OpenAI: gpt-oss-120b (exacto)
Analysis Summary
OpenAI's gpt-oss-120b (exacto) is a variant of the 120B open-weight model with tool use, function calling, and a 131K context window at very low cost ($0.039 input, $0.19 output). No benchmark data exists for this specific variant, so its reasoning, coding, or agentic performance cannot be assessed independently.
The base gpt-oss-120b model has benchmark data showing a reasonable intelligence index, so this variant may perform similarly, but without confirmation it must be treated as unverified. Businesses should not assume parity with the benchmarked sibling.
For cost-sensitive, high-volume workloads where the base model has already been validated internally, this variant may be worth testing. For new deployments, use the benchmarked version until this variant's performance is confirmed.
Assessed June 6, 2026
Editorial notes
GPT-OSS-120B (exacto) from OpenAI has tool use, function calling, and low pricing, but no benchmark data is available to verify its capability in this specific variant.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How OpenAI: gpt-oss-120b (exacto) compares
Its 131K-token context window is larger than 59% of the models we list. At $0.04 per million input tokens it is cheaper than 74% of comparable models.
About OpenAI: gpt-oss-120b (exacto)
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.
Capabilities
How does OpenAI: gpt-oss-120b (exacto) stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
openai/gpt-oss-120b:exacto
|
| Provider | openai |
| Release Date | August 5, 2025 |
| Context Length | 131,072 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.04 | $0.000039 |
| Output | $0.19 | $0.000190 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about OpenAI: gpt-oss-120b (exacto)
How much does OpenAI: gpt-oss-120b (exacto) cost?
OpenAI: gpt-oss-120b (exacto) costs $0.04 per million input tokens and $0.19 per million output tokens.
What is the context window of OpenAI: gpt-oss-120b (exacto)?
OpenAI: gpt-oss-120b (exacto) has a context window of 131,072 tokens (131K).
What can OpenAI: gpt-oss-120b (exacto) do?
OpenAI: gpt-oss-120b (exacto) supports tool use and function calling.
Who created OpenAI: gpt-oss-120b (exacto)?
OpenAI: gpt-oss-120b (exacto) is developed by OpenAI and was released on August 5, 2025.
