OpenRouter
Catalog quote- Input
- $0.018
- Output
- $0.09
- Cached input
- $0.009
openaiListed Aug 4, 2025
gpt-oss-20b
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…
Source description
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 lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
Context window131.1K
Max output32.8K
Parameters20B
Provider endpoints20
Benchmark results0
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Access & cost
20 quotesPrices across providers
Your token mix
USD · listed token rates- Input
- $0.03
- Output
- $0.14
groq
via Hugging Face- Input
- $0.10
- Output
- $0.50
nscale
via Hugging Face- Input
- $0.05
- Output
- $0.20
featherless-ai
via Hugging Face- Input
- —
- Output
- —
ovhcloud
via Hugging Face- Input
- $0.05
- Output
- $0.18
deepinfra
via Hugging Face- Input
- $0.03
- Output
- $0.14
Experiential
Standard list rate
- Input
- $0.61
- Output
- $2.94
Catalog list rate. Plan allowances and temporary discounts are separate.
Groq
Production · Developer PAYG
- Input
- $0.075
- Output
- $0.30
- Input
- $0.018
- Output
- $0.09
- Cached input
- $0.009
- Input
- $0.02
- Output
- $0.10
- Input
- $0.029
- Output
- $0.14
- Cached input
- $0.029
- Input
- $0.03
- Output
- $0.13
- Cached input
- $0.03
- Input
- $0.03
- Output
- $0.14
- Input
- $0.03
- Output
- $0.15
- Cached input
- $0.02
- Input
- $0.04
- Output
- $0.18
Endpoint degraded (status -2)
- Input
- $0.07
- Output
- $0.15
- Input
- $0.07
- Output
- $0.15
- Input
- $0.07
- Output
- $0.25
- Input
- $0.075
- Output
- $0.30
- Cached input
- $0.0375
Model specifications
- Developer
- openai
- Modality
- Language
- Context
- 131,072 tokens
- Maximum output
- 32,768 tokens
- Weights
- Open weights
- Provider listed
- Aug 4, 2025
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
openai/gpt-oss-20b - deepinfra
openai/gpt-oss-20b - huggingface
openai/gpt-oss-20b - experiential
gpt-oss-20b
Sources
Updated Oct 18, 2026
More from openai
View all ↗openaiListed 18 days ago
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...
1.1M contextImage inputTool callingNo reported score
No reported score
$1.00in$5.00out/ 1M tokens · USDOpenAI · via OpenRouter · 8 endpointsopenai/flex · tier=flex · prompt ≤ 272000 tokens
openaiListed 18 days ago
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...
1.1M contextImage inputTool callingNo reported score
No reported score
$1.00in$5.00out/ 1M tokens · USDOpenAI · via OpenRouter · 2 endpointsopenai · prompt ≤ 272000 tokens
openaiListed 18 days ago
OpenAI: GPT-6.1 Sol (batch)
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...
1.1M contextImage inputTool callingNo reported score
No reported score
$1.00in$5.00out/ 1M tokens · USDOpenAI · via OpenRouter · 2 endpointsopenai · prompt ≤ 272000 tokens
openaiReleased 19 days ago
OpenAI: GPT-6.1 Sol
Requires Responses API for tools; offers Ultrafast inference with US or EU data residency.
1.1M contextImage inputTool calling
AA IntelligenceEffort: max · Max51.83LiveBenchEffort: max · single run · equal mean of 7 suites85.41%
$1.00in$5.00out/ 1M tokens · USDOpenAI · via OpenRouter · 10 endpointsopenai/flex · tier=flex · prompt ≤ 272000 tokens