GroqCloud APIStableChecked 2026-07-15

GPT-OSS 120B on Groq pricing, context window, and cost calculator

OpenAI GPT-OSS 120B served through GroqCloud, with source-tracked token pricing and limits.

Verified fields

Quick facts

API access providerGroqCloud
Model creatorOpenAI
API model IDopenai/gpt-oss-120b
Default input / 1M$0.15
Default output / 1M$0.60
Context window131,072
Default profilestandard
Acceptstext
Producestext
StatusStable
Maximum output65,536 tokens

Supported capabilities

  • Streaming
  • Function calling
  • Structured outputs
  • Prompt caching
  • Reasoning
  • Code execution
  • Search grounding

Only capabilities explicitly tracked from provider documentation are shown.

Source-tracked rates

Verified pricing profiles

Amounts are USD per 1M tokens unless the column states an hourly storage unit.

ProfileInput / 1MCached input / 1MOutput / 1MNotes
standardDefault$0.15 USD$0.075 USD$0.60 USDUsed for default estimates.
Workload estimate

GPT-OSS 120B on Groq cost calculator

Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.

Estimated monthly total$4.50
Monthly input cost
$1.50
Monthly output cost
$3.00
Per 1,000 requests
$0.45
Active profile
standard

Estimate excludes untracked provider-specific charges.

Explicit assumptions

Common workload examples

Input only

1M input tokens

$0.15 under the standard profile, excluding output and other charges.

Output only

1M output tokens

$0.60 under the standard profile, excluding input and other charges.

Default workload

10,000 monthly requests

At 1,000 input and 500 output tokens per request: $4.50 under standard.

Cache scenario

50% cached input

The same default workload with 50% cached input is estimated at $4.125. Cache savings apply only to the tracked cached-input rate.

Verification

Sources and methodology

Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.

Calculator profile rule: standard is the verified default. Estimates use GroqCloud token rates for the exact openai/gpt-oss-120b API identifier and do not represent pricing from other hosts.