DevPass
by LLM Gateway
ModelsGuidesPricingCompareLeaderboardDocsSign inGet Started

Coding models on DevPass

The coding models on your DevPass plan — filter by pricing tier to see exactly which models count against the weekly premium allowance and which don't.

Compare
Pricing Tier (DevPass)
Capabilities
Provider
Input Price ($/M tokens)
Output Price ($/M tokens)
Context Size (tokens)
107
Models
49
Providers
71
Vision Models
107
Tool-enabled
0
Free Models
Features
Alibaba Cloud(cn-beijing)
qwen-flash
$0.02$0.22$0.00
Alibaba Cloud(singapore)
qwen-flash
$0.05$0.40$0.01
Alibaba Cloud
qwen-flash
$0.05$0.40$0.01
Alibaba Cloud(singapore)
qwen-plus-latest
$0.40$1.20$0.08
Alibaba Cloud(cn-beijing)
qwen-plus-latest
$0.11$0.29$0.02
Alibaba Cloud
qwen-plus-latest
$0.40$1.20$0.08
Alibaba Cloud(us-virginia)
qwen-plus
$0.11$0.29$0.02
Alibaba Cloud(singapore)
qwen-plus
$0.40$1.20$0.08
Alibaba Cloud(cn-beijing)
qwen-plus
$0.11$0.29$0.02
Alibaba Cloud
qwen-plus
$0.40$1.20$0.08
Nebius AI
kimi-k2
$0.50$2.40—
ByteDance
kimi-k2
$0.60$2.50$0.12
Moonshot AI
kimi-k2
$0.60$2.50$0.15
NovitaAI
kimi-k2
$0.57$2.30—
Alibaba Cloud
kimi-k2
$0.57$2.29—
Alibaba Cloud(cn-beijing)
kimi-k2
$0.57$2.29—
Groq
kimi-k2
$1.00$3.00$0.50
xAI
grok-code-fast-1
$0.20$1.50$0.02
xAI
grok-4-0709
$3.00$15.00$0.75
xAI
grok-3
$3.00$15.00$0.75
Google AI Studio
gemini-2.5-flash
$0.30$2.50$0.03
Google Vertex AI
gemini-2.5-flash
$0.30$2.50$0.03
Google Vertex AI
gemini-2.5-pro
$1.25$10.00$0.13
Google AI Studio
gemini-2.5-pro
$1.25$10.00$0.13
Azure
gpt-5-nano
$0.05$0.40$0.01
OpenAI
gpt-5-nano
$0.05$0.40$0.01
OpenAI
gpt-5-mini
$0.25$2.00$0.02
Azure
gpt-5-mini
$0.25$2.00$0.02
OpenAI
gpt-5
$1.25$10.00$0.13
Azure
gpt-5
$1.25$10.00$0.13
Azure
gpt-4.1-nano
$0.10$0.40$0.02
OpenAI
gpt-4.1-nano
$0.10$0.40$0.02
Azure
gpt-4.1-mini
$0.40$1.60$0.10
OpenAI
gpt-4.1-mini
$0.40$1.60$0.10
OpenAI
gpt-4.1
$2.00$8.00$0.50
Azure
gpt-4.1
$2.00$8.00$0.50
OpenAI
gpt-4o
$2.50$10.00$1.25
Azure
gpt-4o
$2.50$10.00$1.25
OpenAI
gpt-4o-mini
$0.15$0.60$0.07
Page 6 of 6

Premium vs. standard models

Premium is a pricing classification, not a marketing tag: a model is premium when any provider charges $5+ per million input tokens or $15+ per million output tokens. Premium usage is covered by a weekly fair-use allowance on top of your plan credits: 12% of monthly credits on Lite, 15% on Pro, and 18% on Max. The allowance works on a fixed 7-day window that opens with your first premium request and fully resets when it ends.

Standard models have no weekly cap — use them as much as your plan credits allow. Use the Pricing Tier filter above to see exactly which models fall on each side; premium models are also marked with a gem icon.

Newsletter

Stay ahead of the curve

Join developers who get weekly insights on new models, cost optimization, and AI coding tips — straight to their inbox.

No spam. Unsubscribe anytime.

DevPass
by LLM Gateway — one API for 200+ models

Product

  • Coding Models
  • Pricing
  • Compare Plans
  • All Models
  • LLM Gateway

Resources

  • Documentation
  • Integrations
  • Blog

Community

  • Discord
  • Twitter
  • GitHub

© 2026 LLM Gateway. All rights reserved.

Privacy PolicyTerms of Use