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.
| Grok 4.7 xai/grok-4.7 | Claude Haiku 5.5 anthropic/claude-haiku-5.5 | |
|---|---|---|
| Provider | xAI | Anthropic |
| Family | Grok 4 | Claude 4 |
| Modality | text | text |
| Context window | 500,000 tok | 1,000,000 tok |
| Max output | 32,768 tok | 128,000 tok |
| Released | 2026-09-22 | 2026-10-12 |
| Input price | $2.00 /1M | $0.100 /1M |
| Output price | $6.00 /1M | $0.500 /1M |
| Cache read | — | — |
| Tools | — | yes |
| Streaming | yes | yes |
| Vision | yes | yes |
| JSON mode | — | yes |
| Reasoning | — | — |
| Prompt caching | — | — |
xAI's Grok 4.7, a frontier reasoning model for coding, agentic tasks, and knowledge work. Accepts text and image inputs, and supports function calling, structured outputs, and configurable reasoning effort (low, medium, high, xhigh).
Claude Haiku 5.5 is a fast, cost-efficient model for high-volume, latency-sensitive tasks such as classification, extraction, routing, and subagent work.
# 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 Grok 4.7
client.chat.completions.create(
model="xai/grok-4.7",
messages=[{"role":"user","content":"hello"}],
)
# Try Claude Haiku 5.5 — same client, same key
client.chat.completions.create(
model="anthropic/claude-haiku-5.5",
messages=[{"role":"user","content":"hello"}],
)