glm-4p5-air
fireworks_ai · chat model
Input
$0.2200 / 1M tokens
Output
$0.8800 / 1M tokens
Cached input
N/A
Context
96.0K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 2.2e-7 | $0.2200 / 1M tokens |
| Output | 8.8e-7 | $0.8800 / 1M tokens |
| Embedding | 2.2e-7 | $0.2200 / 1M tokens |
Token limits
Context window
96.0K
Max input tokens
128.0K
Max output tokens
96.0K
Max tokens
96.0K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Function calling | Yes |
| Parallel function calling | No |
| Tool choice | Yes |
| Prompt caching | No |
| Reasoning | Yes |
| Response schema | Yes |
| 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 |
|---|---|---|---|---|---|---|
| llama4-maverick-instruct-basic | fireworks_ai | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 131.1K | N/A | |
| qwen.qwen3-235b-a22b-2507-v1:0 | bedrock_converse | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 131.1K | N/A | Tools Reasoning |
| qwen3-235b-a22b | fireworks_ai | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 131.1K | N/A | |
| qwen3-235b-a22b-instruct-2507 | fireworks_ai | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 262.1K | N/A | |
| qwen3-235b-a22b-thinking-2507 | fireworks_ai | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 262.1K | N/A | |
| qwen3-vl-235b-a22b-instruct | fireworks_ai | $0.2200 / 1M tokens | $0.8800 / 1M tokens | 262.1K | 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": 2.2e-7,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 128000,
"max_output_tokens": 96000,
"max_tokens": 96000,
"mode": "chat",
"output_cost_per_token": 8.8e-7,
"source": "https://artificialanalysis.ai/models/glm-4-5-air",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
}