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.
| Gemini 4 Carbon google/gemini-4-carbon | Kimi-K3.1-Pro moonshot/kimi-k3.1-pro | |
|---|---|---|
| Provider | Moonshot AI | |
| Family | ||
| Modality | text | text |
| Context window | 1,048,576 tok | 1,048,576 tok |
| Max output | 65,536 tok | 1,048,576 tok |
| Released | 2026-11-11 | 2026-11-05 |
| Input price | $2.00 /1M | $2.00 /1M |
| Output price | $10.00 /1M | $10.00 /1M |
| Cache read | — | — |
| Tools | — | yes |
| Streaming | yes | yes |
| Vision | — | yes |
| JSON mode | — | yes |
| Reasoning | — | yes |
| Prompt caching | — | — |
Google's most capable Gemini 4 reasoning model, built for complex software engineering, math and science problems, autonomous multi-step agents, and long outputs up to 1M tokens.
# 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 Gemini 4 Carbon
client.chat.completions.create(
model="google/gemini-4-carbon",
messages=[{"role":"user","content":"hello"}],
)
# Try Kimi-K3.1-Pro — same client, same key
client.chat.completions.create(
model="moonshot/kimi-k3.1-pro",
messages=[{"role":"user","content":"hello"}],
)