gpt-oss-safeguard-20b
Groq · chat model
Input
$0.0750 / 1M tokens
Output
$0.3000 / 1M tokens
Cached input
$0.0370 / 1M tokens
Context
65.5K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 7.5e-8 | $0.0750 / 1M tokens |
| Output | 3e-7 | $0.3000 / 1M tokens |
| Cached input | 3.7e-8 | $0.0370 / 1M tokens |
| Embedding | 7.5e-8 | $0.0750 / 1M tokens |
Token limits
Context window
65.5K
Max input tokens
131.1K
Max output tokens
65.5K
Max tokens
65.5K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | No |
| Tool choice | Yes |
| Prompt caching | No |
| Reasoning | Yes |
| Response schema | Yes |
| System messages | No |
| Audio input | No |
| Audio output | No |
| Web search | Yes |
| PDF input | No |
| Video input | No |
Similar models
Models with comparable pricing in the same mode (chat).
| Model | Provider | Input | Output | Context | Coding | Features |
|---|---|---|---|---|---|---|
| Phi-4-mini-instruct | azure_ai | $0.0750 / 1M tokens | $0.3000 / 1M tokens | 4.1K | N/A | Tools |
| gemini-2.0-flash-lite | vertex_ai-language-models | $0.0750 / 1M tokens | $0.3000 / 1M tokens | N/A | N/A | Vision Tools Cache |
| gemini-2.0-flash-lite-001 | vertex_ai-language-models | $0.0750 / 1M tokens | $0.3000 / 1M tokens | N/A | N/A | Vision Tools Cache |
| gemini-2.0-flash-lite | $0.0750 / 1M tokens | $0.3000 / 1M tokens | N/A | N/A | Vision Tools Cache | |
| gpt-oss-20b | Groq | $0.0750 / 1M tokens | $0.3000 / 1M tokens | 32.8K | N/A | Tools Reasoning |
| google.gemini-2.5-flash-lite | oci | $0.0750 / 1M tokens | $0.3000 / 1M tokens | 65.5K | N/A | Vision Tools |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"cache_read_input_token_cost": 3.7e-8,
"input_cost_per_token": 7.5e-8,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 3e-7,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_web_search": true
}