Skip to content
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for openai

OpenAI: gpt-oss-120b

openai/gpt-oss-120b

Model weights
Compare

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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Modalities

In / Out Price

$0.03 / $0.17per 1M

Context

131K

Released

Aug 5, 2025

Knowledge Cutoff

Jun 2024

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
$0.03$0.17$0.031.80s47 tps
99.83%
$0.03$0.17$0.030.52s30 tps
99.84%
$0.037$0.17--0.62s35 tps
99.64%
$0.05$0.25--0.52s68 tps
95.16%
$0.05$0.45--5.22s11 tps
92.83%
$0.085$0.50--0.79s47 tps
99.47%
$0.10$0.50$0.100.27s225 tps
100.00%
$0.10$0.70$0.020.55s36 tps
99.97%
$0.10$0.75$0.0550.46s104 tps
99.99%
$0.14$0.95--0.70s309 tps
99.17%
$0.15$0.60--0.14s163 tps
--
$0.15$0.60--0.42s126 tps
99.87%
$0.15$0.60$0.0750.26s307 tps
99.99%
$0.15$0.60--0.96s60 tps
99.75%
$0.15$0.60--0.40s297 tps
99.65%
$0.15$0.60--0.24s220 tps
99.66%
$0.35$0.75$0.350.22s770 tps
99.99%
$0.09$0.36--0.53s109 tps
82.35%
$0.15$0.60--0.34s65 tps
90.34%
$0.15$0.75--3.11s144 tps
95.33%

Throughput

770tok/s

P50, best across providers

Latency

0.14s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
Amazon Bedrock
75.0%--
Amazon Bedrock
75.0%--
Parasail
77.0%67.8%
Phala
71.9%--
Baseten
76.5%65.7%
AkashML
76.5%65.4%
+14 more providers
Uptime (3d)

100.00%

Availability (3d)

99.73%

Availability over the last 3 days

Last 72 hours
Availability 99.73%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.77%
Without Routing
73.23%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://mira.tg/
Mira
Mira is a Telegram-native AI assistant.
129Btokens
2.
Favicon for https://convosight.com/
cvi-magic-tasks-ai-tagging
new
32.9Btokens
3.
Favicon for https://craftrpgs.com/?utm_source=openrouter
Craft
Build and play AI RPGs
17.4Btokens
4.
Favicon for https://app.makemycv.com/
MakeMyCV
new
10.2Btokens
5.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
9.86Btokens

Frequently asked questions

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 to run on a single H100 GPU with native MXFP4 quantization.

gpt-oss-120b costs $0.03/M input tokens and $0.17/M output tokens, with separate rates for Cache Read at $0.03/M tokens.

gpt-oss-120b has a 131,072 token context window. It supports up to 131,072 completion tokens.

Yes. gpt-oss-120b accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

gpt-oss-120b is served by 18 providers on OpenRouter: AkashML, CoreWeave, DeepInfra (Turbo), NovitaAI, SiliconFlow, Mancer, Google Vertex, Baseten and 10 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

gpt-oss-120b was released on August 5, 2025. Its knowledge cutoff is June 30, 2024.