Multimodal
inferx
deepinfra
siliconflow-cn
nano-gpt
hetzner
umans-ai-coding-plan
neuralwatt
wandb
blueclaw
scaleway
merge-gateway
empiriolabs
alibaba
openrouter
Qwen Family
Open Source
Released: Apr 2026
Updated: Aug 2026 Qwen3.6 35B-A3B
Qwen3.6 35B-A3B is a Multimodal model.
Open multimodal Qwen MoE for local agents that need vision, audio, and code
Vision
Audio
Tool Use
Reasoning
Citations
Key Specs
Context
262k
Max Output
262k
Best Price (Input / Output)
Chat with Model
$0.07 / $0.42 per 1M tokens
Pricing Comparison
| Provider | Input (1M) | Output (1M) | Image (1k) |
|---|---|---|---|
| hetzner (FP8) | Free | Free | - |
| inferx (FP8) | Free | Free | - |
| umans-ai-coding-plan | Free | Free | - |
| empiriolabs | $0.07 | $0.42 | - |
| deepinfra | $0.10 | $0.95 | - |
| nano-gpt | $0.11 | $0.80 | - |
| openrouter | $0.15 | $1.00 | - |
| nano-gpt (TEE) | $0.20 | $1.27 | - |
| siliconflow-cn | $0.23 | $1.86 | - |
| alibaba | $0.25 | $1.49 | - |
| merge-gateway | $0.25 | $1.49 | - |
| scaleway | $0.25 | $1.50 | - |
| wandb | $0.25 | $1.25 | - |
| neuralwatt | $0.29 | $1.15 | - |
Prices are per 1 million tokens unless otherwise noted. Image pricing is per 1000 images if applicable.
Price History
Prompt Price
Completion Price
Price trend per 1 million tokens over time.
Supported Parameters
frequency_penalty
reasoning
min_p
structured_outputs
response_format
include_reasoning
stop
top_k
max_tokens
top_logprobs
temperature
presence_penalty
tools
seed
tool_choice
logit_bias
logprobs
repetition_penalty
top_p