Qwen3 30B A3b fp8 pricing & specs
Alibaba (Qwen) · released 2025-04-28 · ● verified 2026-10-11
input / 1M$0.0509via Cloudflare Workers AI
output / 1M$0.335via Cloudflare Workers AI
context32.8K
max output32.8K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Qwen3 30B A3b fp8 |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −59% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −54.9% |
| Qwen Turbo | $0.05 | $0.20 | 1M | −28.2% |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | 1.05M | −26.2% |
| GPT OSS 120B | $0.05 | $0.25 | 131.1K | −18% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Cloudflare Workers AI | $0.0509 | $0.335 |
| DeepInfra | $0.12 | $0.50 |
// faq
How much does Qwen3 30B A3b fp8 cost?
Qwen3 30B A3b fp8 costs $0.0509 per million input tokens and $0.335 per million output tokens (cheapest tracked host: Cloudflare Workers AI). At 50M input and 10M output tokens per month that is about $5.90.
What is the context window of Qwen3 30B A3b fp8?
32.8K tokens, with up to 32.8K output tokens per request.
What are cheaper alternatives to Qwen3 30B A3b fp8?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.
Is Qwen3 30B A3b fp8 open weights?
Yes. It is available from 2 tracked hosts; the cheapest is Cloudflare Workers AI at $0.0509 input and $0.335 output per million tokens.
// spec sheet
- input / 1M
- $0.0509
- output / 1M
- $0.335
- blended (3:1)
- $0.1219
- context
- 32.8K
- max output
- 32.8K
- input types
- text
- reasoning
- yes
- tool calling
- yes
- structured output
- no
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- Cloudflare Workers AI
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Qwen Turbo | $0.05 | $0.20 | $4.50 |
| Qwen3 30B A3b fp8 | $0.0509 | $0.335 | $5.90 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.