Qwen3 30B A3B API pricing
7 providers serve Qwen3 30B A3B. Qwen3 30B A3B is an open-weight model (Apache-2.0) with 30.5B total parameters, 3.3B active per token (mixture-of-experts), up to 131K context. Prices below are per 1M tokens, cheapest input first (self-hosting math further down).
Refreshed 2026-08-23 · list prices from provider APIs| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context | |
|---|---|---|---|---|---|
| Cloudflare | $0.051 | $0.335 | - | 33K | Use |
| DeepInfra | $0.080 | $0.290 | - | 41K | Use |
| Novita AI | $0.090 | $0.450 | - | 41K | Use |
| Pinstripes | $0.090 | $0.200output floor | - | 131K | |
| Nebius | $0.100 | $0.300 | - | 33K | Use |
| OpenRouter marketplace quote | $0.120 | $0.500 | - | 131K | Use |
| Fireworks AI | $0.150 | $0.600 | - | 131K | Use |
The cheapest way to run Qwen3 30B A3B
On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $12.30/month, at Pinstripes. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. On output-token cost alone, a busy self-hosted deployment can work out cheaper (~$0.029/1M output on A6000). See the math below. Run your own numbers in the breakeven calculator, or read the breakeven math.
Your actual monthly cost
Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.
Or run it yourself: Qwen3 30B A3B self-hosting economics
Qwen3 30B A3B is open-weight (Apache-2.0), so the API price above competes with the GPU-hour market. 30.5B total parameters (MoE, ~3.3B active per token) needs roughly 42 GB VRAM at FP8 or 21 GB at INT4, KV-cache headroom included.
| GPU that fits (FP8, single card) | VRAM | From $/hr | Cheapest at | |
|---|---|---|---|---|
| A6000 | 48 GB | $0.287marketplace | Vast.ai | Rent |
| A40 | 48 GB | $0.350community | RunPod | Rent |
| 6000 Ada | 48 GB | $0.388marketplace | Vast.ai | Rent |
| L40 | 48 GB | $0.402marketplace | Vast.ai | Rent |
| A100 PCIe | 80 GB | $0.442marketplace | Vast.ai | Rent |
| L40S | 48 GB | $0.467marketplace | Vast.ai | Rent |
Related models
| Model | Cheapest in $/1M | Cheapest out $/1M | Providers |
|---|---|---|---|
| Qwen3 235B A22B | $0.071 | $0.100 | 10 |
| Qwen3 32B | $0.050 | $0.100 | 9 |
| Qwen3 Next 80B A3B Instruct | $0.100 | $0.900 | 7 |
| Qwen3 Next 80B A3B Thinking | $0.140 | $0.900 | 7 |
| Qwen3-Coder-480b-A35b-Instruct | $0.220 | $1.30 | 6 |
| Qwen3 VL 235B A22B Instruct | $0.210 | $0.880 | 5 |
FAQ
What is the cheapest API for Qwen3 30B A3B?
As of 2026-08-23, the lowest input price for Qwen3 30B A3B is Cloudflare at $0.051 per 1M input tokens. The lowest output price is Pinstripes at $0.200 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is DeepInfra at $0.080, a 57% difference.
How much VRAM do you need to self-host Qwen3 30B A3B?
Qwen3 30B A3B has 30.5B parameters, so plan for roughly 42 GB of VRAM at FP8 or 21 GB at INT4/AWQ, KV-cache headroom included. A single A6000 (48 GB) fits it.
← All models · GPU rental prices · Breakeven calculator · Get this data as JSON