deepseek-r1
DeepSeek · chat model
Input
$0.5500 / 1M tokens
Output
$2.1900 / 1M tokens
Cached input
$0.1400 / 1M tokens
Context
8.2K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 5.5e-7 | $0.5500 / 1M tokens |
| Output | 0.00000219 | $2.1900 / 1M tokens |
| Cached input | N/A | $0.1400 / 1M tokens |
| Embedding | 5.5e-7 | $0.5500 / 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 | Yes |
| Parallel function calling | No |
| Tool choice | Yes |
| Prompt caching | Yes |
| Reasoning | Yes |
| Response schema | No |
| 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 |
|---|---|---|---|---|---|---|
| deepseek-r1-basic | fireworks_ai | $0.5500 / 1M tokens | $2.1900 / 1M tokens | 20.5K | N/A | |
| glm-4p5 | fireworks_ai | $0.5500 / 1M tokens | $2.1900 / 1M tokens | 96.0K | N/A | Tools Reasoning |
| glm-4p6 | fireworks_ai | $0.5500 / 1M tokens | $2.1900 / 1M tokens | 202.8K | N/A | Tools Reasoning |
| deepseek-r1 | OpenRouter | $0.5500 / 1M tokens | $2.1900 / 1M tokens | 8.2K | N/A | Tools Cache Reasoning |
| DeepSeek-R1-0528-tput | Together AI | $0.5500 / 1M tokens | $2.1900 / 1M tokens | N/A | N/A | Tools |
| deepseek-r1 | vercel_ai_gateway | $0.5500 / 1M tokens | $2.1900 / 1M tokens | 8.2K | N/A |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"input_cost_per_token": 5.5e-7,
"input_cost_per_token_cache_hit": 1.4e-7,
"litellm_provider": "deepseek",
"max_input_tokens": 65536,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.00000219,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
}