NexoToken · Grok 4.6Authenticity, speed and price analysis
(seconds)
coding session
availability
Comparison summary
Grok 4.6 on NexoToken: availability over the last 24 hours is 93.3%, ranking 3 of 5 relays with data (median 93.3%); time to first token is 12.86 s, ranking 4 of 4 (median 6.17 s).
Authenticity checks (model consistency and dilution) are not live yet; once they are, this section will compare the relay with the official API.
Authenticity
Model consistency
Output distribution for the same requests on this relay and on the official API · higher is better
Speed
Measured by time to first token (seconds) and output speed (tokens / second)
Time to first token
Seconds until the first token · lower is better
Price
Cost per coding session
Grok 4.6 · 2M input and 40k output tokens (¥) · split by token type · lower is better
Prices: cache hit, input and output
¥ / 1M tokens
Cache
Coding requests repeat much of their context, so the cache hit rate largely decides what you actually pay. Drag the hit rate and the costs and ranking below are reweighted with cache prices.
Cache-weighted session cost
Grok 4.6 · of 2M input tokens, the hit share is billed at the cache price and the rest at the input price, plus 40k output (¥) · lower is better
Stability
Availability
Request success rate, last 24 hours · higher is better
Status of each model, last 24 hours
One cell per hour · green ok, yellow delayed, red failed
| Model | Group | Availability | Last 24 hours | First token | Samples |
|---|---|---|---|---|---|
| GPT 6 Sol | GPT外接（不降智） | 100.0% | 10.13 s | 29 | |
| GPT 6 Astra | GPT外接（不降智） | 100.0% | 8.02 s | 30 | |
| GPT 5.6 Terra | GPT·Codex Pro稳定分组 | 100.0% | 12.37 s | 30 | |
| Grok 4.7 | Grok-heavy分组 | 96.7% | 10.99 s | 30 | |
| Kimi K3 | 国产优选 | 96.7% | 4.34 s | 30 | |
| Claude Sonnet 5 | Claude Pro Max | 96.7% | 6.55 s | 30 | |
| DeepSeek V4 Pro | 国产优选 | 96.7% | 9.57 s | 30 | |
| Grok 4.5 | Grok-heavy分组 | 96.7% | 18.80 s | 30 | |
| Grok 4.6 | Grok-heavy分组 | 93.3% | 12.86 s | 30 | |
| GPT 6.1 Sol | gpt 不降智 | 90.0% | 6.70 s | 30 | |
| GPT 5.6 Sol | GPT外接（不降智） | 90.0% | 6.39 s | 30 | |
| DeepSeek V4 Flash | 国产优选 | 90.0% | 13.78 s | 30 | |
| GLM 5.3 | 国产优选 | 90.0% | 7.27 s | 30 | |
| DeepSeek V4.1 Flash | 国产优选 | 89.7% | 6.03 s | 29 | |
| GLM 5.3 Flash | 国产优选 | 80.0% | 9.14 s | 30 | |
| Qwen 3.8 Max | 国产优选 | — | None yet | — | — |
| Claude Opus 5 | Anthropic 方案 2 | — | None yet | — | — |
| Claude Fable 5 | Anthropic 方案 2 | — | None yet | — | — |
| Gemini 3.8 Flash | Gemini·CLI特价版 | — | None yet | — | — |
| Gemini 3.1 Pro Preview | Gemini·CLI特价版 | — | None yet | — | — |
| Gemini 3.7 Flash | Gemini·CLI特价版 | — | None yet | — | — |
| Gemini 3.5 Flash | Gemini·CLI特价版 | — | None yet | — | — |
| Gemini 3.6 Flash | Gemini·CLI特价版 | — | None yet | — | — |
Service details
FAQ
How much does Grok 4.6 cost on NexoToken?
No public price yet.
How does the cache hit rate affect price?
NexoToken has not published a cache price for this route, so cache hits are billed at the input price.Measured hit rates will replace this assumption once available.
Which models does NexoToken support?
Folkbench currently lists 23: GPT 6 Astra, GPT 6 Sol, GPT 6.1 Sol, DeepSeek V4.1 Flash, Grok 4.7, Claude Sonnet 5, GPT 5.6 Sol, Claude Fable 5, Claude Opus 5, GPT 5.6 Terra, Kimi K3, DeepSeek V4 Pro, Grok 4.6, Gemini 3.8 Flash, Grok 4.5, Qwen 3.8 Max, DeepSeek V4 Flash, Gemini 3.1 Pro Preview, GLM 5.3, GLM 5.3 Flash, Gemini 3.7 Flash, Gemini 3.5 Flash, Gemini 3.6 Flash.
What does the data security level mean?
Folkbench rates relays from 0 to 4 based on public policies and verifiable evidence; NexoToken is currently level 0. The check covers leaks in responses and error messages only, and does not prove data retention or training policies.
How often is this data updated?
Availability and time to first token use a 24-hour window, and this page syncs live data every 15 minutes.