Verified provider routes accept text and image input and produce text output. Supported combinations depend on the provider route.

Source 1 · Source 2 · Source 3

Identity and capabilities

Status
active
Local execution
Available weights · transformers · apache-2.0 Hardware requirements and licence restrictions apply.
Context window
262,144
Maximum output
65,536
Image input
Yes
Reasoning
Yes
Tool calling
Yes
Release date
First seen
2026-08-29 19:40:01Z UTC
Last verified

Current offers - prices in USD · per 1M tokens

Prices by provider, service tier, context and offer route
DeepInfraHugging Face Inference Providers⊕ 4 routes ▾Novita AIOpenRouterAlibaba / Qwen
0 < input tokens ≤ 256,000Default offer · Thinking mode
Input————
$0.6
Output————
$3.6
Base contextDeepInfra
Cached input
$0.22
——
$0.3
—
Input
$0.45
$0.45
$0.6
$0.5
—
Output
$3
$3
$3.6
$3.6
—
Hugging Face Inference Providers · 4 routes — show all prices

The main table shows DeepInfra: the lowest available starting token price for 2 input tokens per output token. Other input lengths, service tiers and usage ratios may favour another route.

Prices by provider, service tier, context and offer route
DeepInfra
Novita
Scaleway
Ovhcloud
Input
$0.45
$0.6
$0.684
$0.71
Output
$3
$3.6
$4.104
$4.25

Active promotions

No officially confirmed promotion applies to this model.

Recent price changes

  • Prices moved both ways · cause unverified
    • Input: $0.55 → $0.5
    • Output: $3.5 → $3.6
    OpenRouterqwen/qwen3.5-397b-a17b