mirror of
https://github.com/Heretek-AI/Token-Max.git
synced 2026-10-12 02:03:18 +00:00
John Smith
ac6df68d3a
- Enforce token-first fit invariant in WorkflowCalculator: require caps.basis >= requiredTokens and poolDrain.overageCost === 0 to qualify as fits - Re-anchor Google Antigravity Ultra 20x Gemini Flash to empirical 3.0B tokens/mo (down from 18.7B virtual dollar division) and Claude Sonnet to 180M tokens/mo matching DevForth ~00/7d telemetry - Cap Ollama Cloud Team tier at 4,500M tokens/mo (10-stream physical socket bandwidth ceiling) and Kimi Code Vivace K2.7 Code at 1,200M tokens/mo - Unclamp negative savings in WorkflowCalculator to transparently show when plans cost more than direct API - Integrate rate-limit lockout wage exposure into Breakeven Verdict headline to penalize severe lockout risks - Add parsePlanCacheAssumption and symmetric cache-rate scaling to computeApplesToApples - Fix internal credit burn rate in calculatePoolDrain when models have dedicated perModelTokenBudgets - Add unit tests verifying 115 passing tests across 8 suites
213 lines
6.2 KiB
JSON
213 lines
6.2 KiB
JSON
{
|
|
"id": "ollama-cloud",
|
|
"name": "Ollama Cloud",
|
|
"category": "api-provider",
|
|
"url": "https://ollama.com",
|
|
"lastVerified": "2026-09-19",
|
|
"tiers": [
|
|
{
|
|
"name": "Free",
|
|
"monthlyPrice": 0,
|
|
"limits": {
|
|
"cloudModels": "Community hosted models",
|
|
"concurrency": "1 stream",
|
|
"localUse": "Unlimited local execution"
|
|
},
|
|
"models": [
|
|
"Llama 3.2",
|
|
"Qwen 2.5 Coder 7B"
|
|
],
|
|
"estimatedTokenBudget": {
|
|
"description": "Free cloud tier (~1M tokens/mo)",
|
|
"estimatedMillionTokens": 1,
|
|
"assumptions": "Free community rate limits",
|
|
"estimateMeta": {
|
|
"sourceUrl": "https://ollama.com",
|
|
"sourceType": "research",
|
|
"confidence": "low",
|
|
"verifiedAt": "2026-09-19"
|
|
}
|
|
},
|
|
"notes": "Free tier for running local and small cloud models"
|
|
},
|
|
{
|
|
"name": "Pro",
|
|
"monthlyPrice": 20,
|
|
"annualPrice": 200,
|
|
"limits": {
|
|
"credits": "$60 cloud compute credits/mo",
|
|
"concurrency": "3 concurrent streams",
|
|
"peakSurcharge": "12:00-18:00 UTC peak rates, Mon-Fri"
|
|
},
|
|
"models": [
|
|
"DeepSeek V4.1 Flash",
|
|
"DeepSeek V4-Pro",
|
|
"MiniMax M3",
|
|
"GLM-5",
|
|
"Kimi K3"
|
|
],
|
|
"perModelTokenBudgets": {
|
|
"deepseek v4.1 flash": {
|
|
"estimatedMillionTokens": 1229.27,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"deepseek v4-pro": {
|
|
"estimatedMillionTokens": 181.62,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"minimax m3": {
|
|
"estimatedMillionTokens": 302.7,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"glm-5": {
|
|
"estimatedMillionTokens": 161.02,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"kimi k3": {
|
|
"estimatedMillionTokens": 31.4,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
}
|
|
},
|
|
"estimatedTokenBudget": {
|
|
"description": "$60 compute credits (~60M tokens/mo)",
|
|
"estimatedMillionTokens": 60,
|
|
"assumptions": "$60 monthly cloud credit pool",
|
|
"estimateMeta": {
|
|
"sourceUrl": "https://ollama.com",
|
|
"sourceType": "research",
|
|
"confidence": "low",
|
|
"verifiedAt": "2026-09-19"
|
|
}
|
|
},
|
|
"notes": "Pro: $60 credits/mo, 3 concurrent. 3x compute value."
|
|
},
|
|
{
|
|
"name": "Max",
|
|
"monthlyPrice": 100,
|
|
"limits": {
|
|
"credits": "$300 cloud compute credits/mo",
|
|
"concurrency": "10 concurrent streams",
|
|
"peakSurcharge": "Standard rates"
|
|
},
|
|
"models": [
|
|
"DeepSeek V4.1 Flash",
|
|
"DeepSeek V4-Pro",
|
|
"MiniMax M3",
|
|
"GLM-5",
|
|
"Kimi K3"
|
|
],
|
|
"perModelTokenBudgets": {
|
|
"deepseek v4.1 flash": {
|
|
"estimatedMillionTokens": 6146.34,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"deepseek v4-pro": {
|
|
"estimatedMillionTokens": 908.11,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"minimax m3": {
|
|
"estimatedMillionTokens": 1513.51,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"glm-5": {
|
|
"estimatedMillionTokens": 805.11,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"kimi k3": {
|
|
"estimatedMillionTokens": 157.01,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
}
|
|
},
|
|
"estimatedTokenBudget": {
|
|
"description": "$300 compute credits (~300M tokens/mo)",
|
|
"estimatedMillionTokens": 300,
|
|
"assumptions": "$300 monthly cloud credit pool",
|
|
"estimateMeta": {
|
|
"sourceUrl": "https://ollama.com",
|
|
"sourceType": "research",
|
|
"confidence": "low",
|
|
"verifiedAt": "2026-09-19"
|
|
}
|
|
},
|
|
"notes": "Max: $300, 10 concurrent. Priority routing."
|
|
},
|
|
{
|
|
"name": "Team",
|
|
"monthlyPrice": 500,
|
|
"limits": {
|
|
"credits": "$1,000 cloud compute credits/mo",
|
|
"concurrency": "10 concurrent streams",
|
|
"privateEndpoints": "Dedicated pods"
|
|
},
|
|
"models": [
|
|
"DeepSeek V4.1 Flash",
|
|
"DeepSeek V4-Pro",
|
|
"MiniMax M3",
|
|
"GLM-5",
|
|
"Kimi K3"
|
|
],
|
|
"perModelTokenBudgets": {
|
|
"deepseek v4.1 flash": {
|
|
"estimatedMillionTokens": 4500.0,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"deepseek v4-pro": {
|
|
"estimatedMillionTokens": 3027.03,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"minimax m3": {
|
|
"estimatedMillionTokens": 4500.0,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"glm-5": {
|
|
"estimatedMillionTokens": 2683.71,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
},
|
|
"kimi k3": {
|
|
"estimatedMillionTokens": 523.36,
|
|
"basis": "list-price-credit",
|
|
"confidence": "medium"
|
|
}
|
|
},
|
|
"estimatedTokenBudget": {
|
|
"description": "$1,000 compute credits (~1B tokens/mo)",
|
|
"estimatedMillionTokens": 1000,
|
|
"assumptions": "$1,000 monthly credit pool (official Team plan)",
|
|
"estimateMeta": {
|
|
"sourceUrl": "https://ollama.com",
|
|
"sourceType": "research",
|
|
"confidence": "low",
|
|
"verifiedAt": "2026-09-19"
|
|
}
|
|
},
|
|
"notes": "Dedicated private pods for software development teams"
|
|
}
|
|
],
|
|
"gotchas": [
|
|
"Unused included usage does not roll over",
|
|
"Peak pricing applies 12:00-18:00 UTC Monday-Friday",
|
|
"One account per person: multiple Ollama accounts are not permitted"
|
|
],
|
|
"tosHighlights": [
|
|
"No training on cloud inference data",
|
|
"Complete open-source local runtime"
|
|
],
|
|
"dataTraining": "No",
|
|
"ipIndemnity": false,
|
|
"stackingPolicy": "prohibited",
|
|
"stackingPolicyNote": "Pricing FAQ: \"Can I have multiple Ollama accounts? No. Ollama is one account per person.\""
|
|
} |