 $0.075input$0.30output”
console.groq.com

Context served

“openai/gpt-oss-20b 1000 $0.075input$0.30output 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: 1000 tokens/sec.

Cloudflare Workers AI

gpt-oss-20b

Model ID, Input, Output

“@cf/openai/gpt-oss-20b $0.200 per M input tokens $0.300 per M output tokens”
developers.cloudflare.com

Variant

“@cf/openai/gpt-oss-20b $0.200 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.
  • Together AI: gpt-oss-20b, Llama 4 Maverick and Qwen3.8-27B appear only in its fine-tuning table, not as serverless inference.
  • 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.
  • 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-20b yourself, or compare its first-party API

FAQ

How much does the gpt-oss-20b API cost?

Listed input prices run from $0.07 to $0.20 per 1M input tokens across 4 offers on October 18, 2026, and output from $0.25 to $0.309 per 1M output tokens. The lowest listed input price is at Google Vertex AI (gpt-oss-20b). No first-party API row is listed.

Which providers serve gpt-oss-20b?

Groq, 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-20b's full context window?

gpt-oss-20b'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 3 offers.

Is there a batch price for gpt-oss-20b?

Per-model batch prices are listed by Google Vertex AI (gpt-oss-20b): $0.035 input and $0.125 output per 1M tokens and Amazon Bedrock (gpt-oss-20b): $0.0361 input and $0.1545 output per 1M tokens. 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 (4 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-20b

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-120b, Llama 4 Maverick, Gemma 4 31B, Mistral Large 3, NVIDIA Nemotron 3.5 Super VL 120B-A12B.

Providers on this page: Groq, Cloudflare Workers AI, Amazon Bedrock, Google Vertex AI.