Free LLM APIs
A live catalog of free AI APIs for current DeepSeek, Qwen, Nemotron, Mistral, Llama, Gemini, and other models. Compare providers, context windows, and limits before connecting Cursor, VS Code, Cline, Open WebUI, or your own application.
Best free models right now
Auto-picked by benchmarks, size, and number of free providers.
New free models this week
All free models
One row per model; the model card lists every free provider, limits, and code examples.
| # | Model ↕ | AA Index ↕ | GPQA ↕ | Context ↕ | Size ↕ | Free at ↕ | |
|---|---|---|---|---|---|---|---|
| 1 | |
45.1 | — | 1M | Frontier |    OrcaRouter, NVIDIA Build, OpenCode Zen |
|
| 2 | |
44.8 | 92% | 1M | Frontier |   Together AI, NVIDIA Build, UnoRouter |
|
| 3 | |
41.8 | 91% | 1M | Mid-size | OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen |
|
| 4 |  |
42.7 | — | 1M | Frontier | NVIDIA Build, UnoRouter |
|
| 5 | |
43.7 | — | 1M | Frontier | NVIDIA Build |
|
| 6 | 43.9 | — | 262K | Small | UnoRouter |
||
| 7 | |
40.9 | 95% | 1M | Mid-size | Google AI Studio |
|
| 8 |
Mimo V2.6 Flash
Open weights
|
37.9 | — | 1M | Small | UnoRouter, OpenCode Zen |
|
| 9 |  |
33.7 | 91% | 262K | Mid-size |   Groq, Cloudflare Workers AI, UnoRouter |
|
| 10 |  |
26.5 | — | 1M | Mid-size |  OpenRouter, OpenCode Zen |
|
| 11 | |
22.9 | 87% | 1M | Frontier | OpenRouter, NVIDIA Build, UnoRouter |
|
| 12 | 25.3 | 90% | 256K | Small | OrcaRouter, UnoRouter |
||
| 13 | 25.7 | 90% | 1M | Small | OpenRouter |
||
| 14 | 25.0 | 87% | 1M | Small | OpenRouter |
||
| 15 |
Solar Mini 4
Upstage
|
24.1 | — | 524K | Small |  Nous Portal |
|
| 16 | |
22.2 | 84% | 1M | Small | UnoRouter |
|
| 17 |  |
16.7 | 79% | 262K | Mid-size | OpenRouter, Together AI, Cloudflare Workers AI, UnoRouter |
|
| 18 | 19.1 | 78% | 1M | Frontier | Nous Portal |
||
| 19 | |
18.2 | 84% | 262K | Mid-size | Together AI, UnoRouter |
|
| 20 | |
12.9 | 74% | 1M | Mid-size |  +1OpenRouter, NVIDIA Build, Vercel AI Gateway, UnoRouter, OpenCode Zen |
|
| 21 | |
14.7 | 86% | 262K | Mid-size | OpenRouter, Together AI, NVIDIA Build |
|
| 22 | |
17.7 | 83% | 262K | Frontier | Together AI |
|
| 23 | |
— | — | 262K | Frontier | OpenRouter, NVIDIA Build, UnoRouter |
|
| 24 | |
— | — | 1M | Frontier | Together AI |
|
| 25 | |
— | — | 1M | Frontier | Together AI |
|
| 26 | |
— | — | 1M | Frontier | Together AI |
|
| 27 | |
— | — | 1M | Frontier | Together AI |
|
| 28 | — | — | 1M | Frontier | Nous Portal |
||
| 29 |  |
— | — | 1M | Frontier | UnoRouter |
|
| 30 | |
— | — | 1M | Frontier | UnoRouter |
|
| 31 | |
10.3 | 47% | 262K | Mid-size |  +1OpenRouter, Together AI, NVIDIA Build, TokenRouter, UnoRouter |
|
| 32 | |
14.2 | 75% | 262K | Mid-size | Together AI |
|
| 33 | |
— | — | 262K | Frontier | Together AI |
|
| 34 | |
— | — | 262K | Frontier | Together AI |
|
| 35 | |
— | — | 262K | Frontier | Together AI |
|
| 36 | |
— | — | 262K | Frontier | Together AI |
|
| 37 | |
— | — | 256K | Frontier | Cloudflare Workers AI |
|
| 38 |
Ornith 1.5 122B
Ornith · 122B · New
|
— | — | 262K | Frontier | Nous Portal |
|
| 39 |
Beam 1.0 501B A23B
Reflection · 501B · 23B
|
— | — | 262K | Frontier | Nous Portal |
|
| 40 | |
— | — | 262K | Frontier | Nous Portal |
|
| 41 |  |
10.0 | 61% | 131K | Mid-size | Groq, Cloudflare Workers AI, NVIDIA Build, UnoRouter |
|
| 42 | |
13.3 | 79% | 262K | Small | Together AI |
|
| 43 | |
13.1 | 77% | 262K | Small | UnoRouter |
|
| 44 | |
— | — | 16K | Frontier | Together AI |
|
| 45 | |
— | — | 131K | Frontier | Together AI |
|
| 46 | |
— | — | 131K | Frontier | Together AI |
|
| 47 | |
— | — | 131K | Frontier | Together AI |
|
| 48 | |
— | — | 66K | Frontier | Together AI |
|
| 49 | |
— | — | 197K | Frontier | Together AI |
|
| 50 | |
— | — | 203K | Frontier | Together AI |
|
| 51 | |
— | — | 203K | Frontier | Together AI |
|
| 52 | |
— | — | 8K | Frontier | Together AI |
|
| 53 | |
— | — | 203K | Frontier | Together AI |
|
| 54 | |
— | — | 131K | Frontier | Together AI |
|
| 55 | |
— | — | 24K | Frontier | Cloudflare Workers AI |
|
| 56 | |
— | — | — | Frontier | OrcaRouter |
|
| 57 | |
— | — | — | Frontier | NVIDIA Build |
|
| 58 | |
— | — | — | Frontier | NVIDIA Build |
|
| 59 |
Palmyra Creative 122B
Writer · 122B
|
— | — | — | Frontier | NVIDIA Build |
|
| 60 | |
— | — | 128K | Frontier | UnoRouter |
|
| 61 | — | — | 8K | Frontier | UnoRouter |
||
| 62 | — | — | 131K | Frontier | UnoRouter |
||
| 63 | |
— | — | 205K | Frontier | UnoRouter |
|
| 64 | 12.3 | — | 260K | Small | UnoRouter |
||
| 65 | |
11.6 | 78% | 131K | Frontier | Groq, Cloudflare Workers AI |
|
| 66 | 12.5 | 70% | 131K | Small | UnoRouter |
||
| 67 |  |
9.9 | 76% | 262K | Small | OpenRouter, UnoRouter |
|
| 68 | |
11.2 | 76% | 262K | Frontier | Together AI |
|
| 69 |  |
— | — | 131K | Mid-size | Mistral AI, Together AI, NVIDIA Build |
|
| 70 | — | — | 1M | Small | OpenRouter, Vercel AI Gateway, Nous Portal, UnoRouter |
||
| 71 | |
— | — | 262K | Mid-size | Mistral AI, UnoRouter |
|
| 72 | |
— | — | 262K | Mid-size | Together AI, Cloudflare Workers AI |
|
| 73 | |
6.5 | 59% | 10.5M | Frontier | Together AI, Cloudflare Workers AI, UnoRouter |
|
| 74 | |
— | — | 1M | Mid-size | UnoRouter |
|
| 75 | |
— | — | 1M | Mid-size | UnoRouter |
|
| 76 | |
— | — | 1M | Mid-size | UnoRouter |
|
| 77 | |
— | — | 1M | Mid-size | UnoRouter |
|
| 78 | |
8.9 | 76% | 1M | Mid-size | NVIDIA Build |
|
| 79 | — | — | 262K | Small | OpenRouter, NVIDIA Build, Nous Portal, UnoRouter |
||
| 80 | |
— | — | 80K | Mid-size | Cloudflare Workers AI, UnoRouter |
|
| 81 | |
— | — | 131K | Mid-size | Cloudflare Workers AI, UnoRouter |
|
| 82 | |
— | — | 33K | Mid-size | Cloudflare Workers AI, UnoRouter |
|
| 83 | |
— | — | 24K | Mid-size | Cloudflare Workers AI, UnoRouter |
|
| 84 |
Muse Glimmer 30B
Meta · 30B
|
— | — | 131K | Mid-size | NVIDIA Build, UnoRouter |
|
| 85 | |
9.5 | 67% | 262K | Mid-size | UnoRouter |
|
| 86 |
Xing4.0 29B A4B
XingChen · 29B · 4B
|
— | — | 262K | Mid-size | OpenRouter |
|
| 87 | — | — | 262K | Mid-size | Together AI |
||
| 88 | |
— | — | 262K | Mid-size | Together AI |
|
| 89 |
Holo3 35B A3B
35B · 3B
|
— | — | 262K | Mid-size | Together AI |
|
| 90 | — | — | 1M | Small | Vercel AI Gateway, UnoRouter, OpenCode Zen |
||
| 91 | — | — | 262K | Mid-size | UnoRouter |
||
| 92 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 93 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 94 | 8.4 | 56% | 128K | Small | OpenRouter, UnoRouter |
||
| 95 | |
5.4 | 22% | 131K | Mid-size | Together AI, Cloudflare Workers AI, NVIDIA Build, UnoRouter |
|
| 96 | |
8.9 | 76% | 262K | Mid-size | Together AI |
|
| 97 | |
7.7 | 50% | 131K | Frontier | Together AI, UnoRouter |
|
| 98 | |
— | — | 16K | Mid-size | Together AI |
|
| 99 | |
— | — | 16K | Mid-size | Together AI |
|
| 100 | |
— | — | 66K | Mid-size | Together AI |
|
| 101 | |
— | — | 131K | Mid-size | Together AI |
|
| 102 | |
— | — | 131K | Mid-size | Together AI |
|
| 103 | |
— | — | 131K | Mid-size | Together AI |
|
| 104 | |
— | — | 131K | Mid-size | Together AI |
|
| 105 | — | — | 131K | Mid-size | Together AI |
||
| 106 | |
— | — | 131K | Mid-size | Together AI |
|
| 107 | |
— | — | 2K | Mid-size | Together AI |
|
| 108 | |
— | — | 41K | Mid-size | Together AI |
|
| 109 | |
— | — | 131K | Mid-size | Together AI |
|
| 110 | |
— | — | 8K | Mid-size | Together AI |
|
| 111 | |
— | — | 128K | Mid-size | Cohere |
|
| 112 | |
— | — | 16K | Mid-size | Cohere |
|
| 113 | |
— | — | 128K | Mid-size | Cloudflare Workers AI |
|
| 114 | |
— | — | 128K | Mid-size | Cloudflare Workers AI |
|
| 115 | |
— | — | — | Mid-size | NVIDIA Build |
|
| 116 | |
— | — | — | Mid-size | NVIDIA Build |
|
| 117 | |
— | — | 131K | Mid-size | UnoRouter |
|
| 118 | |
— | — | 128K | Mid-size | UnoRouter |
|
| 119 | |
— | — | 128K | Mid-size | UnoRouter |
|
| 120 | — | — | 131K | Mid-size | UnoRouter |
||
| 121 | |
— | — | 33K | Mid-size | UnoRouter |
|
| 122 | |
— | — | 25K | Mid-size | UnoRouter |
|
| 123 |
Typhoon V2.5 30B A3B Instruct
30B · 3B
|
— | — | 131K | Mid-size | UnoRouter |
|
| 124 |
Flint 40B
40B · New
|
— | — | — | Mid-size | OpenCode Zen |
|
| 125 | |
8.9 | 58% | 131K | Small | Together AI |
|
| 126 | |
8.6 | 66% | 41K | Mid-size | Together AI |
|
| 127 | |
6.4 | 43% | 16K | Frontier | Together AI, NVIDIA Build |
|
| 128 | |
6.9 | 46% | 262K | Small | Together AI |
|
| 129 | |
7.8 | 43% | 131K | Small | Together AI |
|
| 130 |
Dots3-Note Preview
Dots Studio
|
— | — | 512K | Small | OpenRouter, UnoRouter |
|
| 131 | |
— | — | 16K | Frontier | Together AI, NVIDIA Build |
|
| 132 | |
— | — | 66K | Frontier | Together AI, NVIDIA Build |
|
| 133 | |
7.5 | 73% | 128K | Frontier | NVIDIA Build |
|
| 134 | |
7.3 | 52% | 131K | Frontier | Together AI |
|
| 135 |
Command A 03 2025
Cohere · 111B · Legacy
|
— | — | 288K | Frontier | Cohere |
|
| 136 |
Command A Plus 05 2026
Cohere · 111B · Legacy
|
— | — | 436K | Frontier | Cohere |
|
| 137 | |
— | — | 289K | Frontier | Cohere |
|
| 138 |
Cohere Command A
Cohere · 111B · Legacy
|
— | — | 256K | Frontier | UnoRouter |
|
| 139 |
Allam 2 7B
7B
|
— | — | 4K | Small | Groq, UnoRouter |
|
| 140 | |
— | — | 32K | Small | Together AI, Cloudflare Workers AI |
|
| 141 | |
— | — | 66K | Small | Together AI, NVIDIA Build |
|
| 142 | |
— | — | 131K | Small | Together AI, Cloudflare Workers AI |
|
| 143 |
Flint
Recursive · New
|
— | — | 262K | Small | OpenRouter |
|
| 144 | |
— | — | 256K | Small | Mistral AI |
|
| 145 | |
— | — | 16K | Frontier | Together AI |
|
| 146 | |
— | — | 262K | Small | Together AI |
|
| 147 | |
— | — | 128K | Frontier | Cohere |
|
| 148 |
Command R Plus 08 2024
Cohere · 104B · Legacy
|
— | — | 128K | Frontier | Cohere |
|
| 149 | — | — | 262K | Small | Cloudflare Workers AI |
||
| 150 | — | — | 262K | Small | Cloudflare Workers AI |
||
| 151 | |
— | — | — | Frontier | NVIDIA Build |
|
| 152 |
DBRX Instruct
Databricks · 132B · 36B · Legacy
|
— | — | — | Frontier | NVIDIA Build |
|
| 153 |  |
— | — | — | Frontier | NVIDIA Build |
|
| 154 | |
— | — | — | Frontier | NVIDIA Build |
|
| 155 | |
— | — | — | Frontier | NVIDIA Build |
|
| 156 |
Mistral Large
Mistral AI · Legacy
|
— | — | — | Frontier | NVIDIA Build |
|
| 157 |
Mistral Large 2
Mistral AI · 123B · Legacy
|
— | — | — | Frontier | NVIDIA Build |
|
| 158 | |
— | — | — | Frontier | NVIDIA Build |
|
| 159 |
Palmyra Fin 70B 32K
Writer · 70B · Legacy
|
— | — | 33K | Frontier | NVIDIA Build |
|
| 160 |
Palmyra Med 70B
Writer · 70B · Legacy
|
— | — | — | Frontier | NVIDIA Build |
|
| 161 |
Palmyra Med 70B 32K
Writer · 70B · Legacy
|
— | — | 33K | Frontier | NVIDIA Build |
|
| 162 |
Yi Large
01.AI · Legacy
|
— | — | — | Frontier | NVIDIA Build |
|
| 163 | |
— | — | 256K | Small | UnoRouter |
|
| 164 | — | — | 262K | Small | UnoRouter |
||
| 165 | — | — | 524K | Small | UnoRouter |
||
| 166 | — | — | 262K | Small | UnoRouter |
||
| 167 | 5.6 | 24% | 4K | Small | Together AI |
||
| 168 | |
5.1 | 22% | 33K | Small | Together AI |
|
| 169 | 5.1 | 34% | 131K | Small | UnoRouter |
||
| 170 | |
— | — | 131K | Small | Together AI |
|
| 171 | |
— | — | 33K | Small | Together AI |
|
| 172 | |
— | — | 131K | Small | Together AI |
|
| 173 | |
— | — | 33K | Small | Together AI |
|
| 174 | |
— | — | 131K | Small | Together AI |
|
| 175 | |
— | — | 131K | Small | Together AI |
|
| 176 | |
— | — | 41K | Small | Together AI |
|
| 177 | |
— | — | 41K | Small | Together AI |
|
| 178 | |
— | — | 41K | Small | Together AI |
|
| 179 | |
— | — | 131K | Small | Together AI |
|
| 180 | — | — | 33K | Small | Together AI |
||
| 181 | — | — | 33K | Small | Together AI |
||
| 182 | |
— | — | 80K | Small | Cloudflare Workers AI |
|
| 183 | — | — | 32K | Small | Cloudflare Workers AI |
||
| 184 | — | — | 66K | Small | Cloudflare Workers AI |
||
| 185 | — | — | 131K | Small | Cloudflare Workers AI |
||
| 186 |
clairic
New
|
— | — | 66K | Small | Cloudflare Workers AI |
|
| 187 |
clef-omni
Vision
|
— | — | 66K | Small | Cloudflare Workers AI |
|
| 188 | |
— | — | 4K | Small | Cloudflare Workers AI |
|
| 189 | — | — | 25K | Small | Cloudflare Workers AI |
||
| 190 |
Pod
OrcaRouter · New
|
— | — | — | Small | OrcaRouter |
|
| 191 |
Hy4 preview
Tencent
|
— | — | — | Small | OrcaRouter |
|
| 192 | |
— | — | — | Small | NVIDIA Build |
|
| 193 | |
— | — | 8K | Small | NVIDIA Build |
|
| 194 | — | — | 8K | Small | UnoRouter |
||
| 195 | — | — | 16K | Small | UnoRouter |
||
| 196 | — | — | 8K | Small | UnoRouter |
||
| 197 | — | — | 128K | Small | UnoRouter |
||
| 198 | — | — | 33K | Small | UnoRouter |
||
| 199 | |
— | — | 33K | Small | UnoRouter |
|
| 200 |
SWE 1 6 Slow
Coding
|
— | — | 6K | Small | UnoRouter |
|
| 201 | — | — | 33K | Small | UnoRouter |
||
| 202 | — | — | — | Small | OpenCode Zen |
||
| 203 | |
— | — | 33K | Small | Together AI, Cloudflare Workers AI, NVIDIA Build, UnoRouter |
|
| 204 | |
— | — | 33K | Mid-size | Together AI |
|
| 205 |
Command R 08 2024
Cohere · 35B · Legacy
|
— | — | 128K | Mid-size | Cohere |
|
| 206 |
Command R7b 12 2024
Cohere · 35B · Legacy
|
— | — | 132K | Mid-size | Cohere |
|
| 207 |
Command R7b Arabic 02 2025
Cohere · 35B · Legacy
|
— | — | 128K | Mid-size | Cohere |
|
| 208 | |
— | — | — | Mid-size | NVIDIA Build |
|
| 209 | — | — | — | Mid-size | NVIDIA Build |
||
| 210 | |
— | — | — | Mid-size | NVIDIA Build |
|
| 211 | |
— | — | — | Mid-size | NVIDIA Build |
|
| 212 |  |
— | — | — | Mid-size | NVIDIA Build |
|
| 213 | — | — | — | Mid-size | NVIDIA Build |
||
| 214 | |
— | — | 8K | Small | Together AI, Cloudflare Workers AI, NVIDIA Build |
|
| 215 | |
— | — | 8K | Small | Together AI, Cloudflare Workers AI |
|
| 216 | |
— | — | 8K | Small | Together AI |
|
| 217 | |
— | — | — | Small | NVIDIA Build |
|
| 218 | |
— | — | — | Small | NVIDIA Build |
|
| 219 | |
— | — | — | Small | NVIDIA Build |
|
| 220 | — | — | — | Small | NVIDIA Build |
||
| 221 | — | — | — | Small | NVIDIA Build |
||
| 222 | — | — | — | Small | NVIDIA Build |
||
| 223 | — | — | — | Small | NVIDIA Build |
||
| 224 | — | — | — | Small | NVIDIA Build |
||
| 225 | |
— | — | 131K | Small | NVIDIA Build |
|
| 226 | |
— | — | — | Small | NVIDIA Build |
|
| 227 | — | — | — | Small | NVIDIA Build |
||
| 228 | |
— | — | — | Small | NVIDIA Build |
|
| 229 |
Zamba2 7B Instruct
Zyphra · 7B · Legacy
|
— | — | — | Small | NVIDIA Build |
|
| 230 | |
— | — | 128K | Mid-size | OpenRouter |
|
| 231 | |
— | — | 131K | Mid-size | UnoRouter |
|
| 232 |
Riva Translate 4B Instruct V2
NVIDIA · 4B · Translation
|
— | — | 8K | Small | NVIDIA Build, UnoRouter |
|
| 233 |
Command A Translate 08 2025
Cohere · 111B · Translation · Legacy
|
— | — | 9K | Frontier | Cohere |
|
| 234 |
OrcaVerify Text 1.0
Orca · Moderation
|
— | — | — | Small | OrcaRouter |
|
| 235 |
Riva Translate 4B Instruct
NVIDIA · 4B · Translation
|
— | — | — | Small | NVIDIA Build |
|
| 236 |
Lyria 3 Pro Preview
Google · Audio
|
— | — | 1M | — | OpenRouter |
|
| 237 |
Lyria 3 Clip Preview
Google · Audio
|
— | — | 1M | — | OpenRouter |
|
| 238 |
Mistral Embed
Mistral AI · Embeddings
|
— | — | 8K | — | Mistral AI |
|
| 239 |
Nano Banana Pro (Gemini 3 Pro Image Preview)
Google · Image generation
|
— | — | 66K | — | OrcaRouter |
|
| 240 |
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Google · Image generation
|
— | — | 66K | — | OrcaRouter |
|
| 241 | 
Grok Imagine Image
xAI · Image generation
|
— | — | — | — | OrcaRouter |
|
| 242 |
OrcaDub 1.0
OrcaDub · Audio
|
— | — | — | — | OrcaRouter |
|
| 243 |
Fusion
OrcaRouter · Auto-router
|
— | — | 1M | — | OrcaRouter |
|
| 244 |
Fusion Mini
OrcaRouter · Auto-router
|
— | — | 1M | — | OrcaRouter |
|
| 245 |
Free Models Router
OpenRouter · Auto-router
|
— | — | 200K | — | OpenRouter, OrcaRouter |
|
| 246 |
Fusion Flash
OrcaRouter · Auto-router
|
— | — | 262K | — | OrcaRouter |
Benchmarks: Artificial Analysis (October 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.
Free API providers
Latest check status, model count, and access terms.
Models with the :free suffix allow 50 requests per day, or 1,000 per day after a one-time $10 top-up (20 requests per minute).
Free plan with per-model limits on requests and tokens per minute and per day; very high generation speed on LPU hardware.
The Gemini API free tier covers Flash and Flash-Lite models with rate limits; free-tier content may be used to improve Google products.
The Free plan includes monthly API credits for Mistral models, with low default rate limits.
Only selected models are priced at zero; there is no general free trial.
Trial keys allow 1,000 API calls per month for evaluation, not for production.
Free trial with daily token limits; a verified payment method is required to activate the API.
10,000 Neurons per day are free on both Workers Free and Paid plans.
Free accounts get a small monthly credit for Inference Providers; PRO accounts get more.
BYOK router without token markup; its own Fusion models and selected free routes cost nothing.
Free serverless inference for development and prototyping with a developer account; not intended for production traffic.
Free models and promotional access may be time-limited.
A payment card must be on file even for zero-price models.
The $0 Portal plan includes :free models with standard rate limits.
Large catalog of :free routes without a card; shared capacity and per-model limits.
Models with the -free suffix cost nothing for a limited time; prompts may be used to improve the model.
Free software to use these models
Agents, IDEs, and local runners that plug into free APIs.
Self-improving agent that learns skills from experience and keeps cross-session memory; runs in the CLI, a desktop app, Telegram, Discord, Slack and WhatsApp.
Personal AI assistant (formerly Clawdbot/Moltbot) that runs on your own machine and acts through WhatsApp, Telegram, Discord, Slack, iMessage and 20+ channels.
Open-source terminal coding agent with a TUI, desktop app and IDE integration; plan/build agents, LSP support and any model provider.
Google's open-source terminal agent: coding, file and shell tools, web search grounding, MCP servers and a large context window.
Free AI credits
Free API tiers plus startup and student programs.
Google account and an AI Studio API key; free-tier content may be used to improve Google products
OpenRouter account; applies to :free model variants
GroqCloud account
Organization ID from an Activate Provider (VC, accelerator or angel); pre-Series B
AI-first funded startup with a public website
Verified student via GitHub Education
FAQ
Are there free LLM APIs?
Yes. As of October 24, 2026 we found 246 models with free API access across 16 providers. These are models with zero token prices, a developer free tier, or a free quota.
Which free API model is the strongest right now?
By the Artificial Analysis Intelligence Index, DeepSeek V4.1 Flash (45.1) currently leads — it is free at OrcaRouter, NVIDIA Build, OpenCode Zen. The ranking updates with every catalog refresh.
Do I need a credit card?
Not always. For example, these work without a card: OpenRouter, Groq, Google AI Studio, Cohere, Hugging Face, NVIDIA Build. Cerebras and Vercel AI Gateway require a card even for free models.
How often is the data updated?
The catalog polls provider APIs every four hours. New and removed free models appear in the New models section and the RSS feed.
Can I use free models in Cursor, Cline, or OpenCode?
Yes. Nearly every provider here is OpenAI-compatible: set the provider's base URL, your key, and the model ID from the model card. Compatible apps are listed in the Free software section.
The bot sends fresh free models and AI deals.