cinemasetfree.com
← Back to all generators
deepseek-ai/deepseek-r1
OfficialView on Replicate →
A reasoning model trained with reinforcement learning, on par with OpenAI o1
Capabilities
Max TokensTop-P
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
frequency_penalty | number | Frequency penalty | 0 | — |
max_tokens | integer | The maximum number of tokens the model should generate as output. | 2048 | — |
presence_penalty | number | Presence penalty | 0 | — |
prompt | string | Prompt | "" | — |
temperature | number | The value used to modulate the next token probabilities. | 0.1 | — |
top_p | number | Top-p (nucleus) sampling | 1 | — |
frequency_penaltynumberFrequency penalty
Default:
0max_tokensintegerThe maximum number of tokens the model should generate as output.
Default:
2048presence_penaltynumberPresence penalty
Default:
0promptstringPrompt
Default:
""temperaturenumberThe value used to modulate the next token probabilities.
Default:
0.1top_pnumberTop-p (nucleus) sampling
Default:
1Version:
b09db80a5a7fUpdated: 7/25/20262.3M runs