Skip to content
LLMs
OpenAI logo

OpenAI: gpt-oss-120b

by OpenAI

OpenAI: gpt-oss-120b is a large language model from OpenAI. It costs $0.150 per million input tokens and $0.600 per million output tokens. Its context window is 131K tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weights
Input / 1M tokens
$0.150
Output / 1M tokens
$0.600
Cached input / 1M
$0.075

On repeated prefixes

Context window
131K

tokens

Who serves it cheapest

21 hosts serve gpt-oss-120b. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: gpt-oss-120b, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
VeniceCheapestint4$0.030$0.150128K-99.9%
CoreWeavefp4$0.030$0.170131K-99.8%
DekaLLMbf16$0.030$0.180131K-100.0%
AkashMLbf16$0.030$0.187131K-100.0%
DeepInfrabf16$0.037$0.170131K-99.9%
Crusoebf16$0.050$0.250131K-100.0%
Mancer 2fp8$0.050$0.250131K-99.9%
Novitafp4$0.050$0.250131K-99.9%
DigitalOcean$0.060$0.420128K-100.0%
Google$0.090$0.360131K-19.7%
BaseTenfp4$0.100$0.500128K-100.0%
Amazon Bedrock$0.150$0.600131K-100.0%
Nebiusfp4$0.150$0.600131K-100.0%
SiliconFlowfp8$0.150$0.600131K-73.8%
Phala$0.150$0.600131K-99.7%
Together$0.150$0.600131K-100.0%
Groq$0.150$0.600131K-100.0%
Parasailfp4$0.100$0.750131K-100.0%
Mara$0.150$0.750131K-96.0%
SambaNova$0.140$0.950131K-100.0%
Cerebrasfp16$0.350$0.750131K-100.0%

The spread between Venice and Cerebras is 7.5× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
11.6
Coding index
30.4
Agentic index
3.7

About gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Specifications

OpenAI: gpt-oss-120b specifications
Model IDopenai/gpt-oss-120b
ProviderOpenAI
Context window131K tokens
Max output66K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2024-06-30
Open weightsYes - openai/gpt-oss-120b
ReleasedAugust 5, 2025

Cheaper alternatives

Models that cost less than gpt-oss-120b while keeping at least half its context window and every input modality it supports.

Gemma 4 31B

$0.200 in · $0.400 out

about the same cheaper

Hunyuan A13B Instruct

$0.140 in · $0.570 out

1.1× cheaper

GLM 5.3 Flash

$0.150 in · $0.500 out

1.1× cheaper

Hy3

$0.132 in · $0.528 out

1.1× cheaper

Qwen3.8 Omni Flash

$0.150 in · $0.470 out

1.1× cheaper

Frequently asked

How much does OpenAI: gpt-oss-120b cost?

$0.150 per million input tokens and $0.600 per million output tokens. Cached input reads cost $0.075 per million tokens.

What is the context window of OpenAI: gpt-oss-120b?

131K tokens, with up to 66K tokens of output per request.

Which provider serves OpenAI: gpt-oss-120b cheapest?

Venice at $0.030 per million input tokens - 7.5× cheaper than Cerebras, the most expensive of the 21 hosts serving it.

Confirm against the source: OpenAI official pricing.