{
  "title": "Free Inference",
  "tagline": "Every provider that gives developers free API access to LLM inference \u2014 usable from a harness, agent, or CLI. Web-chat-only free tiers (ChatGPT, Claude.ai, Gemini app, deepseek.com, Grok, Copilot) are excluded on purpose.",
  "verified": "2026-08-12",
  "website": "https://freeinference.dev",
  "repo": "",
  "columns": [
    "Provider",
    "Free tier",
    "Free models",
    "RPM",
    "TPM",
    "RPD",
    "Day tokens",
    "Context",
    "Timeout",
    "Notes"
  ],
  "providers": [
    {
      "name": "OpenCode Zen",
      "url": "https://opencode.ai/docs/zen",
      "free_type": "Promo free (limited time)",
      "notes": "Free models are limited-time promos; some may use data for training. No credit card. OpenAI-compatible base URL opencode.ai/zen/v1. List free models: opencode models | grep -i free",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "Big Pickle",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "DeepSeek V4 Flash",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "MiMo-V2.5",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "Laguna S 2.1",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "Ling-3.0-tiny",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "LongCat-2.0",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "North Mini Code",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "Nemotron 3 Ultra",
          "cost": "$0 (promo)",
          "context": "256K - 1M",
          "rpm": "Not published",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "Not published",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "OpenRouter",
      "url": "https://openrouter.ai/models?max_price=0",
      "free_type": "Rate-limited free",
      "notes": "Gateway, not a model owner. Shared best-effort capacity, no SLA. BYOK program: 1M free routing requests/month with your own provider keys.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "cohere/north-mini-code:free",
          "cost": "$0",
          "context": "250K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "google/gemma-4-26b-a4b-it:free",
          "cost": "$0",
          "context": "256K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "google/gemma-4-31b-it:free",
          "cost": "$0",
          "context": "256K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "inclusionai/ling-3.0-tiny:free",
          "cost": "$0",
          "context": "256K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "liquid/lfm-2.5-2.6b:free",
          "cost": "$0",
          "context": "125K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-3-nano-30b-a3b:free",
          "cost": "$0",
          "context": "250K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
          "cost": "$0",
          "context": "250K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-3-super-120b-a12b:free",
          "cost": "$0",
          "context": "256K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-3-ultra-550b-a55b:free",
          "cost": "$0",
          "context": "1000000",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-3.5-content-safety:free",
          "cost": "$0",
          "context": "125K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-3.5-lightning:free",
          "cost": "$0",
          "context": "1000000",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-nano-12b-v2-vl:free",
          "cost": "$0",
          "context": "125K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "nvidia/nemotron-nano-9b-v2:free",
          "cost": "$0",
          "context": "125K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "openai/gpt-oss-20b:free",
          "cost": "$0",
          "context": "128K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "poolside/laguna-s-2.1:free",
          "cost": "$0",
          "context": "256K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "poolside/laguna-xs-2.1:free",
          "cost": "$0",
          "context": "256K",
          "rpm": "20",
          "tpm": "Provider-dependent",
          "rpd": "50 (below $10 credits) / 1,000 ($10+ credits)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Google AI Studio (Gemini API)",
      "url": "https://ai.google.dev/gemini-api/docs/rate-limits",
      "free_type": "Rate-limited free",
      "notes": "Free forever, no card, most generous major-provider tier. Live-verified against the v1beta API with an API key (2026-08-12) \u2014 model list and context windows are real; per-account quota varies by account age (see AI Studio rate-limit dashboard). Free-tier data may be used for training.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "gemini-2.5-flash",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-2.5-flash-lite",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-2.5-pro",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3-flash-preview",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3.1-flash-lite",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3.1-flash-lite-preview",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3.1-pro-preview",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3.1-pro-preview-customtools",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3.5-flash",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3.5-flash-lite",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-3.6-flash",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-flash-latest",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-flash-lite-latest",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-omni-flash-preview",
          "cost": "$0",
          "context": "128K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemini-pro-latest",
          "cost": "$0",
          "context": "1024K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemma-4-26b-a4b-it",
          "cost": "$0",
          "context": "256K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "gemma-4-31b-it",
          "cost": "$0",
          "context": "256K",
          "rpm": "Varies by account",
          "tpm": "Varies by account",
          "rpd": "Varies by account",
          "tpd": "Not published",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Groq",
      "url": "https://console.groq.com/docs/rate-limits",
      "free_type": "Rate-limited free",
      "notes": "LPU hardware, fastest time-to-first-token. Limits per API key per model; some models get half allowance. No credit card. Limits visible in x-ratelimit-* response headers.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "Llama 3.1 / 3.3",
          "cost": "$0",
          "context": "128K",
          "rpm": "30 (15 for some)",
          "tpm": "6K",
          "rpd": "14,400 (org-wide)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "Llama 4 Scout",
          "cost": "$0",
          "context": "128K",
          "rpm": "30 (15 for some)",
          "tpm": "6K",
          "rpd": "14,400 (org-wide)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "Qwen 3",
          "cost": "$0",
          "context": "128K",
          "rpm": "30 (15 for some)",
          "tpm": "6K",
          "rpd": "14,400 (org-wide)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "Kimi K2",
          "cost": "$0",
          "context": "128K",
          "rpm": "30 (15 for some)",
          "tpm": "6K",
          "rpd": "14,400 (org-wide)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "GPT-OSS 120B",
          "cost": "$0",
          "context": "128K",
          "rpm": "30 (15 for some)",
          "tpm": "6K",
          "rpd": "14,400 (org-wide)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "Gemma 2 9B",
          "cost": "$0",
          "context": "128K",
          "rpm": "30 (15 for some)",
          "tpm": "15K",
          "rpd": "14,400 (org-wide)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Cerebras",
      "url": "https://inference-docs.cerebras.ai/support/rate-limits",
      "free_type": "Rate-limited free (Free Trial)",
      "notes": "Wafer-scale hardware, 2,000+ tok/s. Free tier caps context at 8K (temporary). Per-model limits on a rotating shortlist. No credit card.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "gpt-oss-120b",
          "cost": "$0",
          "context": "8K cap on free tier",
          "rpm": "5",
          "tpm": "30K",
          "rpd": "Not published",
          "tpd": "1M tokens/day (per model)",
          "verified": "2026-08-12"
        },
        {
          "name": "zai-glm-4.7",
          "cost": "$0",
          "context": "8K cap on free tier",
          "rpm": "5",
          "tpm": "30K",
          "rpd": "Not published",
          "tpd": "1M tokens/day (per model)",
          "verified": "2026-08-12"
        },
        {
          "name": "gemma-4-31b",
          "cost": "$0",
          "context": "8K cap on free tier",
          "rpm": "5",
          "tpm": "30K",
          "rpd": "Not published",
          "tpd": "1M tokens/day (per model)",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Cloudflare Workers AI",
      "url": "https://developers.cloudflare.com/workers-ai/platform/limits",
      "free_type": "Rate-limited free",
      "notes": "Neurons are normalized GPU-compute units, shared pool across all models. Resets 00:00 UTC. Hard stop when pool exhausted, errors not overage. No credit card.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "~80 free models (Llama 3.x/4, Qwen, Gemma, DeepSeek-R1 distills, FLUX, Whisper, BGE embeddings)",
          "cost": "$0",
          "context": "8K-128K+ (model-dependent)",
          "rpm": "300 text gen (720-1,500 other tasks)",
          "tpm": "Model-dependent",
          "rpd": "Not published",
          "tpd": "10,000 neurons/day",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Hugging Face",
      "url": "https://huggingface.co/docs/inference-providers",
      "free_type": "Rate-limited free",
      "notes": "Two products: Serverless API (free, rate-limited) and Inference Providers gateway. Cold starts 10-30s on unpopular models. Limits not published as fixed numbers.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "Llama 3.2 8B (Serverless)",
          "cost": "$0",
          "context": "Model-dependent",
          "rpm": "~300 req/hour (Serverless)",
          "tpm": "Model max context",
          "rpd": "Not published",
          "tpd": "Small monthly credit pool (PRO: 2M credits/mo)",
          "verified": "2026-08-12"
        },
        {
          "name": "Qwen 2.5 7B (Serverless)",
          "cost": "$0",
          "context": "Model-dependent",
          "rpm": "~300 req/hour (Serverless)",
          "tpm": "Model max context",
          "rpd": "Not published",
          "tpd": "Small monthly credit pool (PRO: 2M credits/mo)",
          "verified": "2026-08-12"
        },
        {
          "name": "Mistral 7B (Serverless)",
          "cost": "$0",
          "context": "Model-dependent",
          "rpm": "~300 req/hour (Serverless)",
          "tpm": "Model max context",
          "rpd": "Not published",
          "tpd": "Small monthly credit pool (PRO: 2M credits/mo)",
          "verified": "2026-08-12"
        },
        {
          "name": "Inference Providers gateway (15+ partners)",
          "cost": "$0",
          "context": "Model-dependent",
          "rpm": "~300 req/hour (Serverless)",
          "tpm": "Model max context",
          "rpd": "Not published",
          "tpd": "Small monthly credit pool (PRO: 2M credits/mo)",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Mistral La Plateforme",
      "url": "https://docs.mistral.ai",
      "free_type": "Rate-limited free (Experiment)",
      "notes": "Phone (SMS) verification required, no card. Exact limits no longer published - see Admin Console Limits per workspace. Evaluation tier, not production.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "Mistral Large",
          "cost": "$0 (Experiment)",
          "context": "Model-dependent",
          "rpm": "~1 req/sec",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "~1B tokens/month",
          "verified": "2026-08-12"
        },
        {
          "name": "Codestral",
          "cost": "$0 (Experiment)",
          "context": "Model-dependent",
          "rpm": "~1 req/sec",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "~1B tokens/month",
          "verified": "2026-08-12"
        },
        {
          "name": "All API models (Experiment tier)",
          "cost": "$0 (Experiment)",
          "context": "Model-dependent",
          "rpm": "~1 req/sec",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "~1B tokens/month",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "SambaNova Cloud",
      "url": "https://cloud.sambanova.ai/apis",
      "free_type": "Rate-limited free",
      "notes": "OpenAI-compatible base URL api.sambanova.ai/v1. Preview models can be pulled at any time. No credit card, no phone verification.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "DeepSeek-V3.1",
          "cost": "$0",
          "context": "128K",
          "rpm": "20",
          "tpm": "Not published",
          "rpd": "20",
          "tpd": "200K tokens/day",
          "verified": "2026-08-12"
        },
        {
          "name": "MiniMax-M2.7",
          "cost": "$0",
          "context": "128K",
          "rpm": "20",
          "tpm": "Not published",
          "rpd": "20",
          "tpd": "200K tokens/day",
          "verified": "2026-08-12"
        },
        {
          "name": "Gemma 4 31B preview",
          "cost": "$0",
          "context": "128K",
          "rpm": "20",
          "tpm": "Not published",
          "rpd": "20",
          "tpd": "200K tokens/day",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "NVIDIA NIM (build.nvidia.com)",
      "url": "https://build.nvidia.com",
      "free_type": "Trial credits",
      "notes": "Credit-based, not a rate-limited-free tier. Larger grants need corporate email, tie to ~90-day evaluation windows.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "GLM-5",
          "cost": "$0 (trial credits)",
          "context": "Model-dependent",
          "rpm": "~40",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "~1,000 credits at signup (up to ~5,000)",
          "verified": "2026-08-12"
        },
        {
          "name": "Kimi-2.5",
          "cost": "$0 (trial credits)",
          "context": "Model-dependent",
          "rpm": "~40",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "~1,000 credits at signup (up to ~5,000)",
          "verified": "2026-08-12"
        },
        {
          "name": "NIM-packaged open models",
          "cost": "$0 (trial credits)",
          "context": "Model-dependent",
          "rpm": "~40",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "~1,000 credits at signup (up to ~5,000)",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Z.AI (Zhipu)",
      "url": "https://z.ai",
      "free_type": "Rate-limited free",
      "notes": "Free-tier limits revised twice in the past year - verify. Peak-hour throttling. Flash models are free regardless of tier. OpenAI-compatible.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "GLM-5.1",
          "cost": "$0",
          "context": "Up to 203K",
          "rpm": "3 (burst)",
          "tpm": "Not published",
          "rpd": "1,000 (1K RPD tier)",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "GLM-4.5-Flash",
          "cost": "$0",
          "context": "Up to 203K",
          "rpm": "3 (burst)",
          "tpm": "Not published",
          "rpd": "1,000",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "GLM-4.7-Flash",
          "cost": "$0",
          "context": "Up to 203K",
          "rpm": "3 (burst)",
          "tpm": "Not published",
          "rpd": "1,000",
          "tpd": "Not published",
          "verified": "2026-08-12"
        },
        {
          "name": "GLM-4.6V-Flash (vision)",
          "cost": "$0",
          "context": "Up to 203K",
          "rpm": "3 (burst)",
          "tpm": "Not published",
          "rpd": "1,000",
          "tpd": "Not published",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "Together AI",
      "url": "https://www.together.ai/pricing",
      "free_type": "Trial credits",
      "notes": "One-time credit, not forever-free. Card required once credits run out. Startup programs can grant far more.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "200+ open models (Llama, Qwen, DeepSeek)",
          "cost": "$0 (trial credits)",
          "context": "Model-dependent",
          "rpm": "~60 (Build tier)",
          "tpm": "~100K (Build tier)",
          "rpd": "Not published",
          "tpd": "$25 one-time credit",
          "verified": "2026-08-12"
        }
      ]
    },
    {
      "name": "DeepInfra",
      "url": "https://docs.deepinfra.com/account/rate-limits",
      "free_type": "Trial credits",
      "notes": "200 concurrent requests per model - high ceiling. Credit-based, no daily cap while credits last. OpenAI-compatible.",
      "timeout": "Not published",
      "verified": "2026-08-12",
      "models": [
        {
          "name": "40+ open models (Llama, Qwen, DeepSeek, Mistral)",
          "cost": "$0 (trial credits)",
          "context": "Model-dependent",
          "rpm": "~60 (varies by model)",
          "tpm": "Not published",
          "rpd": "Not published",
          "tpd": "$5 signup credits",
          "verified": "2026-08-12"
        }
      ]
    }
  ]
}