gpt-oss-20b
ovhcloud · chat model
Input
$0.0400 / 1M tokens
Output
$0.1500 / 1M tokens
Cached input
N/A
Context
131.0K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 4e-8 | $0.0400 / 1M tokens |
| Output | 1.5e-7 | $0.1500 / 1M tokens |
| Embedding | 4e-8 | $0.0400 / 1M tokens |
Token limits
Context window
131.0K
Max input tokens
131.0K
Max output tokens
131.0K
Max tokens
131.0K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | No |
| Parallel function calling | No |
| Tool choice | No |
| 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 |
|---|---|---|---|---|---|---|
| gpt-oss-20b | deepinfra | $0.0400 / 1M tokens | $0.1500 / 1M tokens | 131.1K | N/A | Tools |
| gpt-oss-20b | novita | $0.0400 / 1M tokens | $0.1500 / 1M tokens | 32.8K | N/A | Vision Reasoning |
| apac.amazon.nova-micro-v1:0 | bedrock_converse | $0.0370 / 1M tokens | $0.1480 / 1M tokens | 10.0K | N/A | Tools Cache |
| qwen3-8b | llamagate | $0.0400 / 1M tokens | $0.1400 / 1M tokens | 8.2K | N/A | Tools |
| NVIDIA-Nemotron-Nano-9B-v2 | deepinfra | $0.0400 / 1M tokens | $0.1600 / 1M tokens | 131.1K | N/A | Tools |
| amazon.nova-micro-v1:0 | bedrock_converse | $0.0350 / 1M tokens | $0.1400 / 1M tokens | 10.0K | N/A | Tools Cache |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"input_cost_per_token": 4e-8,
"litellm_provider": "ovhcloud",
"max_input_tokens": 131000,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.5e-7,
"source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b",
"supports_function_calling": false,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": false
}