Back to all models

Pricing and availability as of

GPT OSS 120B

Open-source 120B parameter model with reasoning capabilities via Groq inference.

gpt-oss-120b
Context
131,072
tokens
Max output
32,768
tokens
Input from
$0.03
per 1M tokens · 3% off
Output from
$0.15
per 1M tokens · 3% off
Providers
6
automatic routing
Released
Aug 5, 2025
  • Streaming
  • Tools
  • Reasoning
  • JSON Output
  • Structured JSON
  • Batch API
No ratings yetSign in to rate
3% offthis model via flexai

Providers for GPT OSS 120B

Compare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.

6 providers · select a column to sort

ProviderActions
3% off
131.1k—$0.0291$0.1455$0.0044
131.1k32.8k$0.17$0.55—
131.1k32.8k$0.15$0.60—
131.1k32.8k$0.15$0.60—
131.1k32.8k$0.35$0.75—
131.1k32.8k$0.15$0.75—

Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.

GPT OSS 120B API pricing

GPT OSS 120B API pricing starts at $0.0291 per 1M input tokens and $0.1455 per 1M output tokens through LLM Gateway, on FlexAI. Cached input starts at $0.0044 per 1M tokens.

ProviderInput / 1M tokensOutput / 1M tokensCached input / 1M tokensContext window
FlexAI$0.0291$0.1455$0.0044131,072 tokens
Azure$0.15$0.60—131,072 tokens
Together AI$0.15$0.60—131,072 tokens
SCX.ai (Turbo)$0.17$0.55—131,072 tokens
Groq$0.15$0.75—131,072 tokens
Cerebras$0.35$0.75—131,072 tokens

What GPT OSS 120B costs at volume

Monthly usageCost on FlexAI
1M input + 250K output tokens$0.0655
10M input + 2.5M output tokens$0.6547
100M input + 25M output tokens$6.55

GPT OSS 120B cost calculator

Estimated monthly cost
$1.02
Cost per request
$0.0001

Frequently asked questions

What is GPT OSS 120B?

Open-source 120B parameter model with reasoning capabilities via Groq inference. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does GPT OSS 120B cost?

Pricing for GPT OSS 120B on LLM Gateway starts at $0.03 per million input tokens and $0.15 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of GPT OSS 120B?

GPT OSS 120B supports a context window of up to 131,072 tokens on its largest provider deployment.

Which providers serve GPT OSS 120B?

GPT OSS 120B is served by FlexAI, SCX.ai (Turbo), Azure, Together AI, Cerebras, Groq through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does GPT OSS 120B support tool calling and structured outputs?

Yes. GPT OSS 120B supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.

When was GPT OSS 120B released?

GPT OSS 120B was released on August 5, 2025.