OpenModels
ModelsProvidersSkillsMCPCompareInsights
Docs
OpenModels

Open-source registry for LLM models, inference providers, and AI agent skills. Community-maintained.

[email protected]

Registry

  • Models
  • Providers
  • Skills
  • MCP
  • Collections
  • Compare

Resources

  • Documentation
  • API Reference
  • CLI
  • Contribute
  • Contributing

Community

  • LinkedIn
  • GitHub

© 2026 OpenModels. Open-source, community-maintained.

Privacy PolicyAll systems operational
OpenModelsOpenModels

OpenModels comparison

Choose the right AI model for your workload

Filter the full registry, compare provider-specific prices and capacity, then estimate cost with your own assumptions. Missing performance data stays missing.

Filters and result options

Filters

Advanced filters

Global model explorer

133 matching models

Contexttokens

Canonical maximum token capacity. Capacity is not quality.

20 of 133 models have a comparable value for this metric

Model shortlist

Flagship and recently added models

Editorial flagship labels and registry dates affect discovery order, never model scores.

Models with registry facts and provider-attributed pricing
#ModelDeveloper / countrySelected metricProvider price · in / outContextRegistry dateCompare
1
Claude Opus 5flagship
proprietary · unknown
Anthropicus300K$5.00 / $25.00Anthropic300K7/21/2026Added to registry
2
GPT-5.6 Solflagship
proprietary · unknown
Openaius1M$5.00 / $30.00OpenAI1M7/9/2026Added to registry
3
Qwen 3.8 Maxflagship
proprietary · unknown
Qwen3cn1M$2.00 / $6.00Alibaba Model Studio1M8/3/2026Added to registry
4
Kimi K3flagship
unknown · unknown
Kimicn1M$3.00 / $15.00Moonshot AI1M7/15/2026Added to registry
5
Gemini 3.1 Proflagship
proprietary · unknown
Googleus2M$7.00 / $21.00Google AI Studio2M3/1/2026Added to registry
6
DeepSeek R1flagship
open weights · unknown
Deepseekcn131K$0.40 / $1.60Deep Infra131K1/20/2025Added to registry
7
Gemini 3.5 Flash-Literecent
proprietary · unknown
Googleus1M$0.30 / $2.50Google AI Studio1M7/21/2026Added to registry
8
Gemini 3.6 Flashrecent
proprietary · unknown
Googleus1M$1.50 / $7.50Google AI Studio1M7/21/2026Added to registry
9
Gemini 3.5 Flash Cyberrecent
proprietary · unknown
Googleus1MNot priced1M7/21/2026Added to registry
10
Motif 3 Betarecent
unknown · unknown
Motifkr262KNot priced262K7/21/2026Added to registry
11
Inklingrecent
unknown · unknown
Inklingus1M$1.87 / $4.68Tinker1M7/15/2026Added to registry
12
Gemini 3.5 Prorecent
proprietary · unknown
Googleus2M$8.00 / $24.00Google Cloud Vertex AI2M7/9/2026Added to registry
13
GPT-5.6 Lunarecent
proprietary · unknown
Openaius400K$0.20 / $1.20OpenAI400K7/9/2026Added to registry
14
GPT-5.6 Terrarecent
proprietary · unknown
Openaius1M$2.00 / $12.00OpenAI1M7/9/2026Added to registry
15
Muse Spark 1.1recent
proprietary · unknown
Museus512K$1.25 / $4.25Meta AI512K7/9/2026Added to registry
16
Grok 4.5recent
proprietary · unknown
XAIus500K$2.00 / $6.00OpenRouter500K7/8/2026Added to registry
17
Claude Sonnet 5recent
proprietary · unknown
Anthropicus1M$2.00 / $10.00Anthropic1M6/30/2026Added to registry
18
Sakana Fugurecent
proprietary · unknown
Sakanajp256K$2.00 / $12.00Sakana AI256K6/22/2026Added to registry
19
Sakana Fugu Ultrarecent
proprietary · unknown
Sakanajp256K$5.00 / $30.00Sakana AI256K6/22/2026Added to registry
20
GLM-5.2recent
open weights · unknown
Zhipu AIcn1M$0.60 / $2.00OpenRouter1M6/13/2026Added to registry
Page 1 of 7

Selected models

Side-by-side comparison

Compare capacity, deployment choice and published cost without synthetic quality scores.

Choose 2–4 models
Choose at least two models from the chart or shortlist.

Cost per task

Estimate your workload, not an abstract blend

Uses the named provider price and your token assumptions. Tool, image, audio and unentered reasoning-token charges are excluded.

Short multi-turn chat; no cache assumed.

Qwen 3.8 MaxAlibaba Model Studio
Per request
$0.00540
Per 1,000
$5.40
Monthly
$540.00

Data trust

What this version can—and cannot—claim

Available

Registry facts

Canonical metadata, capabilities, context, access classification, provider deployments and current published prices.

Not evaluated

Quality & benchmarks

No composite score is shown. Only versioned, sourced benchmark records will be admitted.

Not measured

Speed & latency

Legacy probes are excluded until provider, region, prompt, sample size and methodology are comparable.

Read methodology and data policy →