GPT-oss-120b
GPT-oss-120b is a text model from 
AWS Bedrock with a context window of 131K tokens and max output of 33K tokens. Pricing starts at 0.15 per million input tokens and 0.60 per million output tokens (cheapest at Lemonade (AMD)).
Capabilities
✗ Vision✓ Function Calling✓ Reasoning✓ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Specifications
| Model Key | bedrock_mantle/openai.gpt-oss-120b |
| Provider | AWS Bedrock |
| Provider ID | bedrock_mantle |
| Mode | Text |
| Canonical Name | gpt-oss-120b |
| Context Window | 131K tokens |
| Max Output | 33K tokens |
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | 0.000150 | 0.150 |
| Output Tokens | 0.000600 | 0.600 |
Price Comparison by Provider
Compare prices for GPT-oss-120b across different providers. The same model may be available through multiple providers at different price points.
Provider | Model Key | Input Price, $ | Output Price, $ |
|---|---|---|---|
 IBM watsonx | watsonx/openai/gpt-oss-120b | 0.150 | 0.600 |
 Weights & Biases | wandb/openai/gpt-oss-120b | 0.015 | 0.060 |
 Vertex AI (OpenAI) | vertex_ai/openai/gpt-oss-120b-maas | 0.150 | 0.600 |
 Together AI | together_ai/openai/gpt-oss-120b | 0.150 | 0.600 |
 SambaNova | sambanova/gpt-oss-120b | 3.00 | 4.50 |
 Replicate | replicate/openai/gpt-oss-120b | 0.180 | 0.720 |
 OVHcloud | ovhcloud/gpt-oss-120b | 0.080 | 0.400 |
 OpenRouter | openrouter/openai/gpt-oss-120b | 0.180 | 0.800 |
 AWS Bedrock | openai.gpt-oss-120b-1:0 | 0.150 | 0.600 |
 Ollama | ollama/gpt-oss:120b-cloud | N/A | N/A |
 Novita AI | novita/openai/gpt-oss-120b | 0.050 | 0.250 |
 Lemonade (AMD) | lemonade/gpt-oss-120b-mxfp-GGUF | N/A | N/A |
 Groq | groq/openai/gpt-oss-120b | 0.150 | 0.600 |
 Fireworks AI | fireworks_ai/accounts/fireworks/models/gpt-oss-120b | 0.150 | 0.600 |
 DeepInfra | deepinfra/openai/gpt-oss-120b | 0.050 | 0.450 |
 Databricks | databricks/databricks-gpt-oss-120b | 0.150 | 0.600 |
 Cerebras | cerebras/gpt-oss-120b | 0.350 | 0.750 |
| AWS Bedrock | bedrock_mantle/openai.gpt-oss-120b | 0.150 | 0.600 |
 Azure AI | azure_ai/gpt-oss-120b | 0.150 | 0.600 |
All Variants
All available versions, regions, and API endpoints for GPT-oss-120b.
Model Key | Provider | Mode | Input Price, $ | Output Price, $ | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| bedrock_mantle/openai.gpt-oss-120b | AWS Bedrock | Text | 0.150 | 0.600 | 131K | 33K | no | yes |
| openai.gpt-oss-120b-1:0 | AWS Bedrock | Text | 0.150 | 0.600 | 128K | 128K | no | yes |
| azure_ai/gpt-oss-120b | Azure AI | Text | 0.150 | 0.600 | 131K | 131K | no | yes |
| cerebras/gpt-oss-120b | Cerebras | Text | 0.350 | 0.750 | 131K | 33K | no | yes |
| databricks/databricks-gpt-oss-120b | Databricks | Text | 0.150 | 0.600 | 131K | 131K | no | no |
| deepinfra/openai/gpt-oss-120b | DeepInfra | Text | 0.050 | 0.450 | 131K | 131K | no | yes |
| fireworks_ai/accounts/fireworks/models/gpt-oss-120b | Fireworks AI | Text | 0.150 | 0.600 | 131K | 131K | no | yes |
| groq/openai/gpt-oss-120b | Groq | Text | 0.150 | 0.600 | 131K | 33K | no | yes |
| watsonx/openai/gpt-oss-120b | IBM watsonx | Text | 0.150 | 0.600 | 8K | 8K | no | no |
| lemonade/gpt-oss-120b-mxfp-GGUF | Lemonade (AMD) | Text | N/A | N/A | 131K | 33K | no | yes |
| novita/openai/gpt-oss-120b | Novita AI | Text | 0.050 | 0.250 | 131K | 33K | yes | yes |
| ollama/gpt-oss:120b-cloud | Ollama | Text | N/A | N/A | 131K | 131K | no | yes |
| openrouter/openai/gpt-oss-120b | OpenRouter | Text | 0.180 | 0.800 | 131K | 33K | no | yes |
| ovhcloud/gpt-oss-120b | OVHcloud | Text | 0.080 | 0.400 | 131K | 131K | no | no |
| replicate/openai/gpt-oss-120b | Replicate | Text | 0.180 | 0.720 | N/A | N/A | no | yes |
| sambanova/gpt-oss-120b | SambaNova | Text | 3.00 | 4.50 | 131K | 131K | no | yes |
| together_ai/openai/gpt-oss-120b | Together AI | Text | 0.150 | 0.600 | 128K | N/A | no | yes |
| vertex_ai/openai/gpt-oss-120b-maas | Vertex AI (OpenAI) | Text | 0.150 | 0.600 | 131K | 33K | no | no |
| wandb/openai/gpt-oss-120b | Weights & Biases | Text | 0.015 | 0.060 | 131K | 131K | no | no |