Qwen3 Coder 30B A3B
ChatQwen3-Coder-30B-A3B-Instruct-FP8
Qwen3 Coder 30B A3B on FlexAI: Alibaba LLM (Code), Apache 2.0 license, served via the OpenAI-compatible Token Factory at the live market-tracked rate.
Recommended for
Pricing
Input
$0.07 / M tokens
Output
$0.26 / M tokens
Cached input
$0.0105 / M tokens
Context
256K tokens
API endpoint
/v1/chat/completions
Compatibility
OpenAI
Parameters
30B MoE (3B active)
License
Apache 2.0
Hardware
H100
Quantization
FP8
Estimate your monthly cost
M tokens
M tokens
Cache hit rate25%
Share of input tokens served from prompt cache: repeated system prompts, long documents, and multi-turn context.
7.5M × $0.07/M input$0.53
2.5M × $0.0105/M cached input$0.03
2M × $0.26/M output$0.52
Estimated monthly cost$1.08
Saved vs. no caching$0.14 (11%)
Estimate only, at the current market-tracked rate. Usage-based; no minimums.
Get an API keyQuick Start
Qwen3-Coder-30B-A3B-Instruct-FP8
from openai import OpenAI
client = OpenAI(
base_url="https://tokens.flex.ai/v1",
api_key="your-api-key",
)
response = client.chat.completions.create(
model="Qwen3-Coder-30B-A3B-Instruct-FP8",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)