curl https://app.exnai.com/v1/modelsfrom openai import OpenAI
client = OpenAI(base_url="https://app.exnai.com/v1")Tip
Use our regional edge endpoints to achieve sub-50ms TTFT.
ff
Engineering1 min read
Article Title Preview
Tariqul Islam
Platform Engineer
25 Sept 2026Updated 2 Oct 2026
Models mentioned
Was this page helpful?
Still stuck? Open a support ticket
Use the coding models you already know, through one API
One key for OpenAI- and Anthropic-compatible tools. Pay in BDT or USD, and keep the coding agent you already use.
Create an accountMore in Engineering
Engineering7 min read
What a 1M-token context window changes for coding agents (and what it doesn't)
Million-token context lets an agent hold a whole repository and a long session. It doesn't make each turn cheaper or faster, and some providers raise the price above 200K, 272K or 512K tokens. Here's the arithmetic.
Tokens Team · 3 Oct 2026
Engineering9 min read
Prompt caching explained: how cache-hit pricing works across providers
How prompt caching is priced at DeepSeek, Anthropic, OpenAI, Moonshot, Alibaba and others, why coding agents benefit more than chat apps, what quietly breaks cache hits, and what you can and can't control through a gateway.
Tokens Team · 3 Oct 2026
Engineering9 min read
OpenAI vs Anthropic API Format: Chat Completions, Responses and Messages Compared
Three request formats, one job. Where the system prompt goes, how tool calls and their results are shaped, what the streaming events look like, why output limits and usage fields differ, how a gateway serves the same model in more than one format, and which coding agents speak which.
Tokens Team · 3 Oct 2026