| Mistral | https://docs.mistral.ai/inference/pricing | Yes | Free mode in Mistral Studio: create API keys and use included monthly usage of Mistral models via the API and playground; Mistral Moderation 2 is free ($0/M tokens) | Included monthly usage within the limits shown on the console Limits page; pay-as-you-go prepaid credits needed beyond that | https://docs.mistral.ai |
| Cohere | https://cohere.com/pricing | Yes | Trial API key (auto-created per account): API calls free; access to Cohere models; Production keys are pay-as-you-go | Trial keys are rate limited; not permitted for production or commercial use (see docs.cohere.com/docs/rate-limits) | https://docs.cohere.com/ |
| OpenAI | https://developers.openai.com/api/docs/pricing | No | No free token allowance: API usage is billed at model rates. Free allowances only on tools: 1 GB file search storage and 1 GB ChatKit upload storage per account per month | 1 GB free file search storage; all model usage is pay-as-you-go | https://developers.openai.com/api/reference/overview |
| Anthropic | https://docs.claude.com/en/docs/about-claude/pricing | Yes | Small amount of free credits for new users to test the API (no ongoing free token tier); code execution tool includes 1,550 free container hours per organization per month | One-time trial credits for new users; then prepaid usage, with rate limits set by usage tier | https://platform.claude.com/docs/en/api/rate-limits |
| Azure OpenAI | https://azure.microsoft.com/en-us/pricing/details/azure-openai/ | Yes | No ongoing free tier for the service itself; new Azure accounts get a $200 Azure free account credit valid for 30 days that can be applied to Azure OpenAI. Deployments also use a Free Tier quota tier. | Free Tier is the lowest of seven quota tiers (Free Tier + Tiers 1-6); quotas are scoped at the Azure subscription level and increase automatically with usage. Higher tiers offer e.g. thousands of RPM and millions of TPM per model. | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure |
| Gemini API | https://ai.google.dev/gemini-api/docs/pricing | Yes | Free tier: limited access to certain models — free input & output tokens on Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, 3 Flash Preview, Live/Transcribe/TTS models (Standard); flagship models (Gemini 4 Argon, Pro, image generation) not available; no context caching or Batch API on free tier; Google AI Studio access | Free tier: per-model RPM/TPM rate limits (see rate-limits page); paid usage tiers unlock higher limits; free-tier content used to improve Google products; 5,000 free search grounding requests/month shared across Gemini 3+ models (paid tier) | https://ai.google.dev/gemini-api/docs |
| Hugging Face | https://huggingface.co/docs/inference-providers/en/pricing | No | No free inference credits for free accounts: free users must buy credits to use Inference Providers; PRO users and each Team/Enterprise seat get $2.00/month of credits | Free users: no included monthly credits (credits purchase required); Hub rate limits still apply | https://huggingface.co/docs/inference-providers |
| OpenRouter | https://openrouter.ai/pricing | Yes | 25+ free models from 4 free providers with chat and API access, no platform fees; the Free Models Router (openrouter/free) auto-selects a free model at random, filtering by required features (vision, tool calling, structured outputs). | Free models capped at 20 requests per minute and 50 requests per day, rising to 1,000 requests per day once the account has bought at least $10 of credits; failed attempts count toward the daily cap. | https://openrouter.ai/docs |
