glm-4.5-air
novita · chat model
Input
$0.1300 / 1M tokens
Output
$0.8500 / 1M tokens
Cached input
N/A
Context
98.3K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 1.3e-7 | $0.1300 / 1M tokens |
| Output | 8.5e-7 | $0.8500 / 1M tokens |
| Embedding | 1.3e-7 | $0.1300 / 1M tokens |
Token limits
Context window
98.3K
Max input tokens
131.1K
Max output tokens
98.3K
Max tokens
98.3K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | Yes |
| Tool choice | Yes |
| 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 |
|---|---|---|---|---|---|---|
| gpt-oss-120b | OpenRouter | $0.1800 / 1M tokens | $0.8000 / 1M tokens | 32.8K | N/A | Tools Reasoning |
| ft:gpt-4.1-nano-2025-04-14 | OpenAI | $0.2000 / 1M tokens | $0.8000 / 1M tokens | 32.8K | N/A | Tools Cache |
| deepseek-chat-v3.1 | OpenRouter | $0.2000 / 1M tokens | $0.8000 / 1M tokens | 163.8K | N/A | Tools Cache Reasoning |
| qwen3-235b-a22b-fp8 | novita | $0.2000 / 1M tokens | $0.8000 / 1M tokens | 20.0K | N/A | Reasoning |
| glm-4p5-air | fireworks_ai | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 96.0K | N/A | Tools Reasoning |
| llama4-maverick-instruct-basic | fireworks_ai | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 131.1K | N/A |
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": 1.3e-7,
"output_cost_per_token": 8.5e-7,
"max_input_tokens": 131072,
"max_output_tokens": 98304,
"max_tokens": 98304,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true,
"supports_system_messages": true,
"supports_reasoning": true
}