AI TOOLS RADAR
Submit
All models / OPENAI
openai logo
openai

OpenAI: gpt-oss-120b

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
131,072 tokens
Maximum output
65,536 tokens
Architecture
text->text
Tokenizer
GPT
Knowledge cutoff
2024-06-30
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.15
per 1M tokens
Output
$0.6
per 1M tokens
Cache read
$0.075
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
Yes
Default parameters
medium
Capabilities
high, medium, low
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

No · high · medium · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Available providers

24 providers

Checked: September 18, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

AkashML

bf16
Context
131K
Maximum output
118K
Input
$0.03
Output
$0.17
Cache read
$0.03
Cache write
Not provided

CoreWeave

fp4
Context
131K
Maximum output
118K
Input
$0.03
Output
$0.17
Cache read
$0.03
Cache write
Not provided

DekaLLM

bf16
Context
131K
Maximum output
118K
Input
$0.03
Output
$0.18
Cache read
Not provided
Cache write
Not provided

DeepInfra

bf16
Context
131K
Maximum output
118K
Input
$0.037
Output
$0.17
Cache read
Not provided
Cache write
Not provided

Crusoe

bf16
Context
131K
Maximum output
118K
Input
$0.05
Output
$0.25
Cache read
$0.05
Cache write
Not provided

Novita

fp4
Context
131K
Maximum output
33K
Input
$0.05
Output
$0.25
Cache read
Not provided
Cache write
Not provided

Mancer 2

fp8
Context
131K
Maximum output
118K
Input
$0.05
Output
$0.3
Cache read
Not provided
Cache write
Not provided

DigitalOcean

Not provided
Context
128K
Maximum output
4K
Input
$0.06
Output
$0.42
Cache read
$0.012
Cache write
Not provided

Google

Not provided
Context
131K
Maximum output
118K
Input
$0.09
Output
$0.36
Cache read
Not provided
Cache write
Not provided

BaseTen

fp4
Context
128K
Maximum output
115K
Input
$0.1
Output
$0.5
Cache read
$0.1
Cache write
Not provided

BaseTen

fp4
Context
128K
Maximum output
115K
Input
$0.1
Output
$0.5
Cache read
$0.1
Cache write
Not provided

Parasail

fp4
Context
131K
Maximum output
118K
Input
$0.1
Output
$0.75
Cache read
$0.055
Cache write
Not provided

SambaNova

Not provided
Context
131K
Maximum output
118K
Input
$0.14
Output
$0.95
Cache read
Not provided
Cache write
Not provided

Amazon Bedrock

Not provided
Context
131K
Maximum output
118K
Input
$0.15
Output
$0.6
Cache read
Not provided
Cache write
Not provided

Nebius

fp4
Context
131K
Maximum output
118K
Input
$0.15
Output
$0.6
Cache read
Not provided
Cache write
Not provided

Amazon Bedrock

Not provided
Context
131K
Maximum output
118K
Input
$0.15
Output
$0.6
Cache read
Not provided
Cache write
Not provided

DeepInfra

bf16
Context
131K
Maximum output
16K
Input
$0.15
Output
$0.6
Cache read
Not provided
Cache write
Not provided

SiliconFlow

fp8
Context
131K
Maximum output
8K
Input
$0.15
Output
$0.6
Cache read
$0.075
Cache write
Not provided

Phala

Not provided
Context
131K
Maximum output
118K
Input
$0.15
Output
$0.6
Cache read
Not provided
Cache write
Not provided

Together

Not provided
Context
131K
Maximum output
118K
Input
$0.15
Output
$0.6
Cache read
Not provided
Cache write
Not provided

Groq

Not provided
Context
131K
Maximum output
66K
Input
$0.15
Output
$0.6
Cache read
$0.075
Cache write
Not provided

Mara

Not provided
Context
131K
Maximum output
118K
Input
$0.15
Output
$0.75
Cache read
Not provided
Cache write
Not provided

DeepInfra

fp8
Context
131K
Maximum output
118K
Input
$0.2
Output
$0.95
Cache read
Not provided
Cache write
Not provided

Cerebras

fp16
Context
131K
Maximum output
41K
Input
$0.35
Output
$0.75
Cache read
$0.35
Cache write
Not provided
openai

4 models

All models
openai logoopenai

OpenAI: GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Context
1.1M
Input
file · image · text
Output
text
Input: $0.1Output: $0.5per 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Context
1.1M
Input
file · image · text
Output
text
Input: $0.05Output: $0.25per 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

Context
1.1M
Input
file · image · text
Output
text
Input: $0.1Output: $0.5per 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-6 Luna (batch)

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

Context
1.1M
Input
file · image · text
Output
text
Input: $0.05Output: $0.25per 1M tokens
View model details →