Skip to main content

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. 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.

Model card on Hugging Face
Input / output price
$0.037 / $0.17 per 1M
Context
131K tokens
Released
Aug 5, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "gpt-oss-120b".

Read docs

Providers

16 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/gpt-oss-120b
$0.037/M$0.17/M
DeepInfradeepinfra/gpt-oss-120b
$0.037/M$0.17/M
NovitaRetiringnovita/gpt-oss-120b
$0.05/M$0.25/M
Teratera/gpt-oss-120b
$0.09/M$0.36/M
Basetenbaseten/gpt-oss-120b
$0.10/M$0.50/M

Is a provider down? AWS Bedrock status, Groq status, OpenRouter status

Pricing

Averaged across 16 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.15 per 1M
Average output
$0.53 per 1M
Average cache read
$0.15 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.35/MCerebras and Prime IntellectLowest$0.037/MConcentrate and DeepInfra

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

1026tokens/sacross providers

Faster than 96% of the other 596 models on the gateway

Time to first token

Lower is better

0.7sacross providers

Faster than 83% of the other 153 models on the gateway

Response latency

Lower is better

1.6sacross providers

Faster than 52% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 12 published scores from 8 sources, each linked to where it was published.

16.4/ 100

Respan Index#151 of 176

176 ranked models. The shaded band is this model's 95% interval, 12.8 to 22.7. Qwen3 235B-A22B and Claude 3.5 Sonnet fall inside it, so the gap is within the margin of error.
GPT OSS 120B by category: Coding 6.8, Agents 7.9, Reasoning 22.8, Knowledge & language 11.7 (estimated), Human preference 39.0
  1. 151gpt-oss-120b16.4
  2. 150Qwen3 235B-A22B16.7
  3. 151Claude 3.5 Sonnet16.4

Published scores

BenchmarkScore
SWE-bench VerifiedOpenAI62.4%
WeirdMLHåvard Tveit Ihle48.2%

Compare GPT OSS 120B: gpt-oss-120b vs gpt-oss-20b, gpt-oss-120b vs GPT-6.2 Astra, gpt-oss-120b vs GPT-6 Astra, gpt-oss-120b vs GPT-6.1 Sol, gpt-oss-120b vs GPT-6.1 Terra, gpt-oss-120b vs GPT-6.2 Sol

Apps

Use GPT OSS 120B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

GPT OSS 120B FAQ

Short answers, built from the data on this page.

GPT OSS 120B is a model from OpenAI, released on Aug 5, 2025. 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.

On the Respan gateway, GPT OSS 120B costs from $0.037 per 1M input tokens and $0.17 per 1M output tokens on Concentrate and DeepInfra, after gateway discounts. Averaged across its 16 providers, it costs $0.15 per 1M input tokens and $0.53 per 1M output tokens.

GPT OSS 120B is available through 16 providers: Concentrate, DeepInfra, Novita, Tera, Baseten, Parasail, and 10 more.

GPT OSS 120B accepts up to 131K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "gpt-oss-120b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

GPT OSS 120B scores 16.4 out of 100 on the Respan Index v1.1, ranking #151 of 176 models. By category: Coding 6.8, Agents 7.9, Reasoning 22.8, Knowledge & language 11.7 (estimated), and Human preference 39.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

GPT OSS 120B has 12 published benchmark scores, including SWE-bench Verified 62.4%, APEX-Agents 4.4%, and GPQA Diamond 80.1%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.