Identity and capabilities

Status
Current
Local execution
Available weights · transformers · other Hardware requirements and licence restrictions apply.
Context window
256,000
Maximum output
235,929
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
CloudflareHugging Face Inference Providers⊕ 2 routes ▾Novita AIOpenRouterMoonshot / Kimi
StandardDeepInfra
Cached input
$0.19
—
$0.19
$0.18
Default offer
$0.19
Cached input————
Highspeed mode
$0.38
Input
$0.95
$0.68
$0.95
$0.6712
Default offer
$0.95
Input————
Highspeed mode
$1.9
Output
$4
$3.4
$4
$3.35
Default offer
$4
Output————
Highspeed mode
$8
Hugging Face Inference Providers · 2 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
Input
$0.68
$0.95
Output
$3.4
$4

Active promotions

No officially confirmed promotion applies to this model.

Recent price changes

No price changes in the last 7 days.