Skip to content
OhMyGPT

Search

Search pages, models and actions, or paste a request ID…

GPT-6.2 Astra vs Inkling 2 Small

Compare price, capability score, availability and measured latency for up to 4 models side by side.

Capability
174—
—1403
Priceper 1M tokens
Input
Inputfrom $7.20list $8.00↑ ×21.8$0.33↓
Output
Outputfrom $36.00list $40.00↑ ×32.7$1.10↓
Cache read
Cache readfrom $0.36list $0.40↑ ×10.9$0.033↓
Web searchper request
Web searchper requestfrom $0.009list $0.01—
Limits and modalities
Context
Context1.1M↑1M
Max output
Max output128K↓ 88%1M↑
Modalities
ModalitiesTextImagePDFtoTextTextImagetoText
Availability
Providers
ProvidersAzure AI Foundry, OpenAITogether AI
30-day uptime
30-day uptime——
Measured, last 30 days
Latency (p50)
Latency (p50)——
Cache hit rate
Cache hit rate——
About
Released
Released2026-11-172026-11-05
Knowledge cutoff
Knowledge cutoff2026-05-18—

Capability scores come from independent benchmarks: Epoch AI's ECI index aggregates dozens of public evaluations on a scale anchored at GPT-5 = 150 for direct comparison (CC BY 4.0, as of 2026-11-20). epoch.ai/eci

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text