GPT-5.5 xhigh
-
Cost -Tokens -
AI API Gateway for Developers,more easily to use Codex/Claude
One Gateway for Codex/Claude and more tools
CodeToken Cloud is an OpenAI-compatible AI API gateway for developers building with OpenAI, Codex workflows, Claude integrations, agents, automation scripts, and multi-model AI applications.
JUST ONE ENDPOINT
API URLhttps://api.codetoken.cloud
Copy YOUR_API_KEY to login Codex or Claude Code and more"
Pricing
Pay as You Go Pricing
Recharge credits and use them across OpenAI, Codex, Claude, and multi-model AI workflows. No monthly subscription required.
| Model | Official Input /1M tokens | Cached Input /1M tokens | Official Output /1M tokens | Avg Official /1M tokens | CodeToken /1M tokens |
|---|---|---|---|---|---|
| GPT-5.5 | $5.00 | $0.50 | $30.00 | $6.76 | $1.01 |
| Claude Opus 4.8 | $15.00 | $1.50 | $75.00 | $15.82 | $2.37 |
Assumptions
Input: 80%
Output: 20%
Cache Hit: 90%
Multiplier: 0.15x
Avg Official = (Input * % + Output * %) | CodeToken = Avg Official * Multiplier (adjusted for cache)
Model Comparison
See how much more token capacity you get with CodeToken.
GPT-5.5
Official API1.48M
CodeToken9.86M
Savings85%
Claude Opus
Official API0.63M
CodeToken4.22M
Savings85%
Recharge Amount: $10.00
CodeToken
9.86M
Official API1.48M
6.66x More Capacity
Save about 85%
* Based on 80% input, 20% output, 90% input cache hit rate, and CodeToken pricing at 0.15x official pricing.
Radar
AI Coding Radar
Compare coding model quality, pass rate, latency, token usage, and cache efficiency in one operational view.
LAST UPDATED · -
GPT-5.5 high
-
Cost -Tokens -
GPT-5.5 medium
-
Cost -Tokens -
GPT-5.4 xhigh
-
Cost -Tokens -
GPT-5.4 high
-
Cost -Tokens -
| Model | IQ | Pass | Cost (/ 1K tokens) | Time (s) | Tokens (/ req) | Cache Hit (%) |
|---|---|---|---|---|---|---|
| GPT-5.5 high | - | - | - | - | - | - |
| GPT-5.5 medium | - | - | - | - | - | - |
| GPT-5.5 xhigh | - | - | - | - | - | - |
| GPT-5.4 high | - | - | - | - | - | - |
| GPT-5.4 xhigh | - | - | - | - | - | - |
Status
Live Status
Real-time gateway load, usage, and performance snapshot
Server Load
Current CPU, memory, and system load reported by the gateway server.
-
-
Requests
Total requests processed by the gateway since monitoring began.
-
-
tokens
Total tokens processed today across gateway requests.
-
-
Success Rate
Percentage of requests completed without an error.
-
-
Avg QPS
Average number of requests handled per second during the live data window.
-
-
Avg TPS
Average number of tokens processed per second during the live data window.
-
-
TTFT
Average time to first token — the delay before a response begins.
-
-
Upstream
Overall upstream service health score based on recent gateway checks.
-
-
-