1stTop pick
Researched 48d agoT5Gemma
- Capability signal
- —
- Output (from)
- Free
Best Free LLMs You Can Use Right Now (2026)
Last refreshed 2026-07-15. Next refresh: weekly.
Free LLMs you can use right now: zero-cost hosted tiers first, then open-weight models you can self-host. Updated as free tiers change.
Need the self-host and license-first view? Compare the open-source leaderboard for open-weight models ranked separately from hosted free-tier availability.
Verdict
Use T5Gemma for free-tier work today.
DeepSeek V4 Pro is the runner-up; compare Capability signal against MMLU-Pro.
2ndShortlist
Researched 54d agoDeepSeek V4 Pro
- MMLU-Pro
- 87.5%
- Free basis
- Self-host no token fee
3rdShortlist
Researched 45d agoDeepSeek V4 Flash
- MMLU-Pro
- 86.4%
- Free basis
- Self-host no token fee
How we rank
Free leaders prioritize models with a current zero-dollar hosted tier, then fall back to open-weight models you can self-host without token fees.
- Eligibility — Models qualify if at least one current public/self-serve provider row lists both input and output token pricing as $0, or if the model is open-weight/self-host-capable under the same license flags used by /best/open-source.
- Primary ranking — Zero-cost hosted availability comes first. Within the hosted-free and open-weight fallback groups, rows sort by MMLU-Pro, then GPQA Diamond, then MMLU, then newer release. Podium cards keep hosted $0 routes ahead of open-weight fallback rows; a fallback card is labeled as self-host/no-token-fee rather than paid hosted output.
- Variant collapse — We keep one row per model family (`familySlug` + parameter tier). When headline scores tie within ±0.5 pt (±10 Elo on Chatbot Arena), we pick the canonical SKU by lowest tracked input price, then GA over preview or limited access, then newest `release`. A folded sibling within the benchmark noise band can show a "Tied within margin" chip on that score cell.
- Open-weight fallback — Open-weight fallback rows represent local or self-hosted use where the model itself has no token fee; you still need to budget your own compute.
- Related view — Use /best/open-source when the decision is license and self-host posture first; this free page answers what you can use at zero dollars right now.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Gemma 4 31B IT VisionTools Capability signal: MMLU-Pro 85.2% | Free | Free | |
| 2 | Gemma 4 26B A4B IT VisionTools Capability signal: MMLU-Pro 82.6% | Free | Free | |
| 3 | Nemotron 3 Nano Omni Capability signal: MMLU-Pro 71.8% | Free | Free | |
| 4 | Gemma 4 E4B IT Tools Capability signal: MMLU-Pro 69.4% | Free | Free | |
| 5 | Gemma 4 E2B IT Tools Capability signal: MMLU-Pro 60% | Free | Free | |
| 6 | gpt-oss-120b Tools Capability signal: GPQA Diamond 78.2% | Free | Free | |
| 7 | gpt-oss-20b Tools Capability signal: GPQA Diamond 68.8% | Free | Free | |
| 8 | CoBuddy ReasoningTools Capability signal: — | Free | Free | |
| 9 | Laguna XS.2 Capability signal: — | Free | Free | |
| 10 | Laguna M.1 Capability signal: — | Free | Free | |
| 11 | T5Gemma Tools Capability signal: — | Free | Free | |
| 12 | Gemma 3 Capability signal: — | Free | Free | |
| 13 | Gemma 3n Capability signal: — | Free | Free | |
| 14 | MedGemma VisionTools Capability signal: — | Free | Free | |
| 15 | MedSigLIP VisionTools Capability signal: — | Free | Free | |
| 16 | Qwen3.6-Plus VisionTools Capability signal: MMLU-Pro 88.5% | $0.33 | $1.95 | |
| 17 | Qwen3.6 Max Preview PreviewReasoningVisionTools Capability signal: MMLU-Pro 88.5% | $1.04 | $6.24 | |
| 18 | Qwen3.5-397B-A17B ReasoningVisionTools Capability signal: MMLU-Pro 87.8% | $0.39 | $2.34 | |
| 19 | DeepSeek V4 Pro ReasoningTools Capability signal: MMLU-Pro 87.5% | $0.43 | $0.87 | |
| 20 | Qwen3.5-122B-A10B ReasoningVisionTools Capability signal: MMLU-Pro 86.7% | $0.26 | $2.08 |
Honorable mentions
Next seats in this ranking. Lines below are from each model's stored description in LLMReference seed data—spot-check the model page before relying on a capability claim.
Open-weight dense Qwen3.6 27B model with native multimodal support across text, image, and video. Apache 2.0.
86.2%
MMLU-Pro
Open-weight dense 27B multimodal Qwen3.5 model with native vision-language support. Apache 2.0.
86.1%
MMLU-Pro
- #6GLM-5
Flagship open-weight foundation model from Zhipu AI with 744B parameters (40B active per token) in Mixture of Experts architecture. Trained on 28.5T tokens using DeepSeek Sparse Attention on Huawei Ascend hardware. Achieves state-of-the-art performance on coding and agentic benchmarks (SWE-bench Verified: 77.8%). Supports autonomous planning, multi-step tool use, and self-correction.
86%
MMLU-Pro
Compare Top Picks
Side-by-side comparison of the top picks by price, benchmark, and API access.
Browse Other Categories
Best LLMs for Code GenerationBest LLMs for RAGBest LLMs for Agents & Coding (2026)Best LLMs for ClassificationBest Open Source LLMsBest Multimodal / Vision LLMsBest LLM for Translation in 2026Best AI Image Models in 2026Best AI Video Models in 2026Best LLMs for Reasoning & MathBest Small Language Models (SLMs)Best LLMs for Function Calling & Tool UseCheapest LLM APIs You Can Call Right NowBest Long Context LLMsBest Mainstream LLM APIs, RankedBest LLMs for EnterpriseBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support
Frequently asked questions
Which LLM is best for free-tier use?
T5Gemma is the current LLMReference top pick for free-tier use. The verdict uses the stored category signal Capability signal: —. Output pricing is listed as Free. Review the linked model and provider pages before production use because availability and pricing can change.
How does T5Gemma compare to DeepSeek V4 Pro for free-tier use?
T5Gemma is the top visible pick with Capability signal: —; DeepSeek V4 Pro is the runner-up with MMLU-Pro: 87.5%. The pricing cards show T5Gemma: output pricing is listed as free and DeepSeek V4 Pro: free basis: self-host no token fee.
How does LLMReference rank LLMs for free-tier use?
LLMReference ranks LLMs for free-tier use from stored model, benchmark, freshness, and pricing data. The current methodology summary is: Free leaders prioritize models with a current zero-dollar hosted tier, then fall back to open-weight models you can self-host without token fees.
How often is this list updated?
The LLM rankings on this page are updated daily as new benchmark scores, provider availability, and pricing data are tracked. The "as of" date at the top of the page shows the most recent refresh.
How do you decide which models appear in the top 3?
The podium picks are driven by the primary benchmark signal for this category (shown in the Methodology section), filtered to non-deprecated models with confirmed API availability. In ties, we prefer the more recently released model.
Are preview or beta models included?
Preview models appear in the "Watch list" section but are not in the main ranked podium unless the category explicitly allows it (e.g., /best/coding and /best/agents, where preview models often lead benchmarks).
Can I compare two specific models head-to-head?
Yes — use the Compare tool at llmreference.com/compare for a side-by-side breakdown of context window, pricing, benchmarks, and provider availability.
Is the pricing data real-time?
Pricing is tracked from provider documentation and updated regularly. It reflects the best available public data, not live API quotes — always verify before billing.