Multimodal
siliconflow-cn
nano-gpt
nvidia
novita-ai
merge-gateway
infomaniak
mixlayer
alibaba
openrouter
Qwen Family
Open Source
Released: Feb 2026
Updated: Aug 2026 Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is a Multimodal model.
Qwen vision-language model for visual reasoning, documents, and agent tasks
Vision
Audio
Tool Use
Reasoning
Citations
Key Specs
Context
262k
Max Output
262k
Best Price (Input / Output)
Chat with Model
$0.12 / $0.92 per 1M tokens
Pricing Comparison
| Provider | Input (1M) | Output (1M) | Image (1k) |
|---|---|---|---|
| nvidia | Free | Free | - |
| merge-gateway | $0.12 | $0.92 | - |
| siliconflow-cn | $0.29 | $2.32 | - |
| openrouter | $0.29 | $2.40 | - |
| alibaba | $0.40 | $3.20 | - |
| mixlayer | $0.40 | $3.20 | - |
| novita-ai | $0.40 | $3.20 | - |
| nano-gpt | $0.44 | $3.50 | - |
| nano-gpt (TEE) | $0.46 | $3.68 | - |
| infomaniak (FP8) | $0.50 | $3.97 | - |
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