AI TOOLS RADAR
Explore
All models / OPENAI
openai logo
openai

OpenAI: gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. $0.02 per million input tokens, $0.10 per million output tokens. 131,072 token context window, maximum output of 32,768 tokens. Higher uptime with 12 providers. Includes independent benchmarks from Artificial Analysis.

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
131,072 tokens
Maximum output
117,964 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
$0.02
/M tokens
Output
$0.1
/M tokens
API

Model configuration

Reasoning

Moderated
Yes
Default parameters
medium
Capabilities
high, medium, low
API

Quick start

Call this exact model ID through OpenRouter’s OpenAI-compatible API.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-oss-20b","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_ktop_logprobstop_p
Available providers

13 providers

Live providers on OpenRouter

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

OpenRouter

Darkbloom

fp8
Context
131K
Maximum output
33K
Input
$0.020
Output
$0.100
Cache read
Not provided
Cache write
Not provided

CoreWeave

fp4
Context
131K
Maximum output
118K
Input
$0.030
Output
$0.130
Cache read
$0.030
Cache write
Not provided

DeepInfra

bf16
Context
131K
Maximum output
118K
Input
$0.030
Output
$0.140
Cache read
Not provided
Cache write
Not provided

Parasail

fp4
Context
131K
Maximum output
118K
Input
$0.030
Output
$0.150
Cache read
$0.020
Cache write
Not provided

Phala

unknown
Context
131K
Maximum output
118K
Input
$0.040
Output
$0.150
Cache read
Not provided
Cache write
Not provided

Novita

fp4
Context
131K
Maximum output
33K
Input
$0.040
Output
$0.150
Cache read
Not provided
Cache write
Not provided

SiliconFlow

fp8
Context
131K
Maximum output
8K
Input
$0.040
Output
$0.180
Cache read
Not provided
Cache write
Not provided

Together

unknown
Context
131K
Maximum output
118K
Input
$0.050
Output
$0.200
Cache read
Not provided
Cache write
Not provided

Amazon Bedrock

unknown
Context
131K
Maximum output
118K
Input
$0.070
Output
$0.150
Cache read
Not provided
Cache write
Not provided

Amazon Bedrock

unknown
Context
131K
Maximum output
118K
Input
$0.070
Output
$0.150
Cache read
Not provided
Cache write
Not provided

Google

unknown
Context
131K
Maximum output
33K
Input
$0.070
Output
$0.250
Cache read
Not provided
Cache write
Not provided

Fireworks

unknown
Context
131K
Maximum output
118K
Input
$0.070
Output
$0.300
Cache read
$0.035
Cache write
Not provided

Groq

unknown
Context
131K
Maximum output
66K
Input
$0.075
Output
$0.300
Cache read
$0.037
Cache write
Not provided
openai

models

All models
openai logoopenai

OpenAI: GPT Transcribe

GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and multiple language...

Context
Not provided
Input
audio
Output
transcription
Input: $4500.00Output: Freeper 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-5.6 Luna Pro

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 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: $0.200Output: $1.20per 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-5.6 Luna

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Context
1.1M
Input
file · image · text
Output
text
Input: $0.200Output: $1.20per 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-5.6 Terra Pro

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, 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: $2.00Output: $12.00per 1M tokens
View model details →