modelprices.xyz

54 listed endpoints · free reliability snapshot (may be up to 24h old)

Base

B 54
endpoints
54
avg trust score
74.4
ecosystem avg 51.7
avg 30-day uptime
94.8%
ecosystem avg 53.6%
avg latency (EU)
444 ms
measured from a single EU vantage point; includes network round-trip distance to the endpoint
price band
$0.003–$0.03
USDC per call
networks
1
At a glance

modelprices.xyz operates 54 listed x402 endpoints across 1 network. 54 of them carry a computed trust score, averaging 74.4 of 100 (above the ecosystem average of 51.7). Average 30-day uptime across the measured endpoints is 94.8% (above the ecosystem average of 53.6%). Advertised prices range from $0.003 to $0.03 USDC per call. Best-scored endpoint: /llm/cheapest (grade B, 78.4).

Top endpoints by trust score

All endpoints

endpointgradeuptime 30dconf.price
/llm/price-changesB 77.5
92.8%
1.00$0.03
/llm/limitsB 78.1
94.0%
1.00$0.02
/llm/pricesB 77.7
93.2%
1.00$0.02
/llm/cheapestB 78.4
93.8%
1.00$0.01
/llm/price/%7Bmodel%7DB 77.1
100.0%
1.00$0.003
/llm/limit/%7Bmodel%7DB 77.0
100.0%
1.00$0.003
/llm/limit/:modelB 77.0
100.0%
1.00$0.003
/llm/price/:modelB 77.1
100.0%
1.00$0.003
/ai-model-pricingB 78.1
92.8%
1.00$0.02
/claude-pricingB 73.9
94.7%
1.00$0.01
/gpt-pricingB 73.8
94.7%
1.00$0.01
/gemini-pricingB 73.6
94.3%
1.00$0.01
/llama-pricingB 73.6
94.3%
1.00$0.01
/deepseek-pricingB 73.6
94.3%
1.00$0.01
/mistral-pricingB 73.7
94.3%
1.00$0.01
/grok-pricingB 73.7
94.3%
1.00$0.01
/qwen-pricingB 73.9
94.7%
1.00$0.01
/kimi-pricingB 73.6
94.3%
1.00$0.01
/glm-pricingB 73.8
94.7%
1.00$0.01
/minimax-pricingB 73.9
94.7%
1.00$0.01
/gemma-pricingB 73.7
94.3%
1.00$0.01
/command-pricingB 73.6
94.3%
1.00$0.01
/phi-pricingB 73.8
94.7%
1.00$0.01
/jamba-pricingB 73.7
94.3%
1.00$0.01
/llm/prices/openaiB 73.5
93.8%
1.00$0.01
/llm/prices/anthropicB 73.8
94.7%
1.00$0.01
/llm/prices/googleB 73.9
94.7%
1.00$0.01
/llm/prices/vertex-aiB 73.6
94.3%
1.00$0.01
/llm/prices/bedrockB 73.6
94.3%
1.00$0.01
/llm/prices/azureB 73.6
94.3%
1.00$0.01
/llm/prices/fireworksB 73.7
94.3%
1.00$0.01
/llm/prices/togetherB 73.8
94.7%
1.00$0.01
/llm/prices/deepinfraB 73.8
94.7%
1.00$0.01
/llm/prices/openrouterB 73.7
94.3%
1.00$0.01
/llm/prices/novitaB 73.6
94.3%
1.00$0.01
/llm/prices/replicateB 73.9
94.7%
1.00$0.01
/llm/prices/xaiB 73.6
94.3%
1.00$0.01
/llm/prices/mistralB 73.8
94.7%
1.00$0.01
/llm/prices/cloudflareB 73.8
94.7%
1.00$0.01
/llm/prices/databricksB 73.6
94.3%
1.00$0.01
/llm/prices/nebiusB 73.8
94.7%
1.00$0.01
/llm/prices/watsonxB 73.8
94.7%
1.00$0.01
/llm/prices/oracleB 73.9
94.7%
1.00$0.01
/llm/prices/vercelB 73.9
94.8%
1.00$0.01
/llm/prices/sambanovaB 73.5
93.8%
1.00$0.01
/llm/prices/snowflakeB 73.6
94.3%
1.00$0.01
/llm/cheapest/overallB 73.7
94.3%
1.00$0.01
/llm/cheapest/visionB 73.7
94.3%
1.00$0.01
/llm/cheapest/reasoningB 73.8
94.7%
1.00$0.01
/llm/cheapest/function-callingB 73.7
94.3%
1.00$0.01
/llm/cheapest/long-contextB 73.6
94.3%
1.00$0.01
/llm/cheapest/million-token-contextB 73.7
94.3%
1.00$0.01
/llm/cheapest/128k-contextB 73.9
94.7%
1.00$0.01
/llm/context-windowsB 73.7
94.3%
1.00$0.01

Scores use reduced-density sampling; live probe, full 30-min density and 90-day history via the paid API. Provider-supplied names and descriptions are unverified claims; the grades are our independent measurement.