gpt-oss-120b
cerebras · chat model
Input
$0.3500 / 1M tokens
Output
$0.7500 / 1M tokens
Cached input
N/A
Context
32.8K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 3.5e-7 | $0.3500 / 1M tokens |
| Output | 7.5e-7 | $0.7500 / 1M tokens |
| Embedding | 3.5e-7 | $0.3500 / 1M tokens |
Token limits
Context window
32.8K
Max input tokens
131.1K
Max output tokens
32.8K
Max tokens
32.8K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | Yes |
| Tool choice | Yes |
| Prompt caching | No |
| Reasoning | Yes |
| Response schema | Yes |
| System messages | No |
| Audio input | No |
| Audio output | No |
| Web search | No |
| PDF input | No |
| Video input | No |
Similar models
Models with comparable pricing in the same mode (chat).
| Model | Provider | Input | Output | Context | Coding | Features |
|---|---|---|---|---|---|---|
| meta.llama3-8b-instruct-v1:0 | Bedrock | $0.3600 / 1M tokens | $0.7200 / 1M tokens | 8.2K | N/A | |
| Nemotron-120B-A12B | baseten | $0.3000 / 1M tokens | $0.7500 / 1M tokens | N/A | N/A | |
| meta.llama3-8b-instruct-v1:0 | Bedrock | $0.3900 / 1M tokens | $0.7800 / 1M tokens | 8.2K | N/A | |
| meta.llama3-8b-instruct-v1:0 | Bedrock | $0.3500 / 1M tokens | $0.6900 / 1M tokens | 8.2K | N/A | |
| qwen-3-32b | cerebras | $0.4000 / 1M tokens | $0.8000 / 1M tokens | 128.0K | N/A | Tools Reasoning |
| Qwen3-32B | sambanova | $0.4000 / 1M tokens | $0.8000 / 1M tokens | 8.2K | N/A | Tools Reasoning |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"input_cost_per_token": 3.5e-7,
"litellm_provider": "cerebras",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7.5e-7,
"source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
}