Qwen: Qwen3.8 2.4T A95B (batch) API pricing
Token pricing
| Model | Provider | Input / 1M | Output / 1M | Context | Modalities |
|---|---|---|---|---|---|
| Qwen: Qwen3.8 2.4T A95B (batch) | Qwen | $2.00 | $6.00 | 1,010,000 (1M) | texttext |
Capabilities
Context window
1,010,000 (1M)
Max output
909,000 (909K)
Input modalities
text
Output modalities
text
Supported parameters
frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p
Similar models
| Model | Input / 1M | Output / 1M | Context | Modalities |
|---|---|---|---|---|
| Qwen: Qwen3.8 Max (0902) | $2.00 | $6.00 | 1,000,000 (1M) | text, image, videotext |
| Qwen: Qwen3.8 2.4T A95B | $2.00 | $6.00 | 1,048,576 (1M) | texttext |
| Qwen: Qwen3.7 Max | $1.475 | $4.425 | 1,000,000 (1M) | texttext |
| Qwen: Qwen3.6 Max Preview | $1.027 | $6.162 | 262,144 (262K) | texttext |
| Qwen: Qwen2.5 VL 72B Instruct | $0.80 | $1.00 | 128,000 (128K) | text, imagetext |
| Qwen: Qwen3 Max | $0.78 | $3.90 | 262,144 (262K) | texttext |
| Qwen: Qwen3 Max Thinking | $0.78 | $3.90 | 262,144 (262K) | texttext |
| Qwen2.5 Coder 32B Instruct | $0.66 | $1.00 | 32,768 (33K) | texttext |