deepseek-r1
replicate · chat model
Input
$3.7500 / 1M tokens
Output
$10.0000 / 1M tokens
Cached input
N/A
Context
8.2K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 0.00000375 | $3.7500 / 1M tokens |
| Output | 0.00001 | $10.0000 / 1M tokens |
| Reasoning output | 0.00001 | $10.0000 / 1M tokens |
| Embedding | 0.00000375 | $3.7500 / 1M tokens |
Token limits
Context window
8.2K
Max input tokens
65.5K
Max output tokens
8.2K
Max tokens
8.2K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | No |
| Parallel function calling | No |
| Tool choice | No |
| Prompt caching | No |
| Reasoning | Yes |
| Response schema | No |
| System messages | Yes |
| 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 |
|---|---|---|---|---|---|---|
| mistral-large | watsonx | $3.0000 / 1M tokens | $10.0000 / 1M tokens | 16.4K | N/A | Tools Cache |
| mistral-medium-2505 | watsonx | $3.0000 / 1M tokens | $10.0000 / 1M tokens | 128.0K | N/A | Tools |
| us.writer.palmyra-x4-v1:0 | bedrock_converse | $2.5000 / 1M tokens | $10.0000 / 1M tokens | 8.2K | N/A | Tools |
| writer.palmyra-x4-v1:0 | bedrock_converse | $2.5000 / 1M tokens | $10.0000 / 1M tokens | 8.2K | N/A | Tools |
| gpt-4o-2024-08-06 | Azure | $2.5000 / 1M tokens | $10.0000 / 1M tokens | 16.4K | N/A | Vision Tools Cache |
| gpt-4o-2024-11-20 | Azure | $2.5000 / 1M tokens | $10.0000 / 1M tokens | 16.4K | N/A | Vision Tools |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"input_cost_per_token": 0.00000375,
"output_cost_per_token": 0.00001,
"output_cost_per_reasoning_token": 0.00001,
"litellm_provider": "replicate",
"mode": "chat",
"max_input_tokens": 65536,
"max_output_tokens": 8192,
"max_tokens": 8192,
"supports_reasoning": true,
"supports_system_messages": true
}