GPT-5.6 Sol
Observed throughTokscale Model Report
GPT-5.6 Sol model details and observed coding usage from Tokscale.
Reality Snapshot
Observed tokens
5.3T+861.7%
over 30 days
Estimated tracked spend
$4.3M
Invoices may differ
Active developers
652+149
this month
30-day momentum
+861.7%
Compared with the prior 30-day window
Most-used client
Codex CLI87%
of observed tokens
Observed Usage
Tokens observedDaily active developers
How developers use it
Usage by coding client
Sharevs 30 daysSenpi
<1%0%Token composition
Share of observed tokens
96%cache read
Cache read5.1T96%
Input216.9B4.1%
Output15.2B<1%
Reasoning5.1B<1%
Cache-heavy workloadMost observed tokens reuse cached context across requests.
Observed Variants
default
gpt-5.6-sol5.3T$4.2M$0.7999.12%fast
gpt-5.6-sol-fast26.5B$23.5K$0.880.5%router via codex
router_client:codex/gpt-5.6-sol8.9B$0$0.000.17%high
gpt-5.6-sol-high7.4B$6.3K$0.850.14%xhigh
gpt-5.6-sol-xhigh1.2B$1.9K$1.560.02%via kiro
kiro/gpt-5.6-sol842.8M$4.3K$5.050.02%via cx, high
cx/gpt-5.6-sol-high680.1M$2K$2.870.01%max
gpt-5.6-sol-max607.7M$910.1$1.490.01%via cx
cx/gpt-5.6-sol389.1M$367.6$0.940.01%router via claude
router_client:claude/gpt-5.6-sol379.2M$0$0.000.01%via codex
codex/gpt-5.6-sol20.7M$19.8$0.950%via pecut
pecut/gpt-5.6-sol12.5M$35.6$2.850%router via unknown
router_client:unknown/gpt-5.6-sol9.4M$0$0.000%via openai
openai/gpt-5.6-sol6M$5$0.820%via aerolink
aerolink/gpt-5.6-sol255.4K$0.9$3.700%via cx, xhigh
cx/gpt-5.6-sol-xhigh222.2K$0.5$2.460%via 93170c28-07f9-4728-a359-099834792cc4
93170c28-07f9-4728-a359-099834792cc4/gpt-5.6-sol198.4K$0.5$2.360%via azure-openai
azure-openai/gpt-5.6-sol112.1K$0.6$5.000%via azure
azure/gpt-5.6-sol7.4K$0$5.140%Token Economics
Estimated spend profile
Codex CLI$3.6M83.78%
Gajae-Code$158K3.71%
Pi$176K4.13%
OpenCode$119K2.79%
Hermes Agent$94.7K2.22%
Claude Code$85.6K2.01%
Senpi$30.5K0.72%
OpenClaw$14.9K0.35%
Observed cost signals
Estimated spend per 1M tracked tokens$0.80
Cache-read share95.6%
Estimated cache savingsNot available
Typical workloadcontext-heavy
Estimated tracked spend calculated from Tokscale model and provider pricing data. Actual invoices may differ.
Model Momentum
+861.7%30-day growthRank: Observed model
Compared with the prior non-overlapping window
Fastest-growing client: Codex CLI
Official Model Details
ProviderOpenAI
Tokscale Insight
GPT-5.6 Sol recorded 5.3T coding tokens across 652 developers during the latest 30-day Tokscale window.
Observed confidenceHigh






