OpenRouter
Catalog quote- Input
- $0.15
- Output
- $0.60
- Cached input
- $0.075
openaiListed Aug 4, 2025
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. The model supports…
Source description
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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Context window131.1K
Max output65.5K
Parameters120B
Provider endpoints40
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
41 quotesPrices across providers
Your token mix
USD · listed token rates- Input
- $0.037
- Output
- $0.17
groq
via Hugging Face- Input
- $0.15
- Output
- $0.75
novita
via Hugging Face- Input
- $0.05
- Output
- $0.25
cerebras
via Hugging Face- Input
- $0.35
- Output
- $0.75
nscale
via Hugging Face- Input
- $0.10
- Output
- $0.40
together
via Hugging Face- Input
- $0.15
- Output
- $0.60
fireworks-ai
via Hugging Face- Input
- $0.15
- Output
- $0.60
featherless-ai
via Hugging Face- Input
- —
- Output
- —
scaleway
via Hugging Face- Input
- $0.171
- Output
- $0.684
baseten
via Hugging Face- Input
- $0.10
- Output
- $0.50
ovhcloud
via Hugging Face- Input
- $0.09
- Output
- $0.47
deepinfra
via Hugging Face- Input
- $0.037
- Output
- $0.17
Experiential
Standard list rate
- Input
- $0.15
- Output
- $0.60
Catalog list rate. Plan allowances and temporary discounts are separate.
Fireworks AI
Standard · service_tier=default
- Input
- $0.15
- Output
- $0.60
- Cached input
- $0.015
Fireworks AI
Standard · service_tier=priority
- Input
- $0.18
- Output
- $0.72
- Cached input
- $0.018
Groq
Production · Developer PAYG
- Input
- $0.15
- Output
- $0.60
- Input
- $0.03
- Output
- $0.15
- Cached input
- $0.015
- Input
- $0.03
- Output
- $0.15
- Cached input
- $0.03
- Input
- $0.03
- Output
- $0.17
- Cached input
- $0.03
- Input
- $0.03
- Output
- $0.18
- Cached input
- $0.03
- Input
- $0.03
- Output
- $0.187
- Cached input
- $0.03
- Input
- $0.037
- Output
- $0.17
- Input
- $0.05
- Output
- $0.25
- Cached input
- $0.05
- Input
- $0.05
- Output
- $0.25
- Input
- $0.05
- Output
- $0.25
- Input
- $0.06
- Output
- $0.42
- Cached input
- $0.012
- Input
- $0.09
- Output
- $0.36
Endpoint degraded (status -5)
- Input
- $0.10
- Output
- $0.50
- Cached input
- $0.10
- Input
- $0.10
- Output
- $0.50
- Cached input
- $0.10
- Input
- $0.10
- Output
- $0.75
- Cached input
- $0.055
- Input
- $0.14
- Output
- $0.95
- Input
- $0.15
- Output
- $0.60
- Input
- $0.15
- Output
- $0.60
- Input
- $0.15
- Output
- $0.60
- Input
- $0.15
- Output
- $0.60
- Cached input
- $0.075
Endpoint degraded (status -2)
- Input
- $0.15
- Output
- $0.60
- Input
- $0.15
- Output
- $0.60
- Input
- $0.15
- Output
- $0.60
- Cached input
- $0.075
- Input
- $0.15
- Output
- $0.75
- Input
- $0.35
- Output
- $0.75
- Cached input
- $0.35
Model specifications
- Developer
- openai
- Modality
- Language
- Context
- 131,072 tokens
- Maximum output
- 65,536 tokens
- Weights
- Open weights
- Provider listed
- Aug 4, 2025
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
openai/gpt-oss-120b - deepinfra
openai/gpt-oss-120b - huggingface
openai/gpt-oss-120b - experiential
gpt-oss-120b
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