OpenModels
ModelsProvidersSkillsMCPCompareCalculatorInsights
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
  • Calculator
  • Provider status

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.

Registry freshness is outside the 7-day policy. Values are shown with their source dates.
Filters and result options

Filters

Advanced filters

Global model explorer

224 matching models

Contexttokens

Canonical maximum token capacity. Capacity is not quality.

20 of 224 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 5.5flagship
proprietary · unknown
Anthropicus1M$4.00 / $20.00Anthropic1M9/22/2026Added to registry
2
GPT-6 Astraflagship
proprietary · unknown
Openaius1.1M$10.00 / $50.00OpenAI1.1M9/3/2026Added to registry
3
GPT-6.1 Solflagship
proprietary · unknown
Openaius1.1M$2.00 / $10.00OpenAI1.1M9/29/2026Added to registry
4
Gemini 4 Argonflagship
proprietary · unknown
Googleus1M$2.00 / $10.00Google AI Studio1M10/1/2026Added to registry
5
GPT-6.1 Terrarecent
proprietary · unknown
Openaius1.1M$1.00 / $5.00OpenAI1.1M10/26/2026Added to registry
6
Kimi K3.1 Prorecent
unknown · unknown
Kimicn1M$2.00 / $10.00Moonshot AI1M10/23/2026Added to registry
7
WeVisOne-VL 2Brecent
open weights · unknown
Wevisonecn262KNot priced262K10/22/2026Added to registry
8
WeVisOne-VL 4Brecent
open weights · unknown
Wevisonecn262KNot priced262K10/22/2026Added to registry
9
Qwen3 Coder 30B A3B Instructrecent
open weights · unknown
Qwen3cn1M$0.0675 / $0.27Synap by Linkrra1M10/21/2026Added to registry
10
Recursive Flintrecent
open weights · unknown
FlintCountry unknown262KNot priced262K10/21/2026Added to registry
11
MiniMax M3.1 Flashrecent
proprietary · unknown
Minimaxcn1M$0.15 / $0.60MiniMax1M10/19/2026Added to registry
12
Mercury 3recent
proprietary · unknown
Mercuryus1M$0.10 / $0.35OpenRouter1M10/19/2026Added to registry
13
Muse Spark Openrecent
unknown · unknown
Museus1M$1.25 / $4.25OpenRouter1M10/15/2026Added to registry
14
Nemotron 3.5 Super VLrecent
unknown · unknown
Nvidiaus1M$0.15 / $0.50OpenRouter1M10/15/2026Added to registry
15
Nemotron 3.5 Bolt 74B-A9B 24GBrecent
unknown · unknown
Nvidiaus262KNot priced262K10/15/2026Added to registry
16
Muse Wonderrecent
proprietary · unknown
Museus1M$4.00 / $20.00Meta AI1M10/12/2026Added to registry
17
Muse Wonder Fullrecent
proprietary · unknown
Museus1MNot priced1M10/12/2026Added to registry
18
Claude Haiku 5.5recent
proprietary · unknown
Anthropicus1M$0.10 / $0.50Anthropic1M10/7/2026Added to registry
19
Mistral Large 4recent
unknown · unknown
Mistralfr1M$0.68 / $2.09Mistral AI1M10/6/2026Added to registry
20
Kolibri 1recent
open weights · unknown
Kolibride1MNot priced1M10/2/2026Added to registry
Page 1 of 12

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.

Select models with current provider pricing to estimate cost.

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 →