• DevPass
    • Lounge
    • Models
    • Docs
    • Pricing
    • DevPass
    • Lounge
    • Pricing
    • Docs
    • Models
      • AI Gateway
      • DevPass
      • Lounge
      • Observability
      • Enterprise
      • Blog
      • Changelog
      • Integrations
      • Reliability
      • Features
      • Guardrails
      • Providers
      • Partners
      • Rankings
      • Apps
      • Models
      • Model Timeline
      • Compare
      • Token Cost Calculator
      • Savings Audit
      • State of LLM Usage
      • Referral Program
      • MCP Server
      • CLI
      • Agents
      • AI SDK Provider
      • Agent Skills
      • Templates
      • Guides
    Log InGet Started

    Open Source Models

    Open-weight models — Llama, DeepSeek, Qwen, GLM, Kimi, GPT-OSS, Gemma, and more — served through one API

    Compare
    Use Case
    Lounge Plan
    Capabilities
    Provider
    Status
    Input Price ($/M tokens)
    Output Price ($/M tokens)
    Context Size (tokens)
    73/324
    Models
    33/57
    Providers
    37
    Vision Models (filtered)
    66
    Tool-enabled (filtered)
    0
    Free Models (filtered)
    289 provider offers · page 1 of 6
    Features
    Alibaba Cloud
    glm-5.3-prime
    $2.80$8.80$0.56
    Alibaba Cloud(cn-beijing)
    glm-5.3-prime
    $2.20$7.70$0.55
    Alibaba Cloud(singapore)
    glm-5.3-prime
    $2.80$8.80$0.56
    Fireworks AI
    muse-spark-open
    $1.25$4.25$0.15
    Together AI
    muse-spark-open
    $1.25$4.25$0.15
    Xiaomi
    mimo-v2.6-pro-ultraspeedPlus: needs a Lounge Plus or Pro membership
    $4.35$8.70$0.04
    Meta
    muse-ember-1.0
    $0.10$0.50$0.00
    Consensus Protocol
    deepseek-v4.1-flash-uncensored
    $0.18$0.65$0.01
    Alibaba Cloud
    deepseek-v4-flash-0731
    $0.44$1.32$0.04
    Alibaba Cloud(ap-tokyo)
    deepseek-v4-flash-0731
    $0.44$1.32$0.04
    Alibaba Cloud(cn-beijing)
    deepseek-v4-flash-0731
    $0.42$1.27$0.04
    Alibaba Cloud(eu-frankfurt)
    deepseek-v4-flash-0731
    $0.42$1.27$0.04
    Alibaba Cloud(singapore)
    deepseek-v4-flash-0731
    $0.44$1.32$0.04
    Alibaba Cloud(us-virginia)
    deepseek-v4-flash-0731
    $0.42$1.27$0.04
    Baidu
    deepseek-v4-flash-0731
    $0.44$1.32$0.01
    ByteDance
    deepseek-v4-flash-0731
    $0.44$1.32$0.01
    Canopy Wave
    deepseek-v4-flash-0731
    $0.44$0.37
    -15% off
    $1.32$1.12
    -15% off
    $0.04$0.03
    -15% off
    Cloudflare
    deepseek-v4-flash-0731
    $0.44$1.32$0.01
    DeepInfra
    deepseek-v4-flash-0731
    $0.08$0.18$0.02
    FlexAI
    deepseek-v4-flash-0731
    $0.13$0.13
    -3% off
    $0.26$0.25
    -3% off
    $0.02$0.02
    -3% off
    NovitaAI
    deepseek-v4-flash-0731
    $0.14$0.28$0.03
    Tencent Cloud
    deepseek-v4-flash-0731
    $0.15$0.60$0.00
    Tencent Cloud
    glm-5.3-flashx
    $0.37$1.25$0.07
    Z AI
    glm-5.3-flashx
    $0.37$1.25$0.07
    Tencent Cloud
    kimi-k2.8-preview
    $1.00$4.00$0.25
    Inference.net
    deepseek-v4.1-flash-cyber
    $0.30$1.00$0.01
    Canopy Wave
    minimax-m3.1-flash
    $0.15$0.60$0.01
    Fireworks AI
    minimax-m3.1-flash
    $0.15$0.60$0.01
    FlexAI
    minimax-m3.1-flash
    $0.15$0.15
    -3% off
    $0.60$0.58
    -3% off
    $0.01$0.01
    -3% off
    Inference.net
    minimax-m3.1-flash
    $0.10$0.50$0.01
    MiniMax
    minimax-m3.1-flash
    $0.15$0.60$0.01
    Nebius AI
    minimax-m3.1-flash
    $0.15$0.60$0.01
    NovitaAI
    minimax-m3.1-flash
    $0.15$0.60$0.01
    Together AI
    minimax-m3.1-flash
    $0.15$0.60$0.01
    Alibaba Cloud
    deepseek-v4.1-flash-1017
    $0.30$1.20$0.01
    Alibaba Cloud(ap-tokyo)
    deepseek-v4.1-flash-1017
    $0.28$1.13$0.01
    Alibaba Cloud(cn-beijing)
    deepseek-v4.1-flash-1017
    $0.28$1.13$0.01
    Alibaba Cloud(eu-frankfurt)
    deepseek-v4.1-flash-1017
    $0.28$1.13$0.01
    Alibaba Cloud(singapore)
    deepseek-v4.1-flash-1017
    $0.30$1.20$0.01
    Alibaba Cloud(us-virginia)
    deepseek-v4.1-flash-1017
    $0.28$1.13$0.01
    Baidu
    deepseek-v4.1-flash-1017
    $0.28$1.13$0.01
    Canopy Wave
    deepseek-v4.1-flash-1017
    $0.30$0.15
    -50% off
    $1.20$0.60
    -50% off
    $0.01$0.00
    -50% off
    Cloudflare
    deepseek-v4.1-flash-1017
    $0.30$1.20$0.01
    DeepInfra
    deepseek-v4.1-flash-1017
    $0.20$0.60$0.01
    DeepSeek
    deepseek-v4.1-flash-1017
    $0.15$0.60$0.00
    Entrim
    deepseek-v4.1-flash-1017
    $0.20$0.14
    -31% off
    $0.80$0.55
    -31% off
    $0.01$0.00
    -31% off
    Fireworks AI
    deepseek-v4.1-flash-1017
    $0.30$1.20$0.01
    FlexAI
    deepseek-v4.1-flash-1017
    $0.08$0.08
    -3% off
    $0.60$0.59
    -3% off
    $0.01$0.01
    -3% off
    Inference.net
    deepseek-v4.1-flash-1017
    $0.30$1.00$0.01
    Mistral AI
    deepseek-v4.1-flash-1017
    $0.30$1.20$0.01
    Page 1 of 6

    Open-weight models have closed most of the gap with proprietary frontiers: DeepSeek V4, Qwen3.7, GLM-5, Kimi K2, and MiniMax M3 sit near the top of real-world leaderboards, joined by OpenAI's GPT-OSS and Google's Gemma releases. Their weights are public — but running a 200B+ parameter model yourself means serious GPU infrastructure.

    This page lists open-weight models served by hosted providers, so you get the openness — inspectable weights, no lock-in, the option to self-host later — with API convenience. LLM Gateway itself is open source (AGPLv3) and self-hostable, so the whole stack can run on your terms.

    Frequently asked questions

    What is the best open source LLM?

    DeepSeek V4, Qwen3.7, GLM-5.2, Kimi K2.6, and MiniMax M3 are the current leaders, each within striking distance of proprietary frontier models. For smaller, hardware-friendly options, GPT-OSS 20B, Gemma 4, and Qwen3.5 9B are the standouts.

    What does 'open source' mean for LLMs?

    Usually 'open weight': the trained weights are downloadable, but licenses vary — some are Apache 2.0 or MIT, others (like the Llama license) carry usage restrictions, and training data is rarely published. Check the license of a specific model before building on it.

    Should I self-host or use an API?

    Self-hosting pays off with steady high volume, strict data-residency needs, or fine-tuned weights. For everything else, per-token APIs are cheaper than idle GPUs. A middle path: develop against hosted open models and keep self-hosting as an exit option, since the weights are public.

    Are open models cheaper than proprietary ones?

    Dramatically, per token. Competition among hosts drives prices down — DeepSeek V4 Flash and Qwen3 Coder 30B cost 10–50x less than frontier proprietary models. The list above shows every provider's price for each model.

    Newsletter

    Stay ahead of the curve

    Insights on LLM routing, new model launches and cost optimization, sent to your inbox.

    • New models and providers, rounded up
    • Tips to cut LLM costs
    • Major product launches

    No spam. Unsubscribe anytime.

    System status
    AICPA SOC for Service Organizations badgeSOC 2 Type II
    compliant

    Product

    • Features
    • AI Gateway
    • Observability
    • Models
    • Providers
    • Provider status
    • Rankings
    • State of LLM Usage
    • Add Provider
    • Partners
    • Lounge
    • Changelog
    • DevPass
    • Compare Models
    • Enterprise

    Resources

    • Legal Overview
    • Apps
    • Templates
    • Agents
    • MCP Server
    • Use Cases
    • Blog
    • Documentation
    • Developer resources
    • Integrations
    • Guides
    • Brand Assets
    • Token Cost Calculator
    • Copilot Cost Calculator
    • Savings Audit
    • Status & Pricing Badges
    • Referral Program
    • GitHub
    • Discord
    • Twitter
    • About
    • Contact Us

    Compliance

    • Trust Center
    • Security Portal
    • Terms
    • Privacy Policy
    • Provider Information
    • Sub-processors
    • SOC 2 Type II
    • Status

    Compare

    • All Comparisons
    • GitHub Copilot
    • OpenRouter
    • LiteLLM
    • Portkey
    • AWS Bedrock
    • Microsoft Foundry
    • Vercel AI Gateway
    • OpenRouter Alternatives
    • LiteLLM Alternatives
    • Migration Guides

    Models

    • Text Generation
    • Text to Image
    • Image to Image
    • Video Generation
    • Embeddings
    • Decisions
    • Vision
    • Reasoning
    • Tool Calling
    • Web Search
    • Discounted
    • Best for Roleplay
    • Best for Coding
    • Best for Creative Writing
    • Best for Translation
    • Best for Math
    • Best for Cyber Security
    • Best for Reverse Engineering
    • Long Context
    • Cheapest
    • Open Source

    Providers

    • fal
    • OpenAI
    • Anthropic
    • Google AI Studio
    • Google Vertex AI
    • Vertex AI (OpenAI-compatible)
    • Vertex AI (Anthropic)
    • Groq
    • Cerebras
    • xAI
    • DeepSeek
    • Alibaba Cloud
    • Runpod
    • NovitaAI
    • AtlasCloud
    • AWS Bedrock
    • AWS Mantle
    • Azure
    • Azure Anthropic
    • Z AI
    • Moonshot AI
    • Baidu
    • Perplexity
    • Nebius AI
    • Mistral AI
    • CanopyWave
    • Inference.net
    • Together AI
    • ByteDance
    • MiniMax
    • Meta
    • Meta Contributor
    • Sakana AI
    • Xiaomi
    • DeepInfra
    • ElevenLabs
    • Fireworks AI
    • Tencent Cloud
    • TypeSafe AI
    • Cloudflare

    © 2026 LLM Gateway. All rights reserved.

    1.7k