Last refreshed 2026-10-09. Next refresh: weekly.
Why use Apex on Vercel AI Gateway?
Vercel AI Gateway offers Apex with pay-as-you-go pricing at $0.50/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Apex across 2 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport AI_GATEWAY_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],callstack/apexRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="callstack/apex",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "callstack/apex", not the LLMReference slug "callstack-apex".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Apex Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Callstack Apex API | $0.50 | $3.00 |
| Vercel AI Gateway | $0.50 | $3.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.50 |
| Output tokens | $3.00 |
Capabilities
About Apex
Apex is Callstack's agentic coding model for mobile and web development, generally available since 1 October 2026. It is a Qwen-based model that Callstack post-trained on React and React Native source code, widely used open-source React Native libraries and its own engineering documentation, so it is strongest at React Native, React and Next.js work: building features, debugging, code review, tests, upgrades and migrations, including to the New Architecture. It has a 262,144-token context window and plugs into Claude Code, Cursor, Codex and other tools through OpenAI- and Anthropic-compatible endpoints.