Models

Every model. One coworker.

Your coworker runs on 230+ models from every major lab. 70+ of them have open weights. You choose which ones your team may use.

Hire your coworkerSee how it picks

In the catalogue today

237 models · 27 labs

  • OpenAI60 models
    • GPT-4.11M
    • GPT-4.1 (Fast)1M
    • GPT-4.1 mini1M
    • GPT-4.1 mini (Fast)1M
    • GPT-4.1 nano (Fast)1M
    • GPT-4o128K
    • GPT-4o (Fast)128K
    • GPT-4o mini128K
    • GPT-4o mini (Fast)128K
    • GPT-5400K
    • GPT-5 (Fast)400K
    • GPT-5-Codex400K
    • GPT-5 Mini400K
    • GPT-5 mini (Fast)400K
    • GPT-5 Nano400K
    • GPT-5 Pro400K
    • GPT-5.1400K
    • GPT-5.1-Codex400K
    • GPT 5.1 Codex Max400K
    • GPT-5.1 Codex mini400K
    • GPT 5.1 Thinking400K
    • GPT 5.1 Thinking (Fast)400K
    • GPT-5.2400K
    • GPT 5.2 (Fast)400K
    • GPT-5.2-Codex400K
    • GPT-5.2 Pro400K
    • GPT-5.3 Codex400K
    • GPT 5.3 Codex (Fast)400K
    • GPT-5.3 Codex Spark128K
    • GPT-5.41M
    • GPT 5.4 (Fast)1M
    • GPT-5.4 mini400K
    • GPT 5.4 Mini (Fast)400K
    • GPT-5.4 nano400K
    • GPT-5.4 Pro1M
    • GPT-5.51M
    • GPT 5.5 (Fast)1M
    • GPT-5.5 Pro1M
    • GPT-5.61M
    • GPT-5.6 Luna1M
    • GPT 5.6 Luna (Fast)1M
    • GPT-5.6 Sol1M
    • GPT 5.6 Sol (Fast)1M
    • GPT-5.6 Terra1M
    • GPT 5.6 Terra (Fast)1M
    • GPT-6 Astra1M
    • GPT-6 Astra (Fast)1M
    • GPT-6 Luna1M
    • GPT-6 Luna (Fast)1M
    • GPT-6 Sol1M
    • GPT-6 Sol (Fast)1M
    • GPT OSS 20B131K
    • GPT OSS 120B131K
    • gpt-oss-safeguard-20b128K
    • GPT OSS Safeguard 120B128K
    • GPT-Realtime-2.1128K
    • o3200K
    • o3 (Fast)200K
    • o3-pro200K
    • o4-mini (Fast)200K
  • Alibaba30 models
    • Qwen 3 Coder 30B A3B Instruct262K
    • Qwen 3 Max Thinking256K
    • Qwen 3.5 Flash1M
    • Qwen 3.5 Plus1M
    • Qwen 3.6 27B256K
    • Qwen 3.6 Max Preview240K
    • Qwen 3.6 Plus1M
    • Qwen 3.7 Flash991K
    • Qwen 3.7 Max991K
    • Qwen 3.7 Plus1M
    • Qwen 3.8 Flash991K
    • Qwen 3.8 Max262K
    • Qwen 3.8 Omni Flash1M
    • Qwen 3.32B128K
    • Qwen3-14B40K
    • Qwen3-30B-A3B40K
    • Qwen3 235B A22B Instruct 2507262K
    • Qwen3 235B A22B Thinking 2507131K
    • Qwen3 Coder 480B A35B Instruct262K
    • Qwen3 Coder Next256K
    • Qwen3 Coder Plus1M
    • Qwen3 Max262K
    • Qwen3 Max Preview262K
    • Qwen3 Next 80B A3B Instruct262K
    • Qwen3 Next 80B A3B Thinking262K
    • Qwen3 VL Instruct131K
    • Qwen3 VL Thinking131K
    • Qwen3.8 2.4T A95B262K
    • Qwen3.8 27B1M
    • Qwen3.8 Max 0902991K
  • Anthropic18 models
    • Claude Fable 51M
    • Claude Fable 5.11M
    • Claude Haiku 3200K
    • Claude Haiku 4.5200K
    • Claude Opus 4200K
    • Claude Opus 4.5200K
    • Claude Opus 4.61M
    • Claude Opus 4.71M
    • Claude Opus 4.81M
    • Claude Opus 4.8 (Fast)1M
    • Claude Opus 51M
    • Claude Opus 5 (Fast)1M
    • Claude Opus 5.51M
    • Claude Opus 5.5 (Fast)1M
    • Claude Sonnet 41M
    • Claude Sonnet 4.51M
    • Claude Sonnet 4.61M
    • Claude Sonnet 51M
  • Z.ai17 models
    • GLM 4.5128K
    • GLM 4.5 Air128K
    • GLM 4.5V66K
    • GLM 4.6200K
    • GLM 4.7200K
    • GLM 4.7 Flash200K
    • GLM 4.7 FlashX200K
    • GLM-5202K
    • GLM 5 Turbo202K
    • GLM 5.1202K
    • GLM 5.21M
    • GLM 5.2 Fast1M
    • GLM 5.31M
    • GLM 5.3 Fast1M
    • GLM 5.3 Flash1M
    • GLM 5.3 FlashX1M
    • GLM 5V Turbo200K
  • Google13 models
    • Gemini 2.5 Flash1M
    • Gemini 2.5 Flash Lite1M
    • Gemini 2.5 Pro1M
    • Gemini 3 Flash1M
    • Gemini 3.1 Flash Lite1M
    • Gemini 3.1 Pro Preview1M
    • Gemini 3.5 Flash1M
    • Gemini 3.5 Flash Lite1M
    • Gemini 3.6 Flash1M
    • Gemini 3.7 Flash1M
    • Gemini 3.8 Flash1M
    • Gemma 4 26B A4B IT262K
    • Gemma 4 31B IT262K
  • SpaceX AI13 models
    • Grok 4.1 Fast Non-Reasoning1M
    • Grok 4.1 Fast Reasoning1M
    • Grok 4.31M
    • Grok 4.5500K
    • Grok 4.6500K
    • Grok 4.7500K
    • Grok 4.20 Beta Non-Reasoning2M
    • Grok 4.20 Beta Reasoning2M
    • Grok 4.20 Multi-Agent2M
    • Grok 4.20 Multi Agent Beta2M
    • Grok 4.20 Non-Reasoning2M
    • Grok 4.20 Reasoning2M
    • Grok Build 0.1256K
  • Meta11 models
    • Llama 3.1 8B Instruct128K
    • Llama 3.1 70B Instruct128K
    • Llama-3.3-70B-Instruct128K
    • Llama-4-Maverick-17B-128E-Instruct-FP8128K
    • Llama-4-Scout-17B-16E-Instruct-FP8128K
    • Muse Glimmer 30B131K
    • Muse Spark 1.11M
    • Muse Spark 1.21M
    • Muse Spark 1.2 Contributor1M
    • Muse Spark 1.31M
    • Muse Spark 1.3 Contributor1M
  • DeepSeek9 models
    • DeepSeek-V3.1163K
    • DeepSeek V3.1 Terminus131K
    • DeepSeek V3.2 Thinking128K
    • DeepSeek V4 Flash1M
    • DeepSeek V4 Flash 07311M
    • DeepSeek V4 Flash Vision Exp1M
    • DeepSeek V4 Pro1M
    • DeepSeek V4 Pro 08131M
    • DeepSeek V4.1 Flash1M
  • MiniMax8 models
    • MiniMax M2205K
    • MiniMax M2.1204K
    • MiniMax M2.1 Lightning204K
    • MiniMax M2.5204K
    • MiniMax M2.5 High Speed204K
    • Minimax M2.7204K
    • MiniMax M2.7 High Speed204K
    • MiniMax M3512K
  • Moonshot AI8 models
    • Kimi K2 Instruct131K
    • Kimi K2 Thinking216K
    • Kimi K2.5256K
    • Kimi K2.6262K
    • Kimi K2.7 Code256K
    • Kimi K2.7 Code High Speed262K
    • Kimi K31M
    • Kimi K3 Fast1M
  • InclusionAI7 models
    • Ling 3.0 Flash256K
    • Ling 3.0 Flash Fin256K
    • Ling 3.0 Flash Fin (Free)256K
    • Ling 3.0 Flash Sante256K
    • Ling 3.0 Flash Sante (Free)256K
    • Ling 3.0 Flash VL256K
    • Ling 3.0 Flash VL (Free)256K
  • Mistral6 models
    • Codestral (latest)256K
    • Ministral 3B (latest)128K
    • Ministral 8B (latest)128K
    • Mistral Medium Latest262K
    • Mistral Nemo60K
    • Mistral Small (latest)262K
  • Xiaomi5 models
    • MiMo M2.51M
    • MiMo V2.5 Pro1M
    • MiMo V2.6 Flash1M
    • MiMo V2.6 Pro1M
    • MiMo V2.6 Pro UltraSpeed1M
  • NVIDIA4 models
    • Nemotron 3 Ultra1M
    • Nemotron 3.5 Lightning 30B262K
    • Nvidia Nemotron Nano 9B V2131K
    • Nvidia Nemotron Nano 12B V2 VL131K
  • Sakana AI4 models
    • Fugu Max1M
    • Fugu Ultra1M
    • Fugu Ultra v21M
    • Sakana Namazu256K
  • Amazon3 models
    • Nova Lite300K
    • Nova Micro128K
    • Nova Pro300K
  • ByteDance3 models
    • Seed 1.6256K
    • Seed 1.8256K
    • Seed 2.1 Turbo262K
  • Inception3 models
    • Mercury 2128K
    • Mercury 2.5260K
    • Mercury Coder Small Beta32K
  • Perplexity2 models
    • Sonar127K
    • Sonar Pro200K
  • Poolside2 models
    • Laguna S 2.11M
    • Laguna S 2.1 Free256K
  • Quiver AI2 models
    • Arrow 2131K
    • Arrow 2 Telos131K
  • StepFun2 models
    • Step 3.7 Flash256K
    • StepFun 3.5 Flash262K
  • Tencent2 models
    • Hy3262K
    • Tencent Hy4 Preview1M
  • Thinking Machines2 models
    • Inkling256K
    • Inkling Small1M
  • Arcee AI1 model
    • Trinity Large Thinking262K
  • Cohere1 model
    • Command A256K
  • Mixedbread1 model
    • Toast 1131K

From the models.dev catalogue, counted on 23 September 2026. Every one of them calls tools. 199 think step by step. 162 read images.

One job, one engine

A different model for each job

The email tagger does not need the model that writes your board pack. Stop paying top rate for easy work.

The jobThe engine you setCost

  1. Tag 400 support emailsHigh volume, one right answerMinistral 8B (latest)Mistral
  2. Draft each replyYour tone, your refund rulesClaude Sonnet 5Anthropic
  3. Read the 90-page contractOne long document, one passGemini 3 Pro PreviewGoogle
  4. Write the board packHard, and the board reads itClaude Opus 5Anthropic

Four jobs, four engines, one coworker. Change any row and nothing else moves.Cheapest to dearest

See the controls

Controls

Choose the model for the job

Let Alfera recommend a model, or choose one for the conversation.

  1. Choose a model

    Compare the available models in the picker.

  2. Use a recommendation

    Let Alfera choose a model for the work.

  3. Switch when you need

    Choose another model from the conversation composer.

  4. Bring your own keys

    Use your provider contract and the model bill goes to you, under your own agreement.

Model policyWhole workspace

Default

  • Claude Sonnet 5Anthropicdefault

Approved

  • GPT-5.6OpenAI
  • Gemini 3 Pro PreviewGoogle
  • Llama 3.1 70B InstructMeta
  • Ministral 8B (latest)Mistral

Blocked

  • Every other modelblocked

Provider keys

Anthropicsk-ant-••••••••4f21Everything elseBilled through Alfera

Open weights

Open models, no lock-in

70+ of the models we ship have open weights. You can run them cheaper, and you can leave any lab that changes its terms.

  • Llama
  • Qwen
  • DeepSeek
  • GLM
  • Kimi
  • Mistral
  • Gemma
  • gpt-oss

  • The job is repetitive

    Send it to an open model. The same work lands, and the bill is smaller.

  • You swap the engine

    Your memory, your permissions and your connected tools stay where they were.

  • A lab rewrites its terms

    You approve a different model and carry on. Nobody has to migrate anything.

Any models, including open-source

Start on the default. Move to any model your team approves. Your memory and permissions stay put.

Hire your coworkerBook a demo