GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
$0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.
$0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.
| Argument | Type | Description |
|---|---|---|
| model* | string | |
| engine | any | |
| concurrency | integer | |
| max_evidence | integer | |
| quantization | any | |
| context_length* | integer | |
| hardware_system* | string |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model",
"hardware_system",
"context_length"
],
"properties": {
"model": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"engine": {
"anyOf": [
{
"type": "string",
"maxLength": 120,
"minLength": 1
},
{
"type": "null"
}
]
},
"concurrency": {
"type": "integer",
"default": 1,
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"max_evidence": {
"type": "integer",
"default": 12,
"maximum": 50,
"minimum": 1
},
"quantization": {
"anyOf": [
{
"type": "string",
"maxLength": 120,
"minLength": 1
},
{
"type": "null"
}
]
},
"context_length": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"hardware_system": {
"type": "string",
"maxLength": 200,
"minLength": 1
}
},
"additionalProperties": false
}$0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.
| Argument | Type | Description |
|---|---|---|
| model* | string | |
| runtime* | string | |
| objective | string | |
| batch_size | integer | |
| concurrency | integer | |
| ubatch_size | integer | |
| quantization | any | |
| prompt_tokens* | integer | |
| engine_version | any | |
| evidence_policy | string | |
$0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats.
| Argument | Type | Description |
|---|---|---|
| model* | string | |
| engine | any | |
| batch_size | any | |
| concurrency | integer | |
| ubatch_size | any | |
| max_evidence | integer | |
| quantization | any | |
| prompt_tokens* | integer | |
| engine_version | any | |
| flash_attention | any | |
| hardware_system |
$0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported.
| Argument | Type | Description |
|---|---|---|
| mode | string | |
| model* | string | |
| engine | any | |
| objective | string | |
| tco_years | number | |
| batch_size | any | |
| concurrency | integer | |
| cost_policy | string | |
| max_results | integer | |
| ubatch_size | any | |
| quantization | any |
$0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 5,
"maximum": 10,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 160,
"minLength": 1
}
},
"additionalProperties": false
}| flash_attention |
| any |
| hardware_system* | string |
| constraint_policy | string |
| maximum_vram_bytes | integer |
| maximum_power_watts | number |
| candidate_kv_formats | any |
| decode_context_depth | integer |
| minimum_decode_tok_s | number |
| minimum_prefill_tok_s | number |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"runtime",
"model",
"hardware_system",
"prompt_tokens"
],
"properties": {
"model": {
"type": "string",
"maxLength": 240,
"minLength": 1
},
"runtime": {
"enum": [
"vllm",
"llama.cpp"
],
"type": "string"
},
"objective": {
"enum": [
"balanced",
"maximize_decode",
"maximize_prefill",
"minimize_vram",
"minimize_power",
"minimize_capex",
"minimize_tco",
"maximize_decode_per_dollar",
"maximize_prefill_per_dollar"
],
"type": "string",
"default": "balanced"
},
"batch_size": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"concurrency": {
"type": "integer",
"default": 1,
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"ubatch_size": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"quantization": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"prompt_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"engine_version": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"evidence_policy": {
"enum": [
"verified_only",
"include_public",
"all"
],
"type": "string",
"default": "include_public"
},
"flash_attention": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
]
},
"hardware_system": {
"type": "string",
"maxLength": 240,
"minLength": 1
},
"constraint_policy": {
"enum": [
"point_estimate",
"conservative"
],
"type": "string",
"default": "point_estimate"
},
"maximum_vram_bytes": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"maximum_power_watts": {
"type": "number",
"exclusiveMinimum": 0
},
"candidate_kv_formats": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"maxItems": 20
},
{
"type": "null"
}
]
},
"decode_context_depth": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0
},
"minimum_decode_tok_s": {
"type": "number",
"exclusiveMinimum": 0
},
"minimum_prefill_tok_s": {
"type": "number",
"exclusiveMinimum": 0
}
},
"additionalProperties": false
}| string |
| kv_cache_type_k | any |
| kv_cache_type_v | any |
| requested_metrics | array |
| decode_context_depth | any |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model",
"hardware_system",
"prompt_tokens"
],
"properties": {
"model": {
"type": "string",
"maxLength": 240,
"minLength": 1
},
"engine": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"batch_size": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"concurrency": {
"type": "integer",
"default": 1,
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"ubatch_size": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"max_evidence": {
"type": "integer",
"default": 12,
"maximum": 50,
"minimum": 1
},
"quantization": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"prompt_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"engine_version": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"flash_attention": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
]
},
"hardware_system": {
"type": "string",
"maxLength": 240,
"minLength": 1
},
"kv_cache_type_k": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"kv_cache_type_v": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"requested_metrics": {
"type": "array",
"items": {
"enum": [
"prefill_tok_s",
"decode_tok_s",
"peak_vram_bytes",
"avg_power_watts"
],
"type": "string"
},
"default": [
"prefill_tok_s",
"decode_tok_s",
"peak_vram_bytes",
"avg_power_watts"
],
"maxItems": 4,
"minItems": 1
},
"decode_context_depth": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0
},
{
"type": "null"
}
]
}
},
"additionalProperties": false
}| budget_amount | any |
| prompt_tokens* | integer |
| engine_version | any |
| ownership_mode | string |
| quality_policy | string |
| budget_currency | string |
| evidence_policy | string |
| flash_attention | any |
| hardware_system | any |
| workload_profile | any |
| constraint_policy | string |
| maximum_tco_amount | any |
| maximum_vram_bytes | any |
| quality_thresholds | any |
| maximum_power_watts | any |
| candidate_kv_formats | any |
| decode_context_depth | any |
| minimum_decode_tok_s | any |
| recommendation_scope | string |
| manual_hardware_costs | any |
| minimum_prefill_tok_s | any |
| materiality_tiebreaker | string |
| quality_policy_version | string |
| quality_evidence_policy | string |
| economic_materiality_pct | number |
| electricity_rate_per_kwh | number |
| workload_profile_version | any |
| utilization_days_per_year | number |
| utilization_hours_per_day | number |
| economic_materiality_amount | number |
| allow_manual_market_override | boolean |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model",
"prompt_tokens"
],
"properties": {
"mode": {
"enum": [
"configuration",
"hardware_experimental"
],
"type": "string",
"default": "configuration"
},
"model": {
"type": "string",
"maxLength": 240,
"minLength": 1
},
"engine": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"objective": {
"enum": [
"balanced",
"maximize_decode",
"maximize_prefill",
"minimize_vram",
"minimize_power",
"minimize_capex",
"minimize_tco",
"maximize_decode_per_dollar",
"maximize_prefill_per_dollar"
],
"type": "string",
"default": "balanced"
},
"tco_years": {
"type": "number",
"default": 3,
"maximum": 20,
"exclusiveMinimum": 0
},
"batch_size": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"concurrency": {
"type": "integer",
"default": 1,
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"cost_policy": {
"enum": [
"latest_official",
"latest_any",
"manual_only",
"market_preferred",
"market_only",
"market_override_only"
],
"type": "string",
"default": "latest_official"
},
"max_results": {
"type": "integer",
"default": 5,
"maximum": 5,
"minimum": 1
},
"ubatch_size": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"quantization": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"budget_amount": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "null"
}
]
},
"prompt_tokens": {
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
"engine_version": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"ownership_mode": {
"enum": [
"purchase",
"owned"
],
"type": "string",
"default": "purchase"
},
"quality_policy": {
"enum": [
"prefer",
"require",
"ignore"
],
"type": "string",
"default": "prefer"
},
"budget_currency": {
"type": "string",
"pattern": "^[A-Za-z]{3}$"
},
"evidence_policy": {
"enum": [
"verified_only",
"include_public",
"all"
],
"type": "string",
"default": "include_public"
},
"flash_attention": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
]
},
"hardware_system": {
"anyOf": [
{
"type": "string",
"maxLength": 240,
"minLength": 1
},
{
"type": "null"
}
]
},
"workload_profile": {
"anyOf": [
{
"type": "string",
"maxLength": 120,
"minLength": 1
},
{
"type": "null"
}
]
},
"constraint_policy": {
"enum": [
"point_estimate",
"conservative"
],
"type": "string",
"default": "point_estimate"
},
"maximum_tco_amount": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "null"
}
]
},
"maximum_vram_bytes": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"quality_thresholds": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"required": [
"dimension",
"unit",
"direction",
"value"
],
"properties": {
"unit": {
"type": "string",
"maxLength": 80,
"minLength": 1
},
"value": {
"type": "number"
},
"dimension": {
"type": "string",
"maxLength": 120,
"minLength": 1
},
"direction": {
"enum": [
"higher_is_better",
"lower_is_better"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 30
},
{
"type": "null"
}
]
},
"maximum_power_watts": {
"anyOf": [
{
"type": "number",
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"candidate_kv_formats": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string",
"maxLength": 120,
"minLength": 1
},
"maxItems": 20
},
{
"type": "null"
}
]
},
"decode_context_depth": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0
},
{
"type": "null"
}
]
},
"minimum_decode_tok_s": {
"anyOf": [
{
"type": "number",
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"recommendation_scope": {
"enum": [
"full",
"performance_only"
],
"type": "string",
"default": "full"
},
"manual_hardware_costs": {
"anyOf": [
{
"type": "object",
"propertyNames": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"additionalProperties": {
"type": "number",
"minimum": 0
}
},
{
"type": "null"
}
]
},
"minimum_prefill_tok_s": {
"anyOf": [
{
"type": "number",
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"materiality_tiebreaker": {
"enum": [
"balanced",
"maximize_decode",
"maximize_prefill",
"minimize_vram",
"minimize_power"
],
"type": "string",
"default": "minimize_power"
},
"quality_policy_version": {
"type": "string",
"default": "planner-quality-policy-v2",
"maxLength": 120,
"minLength": 1
},
"quality_evidence_policy": {
"enum": [
"allow_calibrated_estimates",
"allow_cross_model_estimates",
"measured_only"
],
"type": "string",
"default": "allow_calibrated_estimates"
},
"economic_materiality_pct": {
"type": "number",
"default": 2,
"maximum": 100,
"minimum": 0
},
"electricity_rate_per_kwh": {
"type": "number",
"default": 0.18,
"minimum": 0
},
"workload_profile_version": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "null"
}
]
},
"utilization_days_per_year": {
"type": "number",
"default": 365,
"maximum": 366,
"minimum": 0
},
"utilization_hours_per_day": {
"type": "number",
"default": 8,
"maximum": 24,
"minimum": 0
},
"economic_materiality_amount": {
"type": "number",
"default": 25,
"minimum": 0
},
"allow_manual_market_override": {
"type": "boolean",
"default": false
}
},
"additionalProperties": false
}