LLMHOSTING.AI the compute price terminal

Qwen3.5 35B A3B API pricing

1 provider serves Qwen3.5 35B A3B. Qwen3.5 35B A3B is an open-weight model (Apache-2.0) with 36B total parameters, 3B active per token (mixture-of-experts), up to 262K context. Prices below are per 1M tokens, cheapest input first (self-hosting math further down).

Refreshed 2026-08-23 · list prices from provider APIs
Input floor $0.250/1M at OpenRouter Output floor $2.00/1M at OpenRouter Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
OpenRouter $0.250 $2.00output floor - 262K Use

The cheapest way to run Qwen3.5 35B A3B

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $77.50/month, at OpenRouter. 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 (~$0.030/1M output on A100 PCIe). See the math below. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

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: Qwen3.5 35B A3B self-hosting economics

Qwen3.5 35B A3B is open-weight (Apache-2.0), so the API price above competes with the GPU-hour market. 36B total parameters (MoE, ~3B active per token) needs roughly 50 GB VRAM at FP8 or 25 GB at INT4, KV-cache headroom included.

GPU that fits (FP8, single card)VRAMFrom $/hrCheapest at
A100 PCIe 80 GB $0.442marketplace Vast.ai Rent
RTX PRO 6000 96 GB $0.500secure RunPod Rent
H200 NVL 141 GB $0.500community RunPod Rent
MI300X 192 GB $0.500community RunPod Rent
A100 SXM 80GB 80 GB $0.667marketplace Vast.ai Rent
H100 SXM 80 GB $1.34marketplace Vast.ai Rent
Breakeven estimate: a well-batched vLLM deployment on one A100 PCIe ($0.442/hr) at ~8250 aggregate tok/s and 50% utilization works out to roughly $0.030 per 1M output tokens, versus $2.00 via the cheapest output-token API (OpenRouter). Self-hosting wins on cost if you can keep the GPU busy. Planning estimate: throughput varies with hardware, quantization, batch size and context. Tune it in the calculator.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Qwen3 235B A22B $0.071 $0.100 10
Qwen3 32B $0.050 $0.100 9
Qwen3 30B A3B $0.051 $0.200 7
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

FAQ

What is the cheapest API for Qwen3.5 35B A3B?

As of 2026-08-23, the lowest input price for Qwen3.5 35B A3B is OpenRouter at $0.250 per 1M input tokens. The lowest output price is OpenRouter at $2.00 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix.

How much VRAM do you need to self-host Qwen3.5 35B A3B?

Qwen3.5 35B A3B has 36B parameters, so plan for roughly 50 GB of VRAM at FP8 or 25 GB at INT4/AWQ, KV-cache headroom included. A single A100 PCIe (80 GB) fits it.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON