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.
| Nemotron-3-120b-A12b nvidia/nemotron-3-120b-a12b | Claude Haiku 4.5 anthropic/claude-haiku-4.5 | |
|---|---|---|
| Provider | Nvidia | Anthropic |
| Family | Claude 4 | |
| Modality | text | text |
| Context window | 131,072 tok | 200,000 tok |
| Max output | 4,096 tok | 8,192 tok |
| Released | 2026-02-24 | 2026-04-13 |
| Input price | $0.500 /1M | $1.00 /1M |
| Output price | $1.20 /1M | $5.00 /1M |
| Cache read | — | $0.100 /1M |
| Tools | yes | yes |
| Streaming | yes | yes |
| Vision | — | yes |
| JSON mode | yes | yes |
| Reasoning | yes | — |
| Prompt caching | — | yes |
NVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.
Claude Haiku 4.5 delivers similar levels of coding performance at one-third the cost and more than twice the speed of larger models.
# 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 Nemotron-3-120b-A12b
client.chat.completions.create(
model="nvidia/nemotron-3-120b-a12b",
messages=[{"role":"user","content":"hello"}],
)
# Try Claude Haiku 4.5 — same client, same key
client.chat.completions.create(
model="anthropic/claude-haiku-4.5",
messages=[{"role":"user","content":"hello"}],
)