AI TOOLS RADAR
All models / OPENAI
openai logo
openai

OpenAI: gpt-oss-20b

Source description (English)

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
131,072 tokens
Maximum output
32,768 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
$0.018
per 1M tokens
Output
$0.09
per 1M tokens
Cache read
$0.009
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-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

12 providers

Checked: September 29, 2026

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
$0.018
Output
$0.09
Cache read
$0.009
Cache write
Not provided

AkashML

fp4
Context
131K
Maximum output
118K
Input
$0.02
Output
$0.1
Cache read
Not provided
Cache write
Not provided

DekaLLM

bf16
Context
131K
Maximum output
118K
Input
$0.029
Output
$0.14
Cache read
Not provided
Cache write
Not provided

CoreWeave

fp4
Context
131K
Maximum output
118K
Input
$0.03
Output
$0.13
Cache read
$0.03
Cache write
Not provided

DeepInfra

bf16
Context
131K
Maximum output
118K
Input
$0.03
Output
$0.14
Cache read
Not provided
Cache write
Not provided

Parasail

fp4
Context
131K
Maximum output
118K
Input
$0.03
Output
$0.15
Cache read
$0.02
Cache write
Not provided

Novita

fp4
Context
131K
Maximum output
33K
Input
$0.04
Output
$0.15
Cache read
Not provided
Cache write
Not provided

SiliconFlow

fp8
Context
131K
Maximum output
8K
Input
$0.04
Output
$0.18
Cache read
Not provided
Cache write
Not provided

Amazon Bedrock

Not provided
Context
131K
Maximum output
118K
Input
$0.07
Output
$0.15
Cache read
Not provided
Cache write
Not provided

Amazon Bedrock

Not provided
Context
131K
Maximum output
118K
Input
$0.07
Output
$0.15
Cache read
Not provided
Cache write
Not provided

Google

Not provided
Context
131K
Maximum output
33K
Input
$0.07
Output
$0.25
Cache read
Not provided
Cache write
Not provided

Groq

Not provided
Context
131K
Maximum output
66K
Input
$0.075
Output
$0.3
Cache read
$0.0375
Cache write
Not provided
openai

4 models

All models
openai logoopenai

OpenAI: GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic...

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

OpenAI: GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

Context
1.1M
Input
file · image · text
Output
text
Input: $2Output: $10per 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more...

Context
1.1M
Input
file · image · text
Output
text
Input: $1Output: $5per 1M tokens
View model details →
openai logoopenai

OpenAI: GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

Context
1.1M
Input
file · image · text
Output
text
Input: $2Output: $10per 1M tokens
View model details →