deepseek-v3-turbo
novita · chat model
Input
$0.4000 / 1M tokens
Output
$1.3000 / 1M tokens
Cached input
N/A
Context
16.0K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 4e-7 | $0.4000 / 1M tokens |
| Output | 0.0000013 | $1.3000 / 1M tokens |
| Embedding | 4e-7 | $0.4000 / 1M tokens |
Token limits
Context window
16.0K
Max input tokens
64.0K
Max output tokens
16.0K
Max tokens
16.0K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | Yes |
| Tool choice | Yes |
| Prompt caching | No |
| Reasoning | No |
| 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 |
|---|---|---|---|---|---|---|
| ernie-4.5-vl-424b-a47b | novita | $0.4200 / 1M tokens | $1.2500 / 1M tokens | 16.0K | N/A | Vision Reasoning |
| qwen3-coder-480b-a35b-instruct | novita | $0.3000 / 1M tokens | $1.3000 / 1M tokens | 65.5K | N/A | Tools |
| qwen-plus | dashscope | $0.4000 / 1M tokens | $1.2000 / 1M tokens | 16.4K | N/A | Tools Reasoning |
| qwen-plus-2025-01-25 | dashscope | $0.4000 / 1M tokens | $1.2000 / 1M tokens | 8.2K | N/A | Tools Reasoning |
| qwen-plus-2025-04-28 | dashscope | $0.4000 / 1M tokens | $1.2000 / 1M tokens | 16.4K | N/A | Tools Reasoning |
| qwen-plus-2025-07-14 | dashscope | $0.4000 / 1M tokens | $1.2000 / 1M tokens | 16.4K | N/A | Tools Reasoning |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"litellm_provider": "novita",
"mode": "chat",
"input_cost_per_token": 4e-7,
"output_cost_per_token": 0.0000013,
"max_input_tokens": 64000,
"max_output_tokens": 16000,
"max_tokens": 16000,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true,
"supports_system_messages": true
}