GPT-5 · OpenAI-compatible · one key, all models
The same GPT-5, from $10/month
Same OpenAI upstream, same quality — plans from $10/month include every frontier model, with monthly usage worth up to 4.5× the price. Change one line of base_url and your existing OpenAI SDK just works. Try it below, sign in when you are ready.
Best for general AI apps, agents, search, and high-volume API workloads
You pay
$10
per month on the Go plan
You get
$45
of monthly model usage — 4.5× the price
↓ Go $10 · Pro $30 · Max $100 per month — usage worth up to 4.5× the price
Playground (edit before sign-up)
model: gpt-5temp 0.7 · 1024 tok
temperature 0.7max_tokens 1024top_p 1.0
▶ Sign in to runGoogle / GitHub one-click · no credit card to startEst. this run ≈ $0.004 (flatkey · official ≈ $0.006)
Pricing vs official
| GPT-5 output | $6.7 |
| GPT-5 mini output | $1.3 |
| GPT-5 input | $0.83 |
| Cache reads | 50% off |
| Coverage | GPT · Gemini · Claude · DeepSeek · Kimi · Seedance |
* Illustrative pricing — see flatkey pricing page
Live model data from pricing API
gpt-5.5
OpenAI
Input / 1M
$5
Output / 1M
$30
openai
Matched live models
gpt-5.5
OpenAI
gpt-5.5-fk-cx
OpenAI
gpt-5.6-sol-openai-compact
OpenAI
gpt-5.6-terra
OpenAI
AI app backends
Agent workflows
Batch content generation
migrate.py — change one line
# Your existing OpenAI code: from openai import OpenAI client = OpenAI( base_url="https://router.flatkey.ai/v1", api_key="sk-flatkey-...", ) response = client.chat.completions.create( model="gpt-5.5", messages=[{"role": "user", "content": "Hello"}], ) print(response.choices[0].message.content)
Does this use the same model id in my SDK?
Yes. Keep your SDK and switch base_url plus api_key.
Can I control usage before scaling?
Yes. Plan limits, usage analytics, and one invoice keep spend bounded.
One subscription covers every model
Text, image and video in one plan · overage billed as you go · cancel anytime
Go — $10/mo, up to $45 usageStarter / individual
Pro — $30/mo, up to $90 usageMost popular
Max — $100/mo, up to $300 usageTeam / high-volume