cheapoS THE CHEAPSKATE CLUB
COMPUTE OBSERVATORY · TELEMETRY MACRO-DECK

The cheapoS
Engine Room.

Aggregate intelligence across installations. See which models builders deploy, how autonomous agents divide cognitive labor, and where zero-dollar compute replaces commercial retail API spend.

TOTAL COMMUNITY COMPUTE154,413,174Verified machine sync receipts
MODELS BENCHMARKED52across major compute gateways
AUTONOMOUS PERSONAS4Worker, Reviewer, Planner, Coordinator
COMMERCIAL BILLS AVOIDED~$292.92Maximum leverage across providers
COGNITIVE DIVISION OF LABOR

Autonomous Workshop Roles

How autonomous cheapoS agent swarms divide their cognitive workloads when executing software tasks.

🧑‍💻89% share

Worker

The execution workhorse: editing files, running terminal checks, and tool calling.

129.28M129,277,373 tokens
🛡️7.1% share

Reviewer

The quality gatekeeper: auditing diffs, inspecting tests, and enforcing safety.

10.35M10,347,224 tokens
🗺️3.9% share

Planner

The architect: breaking complex requests into actionable autonomous milestones.

5.63M5,628,809 tokens
🧭0.1% share

Coordinator

The dispatcher: routing tasks between subagents and orchestrating checkpoints.

80.9K80,947 tokens
Cognitive Ratio Benchmark: For every 10 tokens a Worker generates executing code, Reviewers audit ~12.5 tokens, and Planners structure ~0.7 tokens. Autonomous quality assurance accounts for ~7.1% of overall compute.
THE MODEL POWER RANKINGS

Community Model Index

Which models do software builders actually deploy when maximizing compute efficiency? Live telemetry aggregated across installations.

#Model NameProviderCompute ShareTotal TokensBills Eliminated
1
dots-studio/dots-3-note-previewopenrouter/dots-studio/dots-3-note-preview:free
OpenRouter
24.4%
37.68M~$113.04
2
gemini-3.1-flash-lite
Google
22%
34.01M~$10.20
3
openai/gpt-oss-120b
Other
10.6%
16.37M~$81.85
4
groq/qwen/qwen3.6-27b
Groq
10.4%
16.05M~$16.05
5
antigravity/gemini-3.1-flash-lite
Google
7.8%
12.09M~$3.63
6
dots-studio/dots-3-note-previewdots-studio/dots-3-note-preview:free
OpenRouter
4.3%
6.65M~$19.94
7
antigravity/gemini-3.7-flash-medium
Google
3.3%
5.05M~$1.52
8
qwen/qwen3.8-27b
Other
2.5%
3.79M~$3.79
9
cohere/north-mini-codeopenrouter/cohere/north-mini-code:free
OpenRouter
1.8%
2.78M~$0.84
10
qwen/qwen3.6-27b
Other
1.4%
2.23M~$2.23
11
cohere/north-mini-codecohere/north-mini-code:free
OpenRouter
1.4%
2.20M~$0.66
12
nvidia/nemotron-3-super-120b-a12bnvidia/nemotron-3-super-120b-a12b:free
OpenRouter
1.3%
1.98M~$9.88
13
groq/qwen/qwen3.8-27b
Groq
1.2%
1.78M~$1.78
14
openai/gpt-oss-20b
Other
1.1%
1.71M~$5.14
15
antigravity/gemini-3.7-flash-low
Google
1.1%
1.70M~$0.51
16
antigravity/gemini-3.1-pro-low
Google
1.1%
1.64M~$0.49
17
nvidia/google/gemma-4-31b-it
Google
0.8%
1.18M~$3.55
18
groq/openai/gpt-oss-120b
Groq
0.7%
1.01M~$5.07
19
antigravity/claude-sonnet-4-6-high
Other
0.6%
939.9K~$2.82
20
nvidia/nemotron-3-super-120b-a12b
Other
0.3%
534.6K~$2.67
21
inclusionai/ling-3.0-flash-finopenrouter/inclusionai/ling-3.0-flash-fin:free
OpenRouter
0.3%
501.7K~$0.50
22
nvidia/nemotron-3-super-120b-a12bopenrouter/nvidia/nemotron-3-super-120b-a12b:free
OpenRouter
0.2%
366.5K~$1.83
23
inclusionai/ling-3.0-flash-fininclusionai/ling-3.0-flash-fin:free
OpenRouter
0.2%
334.5K~$0.33
24
gemini-3.7-flash-low
Google
0.2%
300.2K~$0.09
25
ling-3.0-flash-fin-free
Other
0.2%
276.2K~$0.28
26
nvidia/nvidia/nemotron-3-super-120b-a12b
Other
0.2%
272.1K~$1.36
27
gemma4:31b
Local
0.2%
267.8K~$0.80
28
groq/openai/gpt-oss-20b
Groq
0.1%
222.8K~$0.67
29
google/gemma-4-31b-it
Google
0.1%
209.2K~$0.63
30
claude-sonnet-4-6-high
Other
0.1%
119.9K~$0.36
31
poolside/laguna-xs-2.1poolside/laguna-xs-2.1:free
OpenRouter
0%
61.1K~$0.18
32
poolside/laguna-xs-2.1openrouter/poolside/laguna-xs-2.1:free
OpenRouter
0%
30.5K~$0.09
33
qwen2.5-coder:7b
Other
0%
25.4K~$0.08
34
auto/codingauto/coding:free
OpenRouter
0%
19.6K~$0.06
35
antigravity/gemini-3-flash
Google
0%
13.1K~$0.00
36
antigravity/gemini-3.7-flash-high
Google
0%
8.9K~$0.00
37
google/gemma-4-26b-a4b-itopenrouter/google/gemma-4-26b-a4b-it:free
Google
0%
888~$0.00
38
auto/best-free
Other
0%
879~$0.00
39
mistralai/mistral-nemotron
Other
0%
698~$0.00
40
google/gemma-4-26b-a4b-itgoogle/gemma-4-26b-a4b-it:free
Google
0%
555~$0.00
41
google/gemma-4-31b-itopenrouter/google/gemma-4-31b-it:free
Google
0%
555~$0.00
42
nvidia/nemotron-3-nano-omni-30b-a3b-reasoningnvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
OpenRouter
0%
552~$0.00
43
nvidia/nemotron-3.5-lightningnvidia/nemotron-3.5-lightning:free
OpenRouter
0%
406~$0.00
44
nvidia/nemotron-3-ultra-550b-a55bnvidia/nemotron-3-ultra-550b-a55b:free
OpenRouter
0%
393~$0.00
45
nex-agi/nex-n2.5-pronex-agi/nex-n2.5-pro:free
OpenRouter
0%
362~$0.00
46
nex-agi/nex-n2.5-mininex-agi/nex-n2.5-mini:free
OpenRouter
0%
352~$0.00
47
inclusionai/ling-3.0-flash-santeinclusionai/ling-3.0-flash-sante:free
OpenRouter
0%
330~$0.00
48
inclusionai/ling-3.0-flash-vlinclusionai/ling-3.0-flash-vl:free
OpenRouter
0%
321~$0.00
49
google/gemma-4-31b-itgoogle/gemma-4-31b-it:free
Google
0%
222~$0.00
50
liquid/lfm-2.5-2.6bliquid/lfm-2.5-2.6b:free
OpenRouter
0%
203~$0.00
51
poolside/laguna-s-2.1openrouter/poolside/laguna-s-2.1:free
OpenRouter
0%
200~$0.00
52
openai/gpt-oss-safeguard-20b
Other
0%
195~$0.00
INFRASTRUCTURE PROVENANCE

Where Community Compute Originates

4 compute tiers working together: public free gateways, included developer quotas, local hardware, and pay-as-you-go frontier keys.

98.8%

Public Free Gateways

Free developer endpoints from Google AI Studio, Groq Cloud, OpenRouter free tiers, and Cerebras.

152,518,282 tokens
1.0%

Included Account Quotas

Pre-bundled developer environment quotas and zero-dollar editor allowances.

1,601,645 tokens
0.2%

Local Hardware

On-device inference powered by Apple Silicon unified memory (MLX), local Ollama, and CPU execution.

293,247 tokens
0.0%

Paid Pay-As-You-Go

Targeted out-of-pocket tokens reserved for high-stakes frontier reasoning or heavy benchmarks.

0 tokens

Want your model featured here?

Sponsor next month's spotlight engine on the observatory.

Sponsor prospectus ↗