Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Decisions openai/decisions | Recraft V4.1 Flash recraft/recraftv4-1-flash | |
|---|---|---|
| Provider | OpenAI | Recraft |
| Family | Recraft | |
| Modality | text | image |
| Context window | 1,050,000 tok | — |
| Max output | 32,768 tok | — |
| Released | 2026-10-26 | 2026-10-14 |
| Input price | $0.100 /1M | $0.0070 /img |
| Output price | $0.0000 /1M | — |
| Cache read | — | — |
| Tools | — | — |
| Streaming | yes | — |
| Vision | — | — |
| JSON mode | — | — |
| Reasoning | — | — |
| Prompt caching | — | — |
Decisions uses GPT-6 Luna to evaluate shared text or image evidence against typed questions. It returns probabilities, fixed choices, or rubric scores for low-latency classification, routing, and prioritization workflows.
Recraft V4.1 Flash is Recraft's fastest and lowest-cost image model, generating a 1K raster image in about 1.3 seconds with quality close to Recraft V4.1. Built for high-volume generation and rapid iteration, with strong results for photography, portraits, atmospheric scenes, mixed media, and logo concepts. It outputs raster images only and does not support styles.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Decisions
client.chat.completions.create(
model="openai/decisions",
messages=[{"role":"user","content":"hello"}],
)
# Try Recraft V4.1 Flash — same client, same key
client.chat.completions.create(
model="recraft/recraftv4-1-flash",
messages=[{"role":"user","content":"hello"}],
)