deepseek-coder
DeepSeek · chat model
Input
$0.1400 / 1M tokens
Output
$0.2800 / 1M tokens
Cached input
$0.0140 / 1M tokens
Context
4.1K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 1.4e-7 | $0.1400 / 1M tokens |
| Output | 2.8e-7 | $0.2800 / 1M tokens |
| Cached input | N/A | $0.0140 / 1M tokens |
| Embedding | 1.4e-7 | $0.1400 / 1M tokens |
Token limits
Context window
4.1K
Max input tokens
128.0K
Max output tokens
4.1K
Max tokens
4.1K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | No |
| Tool choice | Yes |
| Prompt caching | Yes |
| Reasoning | No |
| 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-chat | OpenRouter | $0.1400 / 1M tokens | $0.2800 / 1M tokens | 8.2K | N/A | Cache |
| deepseek-chat-v3-0324 | OpenRouter | $0.1400 / 1M tokens | $0.2800 / 1M tokens | 8.2K | N/A | Cache |
| Hermes-3-Llama-3.1-70B | hyperbolic | $0.1200 / 1M tokens | $0.3000 / 1M tokens | 32.8K | N/A | Tools |
| Qwen2.5-72B-Instruct | hyperbolic | $0.1200 / 1M tokens | $0.3000 / 1M tokens | 131.1K | N/A | Tools |
| Qwen2.5-Coder-32B-Instruct | hyperbolic | $0.1200 / 1M tokens | $0.3000 / 1M tokens | 32.8K | N/A | Tools |
| Llama-3.2-3B-Instruct | hyperbolic | $0.1200 / 1M tokens | $0.3000 / 1M tokens | 32.8K | N/A | Tools |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"input_cost_per_token": 1.4e-7,
"input_cost_per_token_cache_hit": 1.4e-8,
"litellm_provider": "deepseek",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 2.8e-7,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
}