Capabilities and specifications
- Creator
- OpenAI
- Model family
- gpt-oss
- Knowledge cutoff
- Not documented
- License
- Not documented
- Release date
- 2025-08-05
- Model ID
openai/gpt-oss-120b
Open GPT reasoning model for self-hosted agents and controllable deployments
openai/gpt-oss-120bProvider-specific identifiers, limits, and prices per million tokens.
| Provider | Provider model ID | Context | Input | Output | Cache read | Capabilities | Source |
|---|---|---|---|---|---|---|---|
gpt-oss-120b |
131.072K | Not listed | Not listed | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
128K | Not listed | Not listed | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.03 | $0.17 | $0.03 | ReasoningToolsJSON | Docs | |
gpt-oss-120b |
131.072K | $0.032 | $0.14 | $0.032 | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.037 | $0.17 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.037 | $0.17 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.039 | $0.19 | - | ReasoningTools | Docs | |
openai/gpt-oss-120b |
131.072K | $0.04 | $0.4 | $0.02 | Tools | Docs | |
openai/gpt-oss-120b |
131.072K | $0.05 | $0.25 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131K | $0.05 | $0.45 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
128K | $0.05 | $0.25 | - | ReasoningToolsJSON | Docs | |
databricks-gpt-oss-120b |
131.072K | $0.072 | $0.28 | - | ReasoningToolsJSON | Docs | |
gpt-oss-120b |
131.072K | $0.072 | $0.28 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
128K | $0.08 | $0.44 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b-maas |
131.072K | $0.09 | $0.36 | - | ReasoningTools | Docs | |
openai/gpt-oss-120b |
131.072K | $0.09 | $0.36 | - | Reasoning | Docs | |
openai/gpt-oss-120b |
131.072K | $0.1 | $0.5 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.1 | $0.5 | - | ReasoningTools | Docs | |
openai/gpt-oss-120b |
128.072K | $0.1 | $0.5 | - | ReasoningToolsJSON | Docs | |
hf:openai/gpt-oss-120b |
131.072K | $0.1 | $0.1 | $0.1 | ReasoningTools | Docs | |
accounts/fireworks/models/gpt-oss-120b |
131.072K | $0.15 | $0.6 | $0.015 | ReasoningTools | Docs | |
openai/gpt-oss-120b |
128K | $0.15 | $0.6 | $0.015 | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.15 | $0.6 | $0.075 | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131K | $0.15 | $0.55 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.15 | $0.6 | $0.015 | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.15 | $0.6 | - | ReasoningTools | Docs | |
gpt-oss-120b |
131.072K | $0.15 | $0.6 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.15 | $0.6 | - | ReasoningTools | Docs | |
gpt-oss-120b |
128K | $0.15 | $0.55 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131.072K | $0.15 | $0.6 | - | ReasoningToolsJSON | Docs | |
gpt-oss-120b |
131.072K | $0.178 | $0.612 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
128K | $0.22 | $0.83 | - | ReasoningToolsJSON | Docs | |
gpt-oss-120b |
131.072K | $0.228 | $0.798 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
65.536K | $0.23 | $0.92 | - | ReasoningTools | Docs | |
openai/gpt-oss-120b |
131.072K | $0.25 | $0.69 | - | ReasoningToolsJSON | Docs | |
@cf/openai/gpt-oss-120b |
128K | $0.35 | $0.75 | - | ReasoningToolsJSON | Docs | |
gpt-oss-120b |
131.072K | $0.35 | $0.75 | - | ReasoningToolsJSON | Docs | |
openai/gpt-oss-120b |
131K | $0.53 | $0.76 | - | ReasoningTools | Docs | |
openai/gpt-oss-120b |
131K | $2.92 | $2.92 | - | ReasoningToolsJSON | Docs |
Capability badges appear only when the provider catalog explicitly lists support.
Observed serving measurements stay separate from model specifications and are never estimated from price or model size.
Generation speed; higher is faster.
Time until the first output token arrives.
Successful requests over a measured period.
Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.
Raw results remain attached to their original source and version.
Detected changes from successful source imports.
Fetch the complete source-linked model record without an API key.
GET https://www.modelbench.lol/api/v1/models/openai/gpt-oss-120bcurl "https://www.modelbench.lol/api/v1/models/openai/gpt-oss-120b"