# tokengratis.id — data lengkap (llms-full.txt)

> Direktori free tier & free credits API LLM, di-aggregate otomatis dari sumber komunitas Indonesia. Aggregator, bukan verifier — tidak ada klaim "verified" di mana pun.

Terakhir di-update: 2026-07-31.
Field yang tidak muncul di sebuah entri berarti sumber datanya memang tidak menyediakan info itu secara terstruktur — bukan ditebak, bukan dikosongkan paksa jadi placeholder.

## Agnes AI

Modalitas: text, vision, image, video

| Model | Context | Modality | Rate Limit |
| --- | --- | --- | --- |
| agnes-1.5-flash | 256K | text + vision | 30 RPM |
| agnes-2.0-flash | 256K | text + vision | 30 RPM |
| agnes-image-2.0-flash | 4K | image | 30 RPM (1K) |
| agnes-image-2.1-flash | 4K | image | 30 RPM (1K) |
| agnes-video-v2.0 | 4K | video | 2 RPM |

Sumber:
- freellm.net (https://freellm.net) — synced 2026-07-31

## Aion Labs

URL: https://www.aionlabs.ai
Base URL: https://api.aionlabs.ai/v1

Permanent free tier, no credit card required. 15 RPM, 20K tokens/day. Specialized for roleplay and storytelling.

Modalitas: text

Gratis: 20K token/hari

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| Aion 2.0 | 128K | 32K | Text (roleplay) | 15 RPM, 20K TPD |
| Aion 2.5 | 128K | 32K | Text (roleplay) | 15 RPM, 20K TPD |
| Aion 3.0 | 128K | 32K | Text (roleplay, reasoning) | 15 RPM, 20K TPD |
| Aion 3.0 Mini | 128K | 32K | Text (roleplay, reasoning) | 15 RPM, 20K TPD |
| Aion-RP 1.0 (8B) | 32K | 32K | Text (roleplay) | 15 RPM, 20K TPD |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31

## Cerebras

URL: https://cloud.cerebras.ai/
Base URL: https://api.cerebras.ai/v1

Free tier with payment method required. Ultra-fast inference. 1M tokens/day cap. 64K context on free tier.

Modalitas: text, image

Gratis: 1M token/hari

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| gemma-4-31b | 131K (65K on free) | 32K (free) / 40K (paid) | Text + Image | 15 RPM, 30K TPM, 1M TPD |
| gpt-oss-120b | 131K (65K on free) | 32K (free) / 40K (paid) | Text | 5 RPM, 30K TPM, 1M TPD |
| Llama 3.1 70B | 131K | - | text | - |
| zai-glm-4.7 (deprecated Aug 2026) | 131K (64K on free) | 40K | Text | 5 RPM, 30K TPM, 1M TPD |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31

## Chutes.ai

Modalitas: text

| Model | Context | Modality | Rate Limit |
| --- | --- | --- | --- |
| DeepSeek-R1 | 131K | text + reasoning | Community-powered, no hard cap |
| Llama 3.1 70B | 131K | text | Community-powered, no hard cap |

Sumber:
- freellm.net (https://freellm.net) — synced 2026-07-31

## Cloudflare Workers AI

URL: https://dash.cloudflare.com/profile/api-tokens
Base URL: https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run

10,000 Neurons/day free. 50+ models available on free tier.

Modalitas: text, code, embeddings

Gratis: 10,000 Neurons/hari

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| @cf/meta/llama-4-scout-17b-16e-instruct | Up to 10M | Shared w/ context | Multimodal | 10K neurons/day (shared) |
| @cf/moonshotai/kimi-k2.7-code | 262K | Shared w/ context | Text (code) | 10K neurons/day (shared) |
| @cf/google/gemma-4-26b-a4b-it | 256K | Shared w/ context | Text | 10K neurons/day (shared) |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | 131K | Shared w/ context | Text | 10K neurons/day (shared) |
| @cf/zhipuai/glm-4.7-flash | 131K | Shared w/ context | Text | 10K neurons/day (shared) |
| @cf/mistralai/mistral-small-3.1-24b-instruct | 128K | Shared w/ context | Text | 10K neurons/day (shared) |
| @cf/openai/gpt-oss-120b | 128K | Shared w/ context | Text | 10K neurons/day (shared) |
| Mistral 7B | 33K | - | text | - |
| Qwen 1.5 7B | 33K | - | text | - |
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 32K | Shared w/ context | Text (reasoning) | 10K neurons/day (shared) |
| @cf/aisingapore/gemma-sea-lion-v4-27b-it | 8K | 128K | - | 10,000 neurons/day |
| @cf/baai/bge-base-en-v1.5 | 8K | - | - | - |
| @cf/baai/bge-large-en-v1.5 | 8K | - | - | - |
| @cf/baai/bge-m3 | 8K | 1K | - | - |
| @cf/baai/bge-small-en-v1.5 | 8K | - | - | - |
| @cf/google/gemma-2b-it-lora | 8K | - | - | - |
| @cf/google/gemma-7b-it-lora | 8K | - | - | - |
| @cf/ibm-granite/granite-4.0-h-micro | 8K | 131K | - | 10,000 neurons/day |
| @cf/meta-llama/llama-2-7b-chat-hf-lora | 8K | - | - | - |
| @cf/meta/llama-3.1-8b-instruct-fp8 | 8K | 32K | - | 10,000 neurons/day |
| @cf/meta/llama-3.2-1b-instruct | 8K | 60K | - | 10,000 neurons/day |
| @cf/meta/llama-3.2-3b-instruct | 8K | 80K | - | 10,000 neurons/day |
| @cf/meta/llama-guard-3-8b | 8K | - | - | 10,000 neurons/day |
| @cf/mistral/mistral-7b-instruct-v0.2-lora | 8K | - | - | 10,000 neurons/day |
| @cf/moondream/moondream3.1-9B-A2B | 8K | - | - | - |
| @cf/moonshotai/kimi-k2.6 | 8K | - | - | 10,000 neurons/day |
| @cf/nvidia/nemotron-3-120b-a12b | 8K | 256K | - | 10,000 neurons/day |
| @cf/openai/gpt-oss-20b | 8K | 16K | - | 10,000 neurons/day |
| @cf/qwen/qwen2.5-coder-32b-instruct | 8K | 32K | - | 10,000 neurons/day |
| @cf/qwen/qwen3-30b-a3b-fp8 | 8K | - | - | 10,000 neurons/day |
| @cf/qwen/qwq-32b | 8K | 24K | - | - |
| @cf/zai-org/glm-5.2 | 8K | 256K | - | 10,000 neurons/day |
| @cf/google/embeddinggemma-300m | - | - | embedding | - |
| @cf/pfnet/plamo-embedding-1b | - | - | embedding | - |
| @cf/qwen/qwen3-embedding-0.6b | - | - | embedding | - |
| Gemma 2B Instruct (LoRA) | - | - | - | 10,000 neurons/day |
| Gemma 7B Instruct (LoRA) | - | - | - | 10,000 neurons/day |
| Llama 2 7B Chat (LoRA) | - | - | - | 10,000 neurons/day |
| Llama 3.2 11B Vision Instruct | - | - | - | 10,000 neurons/day |
| Llama 3.3 70B Instruct (FP8) | - | - | - | 10,000 neurons/day |
| Llama 4 Scout Instruct | - | - | - | 10,000 neurons/day |
| Qwen QwQ 32B | - | - | - | 10,000 neurons/day |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31
- models.dev (https://models.dev) — synced 2026-07-31

## Cohere

URL: https://dashboard.cohere.com/api-keys
Base URL: https://api.cohere.com/v2

Free "Trial" API key, no credit card. 1,000 API calls/month. Non-commercial use only.

Modalitas: text, image

Gratis: 1,000 calls/bln

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| Command A+ (218B) | 436K | 64K | Text + Image | 20 RPM |
| Command A (111B) | 288K | 8K | Text | 20 RPM |
| Command A Reasoning | 288K | ~4K | Text (reasoning) | 20 RPM |
| Aya Expanse 32B | 128K | ~4K | Text | 20 RPM |
| Command A Vision | 128K | ~4K | Text + Image | 20 RPM |
| Command R+ | 128K | 4K | Text | 20 RPM |
| Command R7B | 128K | 4K | Text | 20 RPM |
| Command R7B Arabic | 128K | ~4K | Text | 20 RPM |
| Aya Vision 32B | 16K | ~4K | Text + Image | 20 RPM |
| Command A Translate | ~9K | ~4K | Text | 20 RPM |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31

## GitHub Models

URL: https://github.com/marketplace/models
Base URL: https://models.github.ai/inference

Free prototyping for all GitHub users. 45+ models. Per-request limits (8K in / 4K out).

Modalitas: text, vision, image

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| gpt-4.1 | 1M | 32K | Text | 10 RPM, 50 RPD |
| gpt-4.1-mini | 1M | 32K | Text | 15 RPM, 150 RPD |
| Llama-4-Scout-17B-16E-Instruct | 512K | ~4K | Text + Vision | 15 RPM, 150 RPD |
| AI21 Jamba 1.5 Large | 256K | - | text + reasoning | - |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | 256K | ~4K | Text + Vision | 10 RPM, 50 RPD |
| gpt-5 | 200K | 32K | Text | 10 RPM, 50 RPD |
| o4-mini | 200K | 100K | Text (reasoning) | 10 RPM, 50 RPD |
| Llama-3.3-70B-Instruct | 131K | ~4K | Text | 15 RPM, 150 RPD |
| Mistral Large (24.11) | 131K | - | text + image + reasoning | - |
| Phi-4 | 131K | - | text + reasoning | - |
| gpt-4o | 128K | 16K | Text + Vision | 10 RPM, 50 RPD |
| Mistral-Small-3.1 | 128K | ~4K | Text + Vision | 15 RPM, 150 RPD |
| DeepSeek-R1 | 64K | 8K | Text (reasoning) | 15 RPM, 150 RPD |

35 more models

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31

## Glhf.chat

Modalitas: text

| Model | Context | Modality | Rate Limit |
| --- | --- | --- | --- |
| Llama 3.1 70B | 131K | text | Unlimited for free models |
| Mixtral 8x7B | 33K | text | Unlimited for free models |

Sumber:
- freellm.net (https://freellm.net) — synced 2026-07-31

## Google Gemini

URL: https://aistudio.google.com/app/apikey
Base URL: https://generativelanguage.googleapis.com/v1beta

Free tier unavailable in EU/UK/Switzerland. Free-tier prompts may be used by Google to improve products.

Modalitas: text, vision, image, audio, video

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| Gemini 2.5 Flash | 1M | 65K | Text + Image + Audio + Video | 15 RPM, 1,500 RPD |
| Gemini 2.5 Flash-Lite | 1M | 65K | Text + Image + Audio + Video | 30 RPM, 1,500 RPD |
| Gemini 2.5 Pro | 1M | 65K | Text + Image + Audio + Video | 5 RPM, 50 RPD |
| Gemini 3 Flash (Preview) | 1.0M | - | text | Preview limits |
| Gemini 3.1 Flash-Lite | 1M | 65K | Text + Image + Audio + Video | 30 RPM, 1,500 RPD |
| Gemini 3.5 Flash | 1M | 65K | Text + Image + Audio + Video | 15 RPM, 1,500 RPD |
| Gemini 3.5 Flash-Lite | 1M | 65K | Text + Image + Audio + Video | 30 RPM, 1,500 RPD |
| Gemini 3.6 Flash | 1M | 65K | Text + Image + Audio + Video | 15 RPM, 1,500 RPD |
| Gemini Flash Latest | 1.0M | 64K | vision + audio + reasoning | - |
| Gemini Flash-Lite Latest | 1.0M | 64K | vision + audio + reasoning | - |
| Gemma 4 26B A4B IT | 262K | - | vision + reasoning | - |
| Gemma 4 31B IT | 262K | - | vision + reasoning | - |
| gemini-robotics-er-1.6-preview | 131K | 64K | - | 250,000 tokens/minute, 20 requests/day, 5 requests/minute |
| Gemini 2.5 Flash TTS | - | - | - | 10,000 tokens/minute, 10 requests/day, 3 requests/minute |
| Gemini 3.1 Flash TTS | - | - | - | 10,000 tokens/minute, 10 requests/day, 3 requests/minute |
| Gemini Robotics-ER 1.5 | - | - | - | 250,000 tokens/minute, 20 requests/day, 10 requests/minute |
| Gemma 3 12B Instruct | - | - | - | 15,000 tokens/minute, 14,400 requests/day, 30 requests/minute |
| Gemma 3 1B Instruct | - | - | - | 15,000 tokens/minute, 14,400 requests/day, 30 requests/minute |
| Gemma 3 27B Instruct | - | - | - | 15,000 tokens/minute, 14,400 requests/day, 30 requests/minute |
| Gemma 3 4B Instruct | - | - | - | 15,000 tokens/minute, 14,400 requests/day, 30 requests/minute |
| Gemma 4 26B A4B Instruct | - | - | - | 16,000 tokens/minute, 14,400 requests/day, 30 requests/minute |
| Gemma 4 31B Instruct | - | - | - | 16,000 tokens/minute, 14,400 requests/day, 30 requests/minute |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31
- models.dev (https://models.dev) — synced 2026-07-31

## Groq

URL: https://console.groq.com/keys
Base URL: https://api.groq.com/openai/v1

Free tier, no credit card. Ultra-fast LPU inference.

Modalitas: text

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| GPT-OSS Safeguard 20B | 131K | - | text + reasoning | 1,000 requests/day, 8,000 tokens/minute |
| groq/compound | 131K | 8K | Text | 30 RPM, 250 RPD |
| groq/compound-mini | 131K | 8K | Text | 30 RPM, 250 RPD |
| llama-3.1-8b-instant | 131K | 131K | Text | 30 RPM, 14,400 RPD |
| llama-3.3-70b-versatile | 131K | 32K | Text | 30 RPM, 1,000 RPD |
| Moonshot Kimi K2 | 131K | - | text | - |
| Moonshot Kimi K2 0905 | 131K | - | text | - |
| openai/gpt-oss-120b | 131K | 65K | Text | 30 RPM, 1,000 RPD |
| openai/gpt-oss-20b | 131K | 65K | Text | 30 RPM, 1,000 RPD |
| qwen/qwen3.6-27b | 131K | 16K | Text | 30 RPM, 1,000 RPD |
| allam-2-7b | 8K | - | - | 7,000 requests/day, 6,000 tokens/minute |
| meta-llama/llama-prompt-guard-2-22m | 8K | - | - | - |
| meta-llama/llama-prompt-guard-2-86m | 8K | - | - | - |
| canopylabs/orpheus-arabic-saudi | 4K | 50K | - | - |
| canopylabs/orpheus-v1-english | 4K | 50K | - | - |
| Llama 3.1 8B | - | - | - | 14,400 requests/day, 6,000 tokens/minute |
| Llama 3.3 70B | - | - | - | 1,000 requests/day, 12,000 tokens/minute |
| whisper-large-v3 | - | - | text | 20 RPM, 2,000 RPD |
| whisper-large-v3-turbo | - | - | text | 20 RPM, 2,000 RPD |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31
- models.dev (https://models.dev) — synced 2026-07-31

## Hugging Face

URL: https://huggingface.co/settings/tokens
Base URL: https://router.huggingface.co/v1

100K monthly Inference Provider credits for free users. Routes to Fireworks, Together, Hyperbolic, Nebius, Novita, DeepInfra and others. Thousands of models.

Modalitas: text

Gratis: 100K kredit/bln

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| Qwen2.5-7B-Instruct | 131K | ~4K | Text | Credit-metered |
| Meta-Llama-3.1-8B-Instruct | 128K | ~4K | Text | Credit-metered |
| Phi-3.5-mini-instruct | 128K | ~4K | Text | Credit-metered |
| Mistral-7B-Instruct-v0.3 | 32K | ~4K | Text | Credit-metered |
| Mixtral-8x7B-Instruct-v0.1 | 32K | ~4K | Text | Credit-metered |

thousands of community models

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-29
- freellm.net (https://freellm.net) — synced 2026-07-29
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-29

## Kilo Code

URL: https://kilo.ai
Base URL: https://api.kilo.ai/api/gateway

Free models with no credit card required. kilo-auto/free auto-router routes to minimax/minimax-m2.5:free (80%) and stepfun/step-3.5-flash:free (20%).

Modalitas: text, code

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| nvidia/nemotron-3-super-120b-a12b:free | 262K | 32K | Text | ~200 req/hr |
| x-ai/grok-code-fast-1:free | 256K | - | Text (code) | ~200 req/hr |
| minimax/minimax-m2.5:free | 196K | 8K | Text | ~200 req/hr |
| arcee-ai/trinity-large-thinking:free | 131K | - | Text (reasoning) | ~200 req/hr |
| bytedance-seed/dola-seed-2.0-pro:free | 131K | - | Text | ~200 req/hr |
| openrouter/free | Varies | Varies | Text | ~200 req/hr |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-29
- freellm.net (https://freellm.net) — synced 2026-07-29

## Kilo Gateway

URL: https://kilo.ai/docs/gateway

OpenAI-compatible gateway routing to various providers. Free models work without an account.

| Model | Rate Limit |
| --- | --- |
| Cohere North Mini Code | 200 requests/hour per IP, shared across all free models |
| Kilo Auto Free (Router) | 200 requests/hour per IP, shared across all free models |
| Ling 3.0 Flash | 200 requests/hour per IP, shared across all free models |
| NVIDIA Nemotron 3 Nano Omni 30B A3B (Reasoning) | 200 requests/hour per IP, shared across all free models |
| NVIDIA Nemotron 3 Super 120B A12B | 200 requests/hour per IP, shared across all free models |
| NVIDIA Nemotron 3 Ultra 550B A55B | 200 requests/hour per IP, shared across all free models |
| NVIDIA Nemotron 3.5 Content Safety | 200 requests/hour per IP, shared across all free models |
| OpenRouter Free Models (Router) | 200 requests/hour per IP, shared across all free models |
| Poolside Laguna S 2.1 | 200 requests/hour per IP, shared across all free models |
| Poolside Laguna XS 2.1 | 200 requests/hour per IP, shared across all free models |
| StepFun Step 3.7 Flash | 200 requests/hour per IP, shared across all free models |

Sumber:
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31

## LLM7.io

URL: https://token.llm7.io
Base URL: https://api.llm7.io/v1

Zero-friction API gateway. No registration needed for basic access. 30+ models. GDPR-compliant.

Modalitas: text, vision, audio, code

Gratis: Free, no signup

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| Gemini 3.1 Flash Lite | 1.0M | 64K | vision + audio + reasoning | - |
| Codestral (latest) | 256K | 4K | text | - |
| MiniMax-M2.7 | 205K | - | reasoning | - |
| GPT OSS 20B | 131K | - | reasoning | - |
| mistral-small-3.1-24b | 32K | - | Text | 30 RPM (120 with token) |
| deepseek-r1-0528 | - | - | Text (reasoning) | 30 RPM (120 with token) |
| deepseek-v3-0324 | - | - | Text | 30 RPM (120 with token) |
| gemini-2.5-flash-lite | - | - | Text + Vision | 30 RPM (120 with token) |
| gpt-4o-mini | - | - | Text + Vision | 30 RPM (120 with token) |
| qwen2.5-coder-32b | - | - | Text (code) | 30 RPM (120 with token) |

~24 more models

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- models.dev (https://models.dev) — synced 2026-07-31

## Mistral AI

URL: https://console.mistral.ai/api-keys
Base URL: https://api.mistral.ai/v1

Free "Experiment" plan, no credit card. ~1B tokens/month. Prompts may be used to improve models.

Modalitas: text, image, code

Gratis: ~1B token/bln

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| Codestral | 256K | 256K | Code | ~1 RPS, 500K TPM |
| Ministral 14B | 256K | 256K | Text | ~1 RPS, 500K TPM |
| Ministral 8B | 256K | 256K | Text | ~1 RPS, 500K TPM |
| Mistral Large 3 | 256K | 256K | Text | ~1 RPS, 500K TPM |
| Mistral Medium 3.5 (128B) | 256K | 256K | Text + Image + Code | ~1 RPS, 500K TPM |
| Mistral Small 4 | 256K | 256K | Text + Image + Code | ~1 RPS, 500K TPM |
| Ministral 3B | 128K | 128K | Text | ~1 RPS, 500K TPM |
| Mistral 7B | 33K | - | text | - |
| Mixtral 8x7B | 33K | - | text | - |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31

## ModelScope

URL: https://modelscope.cn/my/myaccesstoken
Base URL: https://api-inference.modelscope.cn/v1

Free API-Inference for registered users. Requires Alibaba Cloud account binding + real-name verification.

Modalitas: text, vision

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| GLM-5.2 | 1.0M | 128K | reasoning | - |
| MiniMax-M3 | 512K | - | vision + reasoning | - |
| Kimi K2.5 | 262K | 64K | vision + reasoning | - |
| MiniMax-M2.5-highspeed | 205K | - | reasoning | - |
| GLM-4.7-FlashX | 200K | - | reasoning | - |
| GLM-5.1 | 200K | - | reasoning | - |
| deepseek-ai/DeepSeek-V3.2 | 8K | - | - | - |
| deepseek-ai/DeepSeek-V4-Flash | 8K | - | - | - |
| deepseek-ai/DeepSeek-V4-Pro | 8K | - | - | - |
| LLM-Research/Llama-4-Maverick-17B-128E-Instruct | 8K | 4K | - | - |
| MedAIBase/AntAngelMed | 8K | - | - | - |
| meituan-longcat/LongCat-Flash-Lite | 8K | 320K | - | - |
| MiniMax/MiniMax-M1-80k | 8K | - | - | - |
| mistralai/Mistral-Large-Instruct-2407 | 8K | - | - | - |
| MusePublic/Qwen-Image-Edit | 8K | - | - | - |
| opencompass/CompassJudger-1-32B-Instruct | 8K | - | - | - |
| OpenGVLab/InternVL3_5-241B-A28B | 8K | - | - | - |
| PaddlePaddle/ERNIE-4.5-0.3B-PT | 8K | - | - | - |
| PaddlePaddle/ERNIE-4.5-21B-A3B-PT | 8K | - | - | - |
| PaddlePaddle/ERNIE-4.5-300B-A47B-PT | 8K | - | - | - |
| PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT | 8K | - | - | - |
| Qwen/Qwen3-14B | 8K | - | - | - |
| Qwen/Qwen3-235B-A22B | 8K | - | - | - |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 8K | - | - | - |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | 8K | - | reasoning | - |
| Qwen/Qwen3-30B-A3B | 8K | - | - | - |
| Qwen/Qwen3-30B-A3B-Thinking-2507 | 8K | - | reasoning | - |
| Qwen/Qwen3-32B | 8K | - | - | - |
| Qwen/Qwen3-4B | 8K | - | - | - |
| Qwen/Qwen3-8B | 8K | - | - | - |
| Qwen/Qwen3-Coder-30B-A3B-Instruct | 8K | - | - | - |
| Qwen/Qwen3-Next-80B-A3B-Instruct | 8K | - | - | - |
| Qwen/Qwen3-Next-80B-A3B-Thinking | 8K | - | reasoning | - |
| Qwen/Qwen3-VL-235B-A22B-Instruct | 8K | - | - | - |
| Qwen/Qwen3-VL-8B-Instruct | 8K | - | - | - |
| Qwen/Qwen3-VL-8B-Thinking | 8K | 32K | reasoning | - |
| Qwen/Qwen3.5-122B-A10B | 8K | - | - | - |
| Qwen/Qwen3.5-397B-A17B | 8K | - | - | - |
| Shanghai_AI_Laboratory/Intern-S1 | 8K | - | - | - |
| Shanghai_AI_Laboratory/Intern-S1-mini | 8K | - | - | - |
| Shanghai_AI_Laboratory/Intern-S2-Preview | 8K | - | - | - |
| stepfun-ai/Step-3.5-Flash | 8K | - | - | - |
| stepfun-ai/Step-3.7-Flash | 8K | - | - | - |
| Tencent-Hunyuan/Hy3 | 8K | - | - | - |
| XGenerationLab/XiYanSQL-QwenCoder-32B-2412 | 8K | - | - | - |
| XGenerationLab/XiYanSQL-QwenCoder-32B-2504 | 8K | - | - | - |
| Qwen/Qwen3.5-27B | - | - | Text | 2,000 RPD total; <=500 RPD/model (dynamic) |
| Qwen/Qwen3.5-35B-A3B | - | - | Text | 2,000 RPD total; <=500 RPD/model (dynamic) |

API-Inference-enabled models

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- models.dev (https://models.dev) — synced 2026-07-31

## NVIDIA NIM

URL: https://build.nvidia.com/explore/discover
Base URL: https://integrate.api.nvidia.com/v1

Free with NVIDIA Developer Program membership. 100+ models. Rate-limited (no daily token cap).

Modalitas: text, vision, image, audio, video, embeddings, reranking

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| deepseek-ai/deepseek-v4-flash | 1M | ~64K | Text | ~40 RPM |
| meta/llama-guard-4-12b | 1.0M | - | text + image | Up to 40 RPM |
| minimaxai/minimax-m3 | 1M | ~64K | Text | ~40 RPM |
| z-ai/glm-5.2 | 1.0M | - | text + reasoning | Up to 40 RPM |
| mistralai/mistral-medium-3.5-128b | 262K | 262K | Text | ~40 RPM |
| moonshotai/kimi-k2.6 | 262K | - | text + image + video + reasoning | Up to 40 RPM |
| nvidia/nemotron-3-super-120b-a12b | 262K | 262K | Text | ~40 RPM |
| nvidia/nemotron-3-ultra-550b-a55b | 262K | 262K | Text | ~40 RPM |
| poolside/laguna-xs-2.1 | 262K | - | text + reasoning | Up to 40 RPM |
| stepfun-ai/step-3.7-flash | 262K | - | text + image + video + reasoning | Up to 40 RPM |
| Inkling | 256K | - | vision + audio + reasoning | - |
| Nemotron 3 Nano Omni 30B A3B Reasoning | 256K | 64K | vision + audio + reasoning | - |
| 01-ai/yi-large | 131K | 4K | text | Up to 40 RPM |
| adept/fuyu-8b | 131K | - | text | Up to 40 RPM |
| ai21labs/jamba-1.5-large-instruct | 131K | - | text | Up to 40 RPM |
| aisingapore/sea-lion-7b-instruct | 131K | - | text | Up to 40 RPM |
| baai/bge-m3 | 131K | 1K | text | Up to 40 RPM |
| bigcode/starcoder2-15b | 131K | - | text | Up to 40 RPM |
| databricks/dbrx-instruct | 131K | - | text | Up to 40 RPM |
| deepseek-ai/deepseek-coder-6.7b-instruct | 131K | - | text | Up to 40 RPM |
| google/codegemma-1.1-7b | 131K | - | text | Up to 40 RPM |
| google/codegemma-7b | 131K | - | text | Up to 40 RPM |
| google/deplot | 131K | - | text | Up to 40 RPM |
| google/gemma-2b | 131K | - | text | Up to 40 RPM |
| google/recurrentgemma-2b | 131K | - | text | Up to 40 RPM |
| ibm/granite-3.0-3b-a800m-instruct | 131K | - | text | Up to 40 RPM |
| ibm/granite-3.0-8b-instruct | 131K | - | text | Up to 40 RPM |
| ibm/granite-34b-code-instruct | 131K | - | text | Up to 40 RPM |
| ibm/granite-8b-code-instruct | 131K | - | text | Up to 40 RPM |
| Llama 3.3 Nemotron Super 49B v1 | 131K | - | reasoning | - |
| meta/codellama-70b | 131K | - | text | Up to 40 RPM |
| meta/llama-3.1-70b-instruct | 131K | - | text | Up to 40 RPM |
| meta/llama-3.2-11b-vision-instruct | 131K | - | text + image | Up to 40 RPM |
| meta/llama-3.2-3b-instruct | 131K | - | text | Up to 40 RPM |
| meta/llama2-70b | 131K | - | text | Up to 40 RPM |
| microsoft/kosmos-2 | 131K | - | text | Up to 40 RPM |
| microsoft/phi-3-vision-128k-instruct | 131K | - | text | Up to 40 RPM |
| microsoft/phi-3.5-moe-instruct | 131K | 4K | text | Up to 40 RPM |
| mistralai/codestral-22b-instruct-v0.1 | 131K | - | text | Up to 40 RPM |
| mistralai/mistral-7b-instruct-v0.3 | 131K | - | text | Up to 40 RPM |
| mistralai/mixtral-8x22b-v0.1 | 131K | - | text | Up to 40 RPM |
| nv-mistralai/mistral-nemo-12b-instruct | 131K | 4K | text | Up to 40 RPM |
| nvidia/cosmos-reason2-8b | 131K | 16K | text + image + video + reasoning | Up to 40 RPM |
| nvidia/llama-3.1-nemotron-51b-instruct | 131K | - | text | Up to 40 RPM |
| nvidia/llama-3.1-nemotron-70b-instruct | 131K | 8K | text | Up to 40 RPM |
| nvidia/llama-3.3-nemotron-super-49b-v1.5 | 131K | - | text + reasoning | Up to 40 RPM |
| nvidia/llama3-chatqa-1.5-70b | 131K | - | text | Up to 40 RPM |
| nvidia/mistral-nemo-minitron-8b-8k-instruct | 131K | - | text | Up to 40 RPM |
| nvidia/nemotron-4-340b-instruct | 131K | - | text | Up to 40 RPM |
| nvidia/nemotron-4-340b-reward | 131K | - | text | Up to 40 RPM |
| nvidia/nemotron-nano-3-30b-a3b | 131K | - | text + reasoning | Up to 40 RPM |
| nvidia/nemotron-parse | 131K | - | text | Up to 40 RPM |
| nvidia/neva-22b | 131K | - | text | Up to 40 RPM |
| nvidia/nvclip | 131K | - | text | Up to 40 RPM |
| nvidia/riva-translate-4b-instruct | 131K | - | text | Up to 40 RPM |
| nvidia/vila | 131K | - | text | Up to 40 RPM |
| openai/gpt-oss-120b | 131K | 131K | Text | ~40 RPM |
| openai/gpt-oss-20b | 131K | 131K | Text | ~40 RPM |
| writer/palmyra-creative-122b | 131K | - | text | Up to 40 RPM |
| writer/palmyra-fin-70b-32k | 131K | - | text | Up to 40 RPM |
| writer/palmyra-med-70b | 131K | - | text | Up to 40 RPM |
| writer/palmyra-med-70b-32k | 131K | - | text | Up to 40 RPM |
| zyphra/zamba2-7b-instruct | 131K | - | text | Up to 40 RPM |
| deepseek-ai/deepseek-v4-pro | 128K | ~64K | Text | ~40 RPM |
| google/gemma-4-31b-it | 128K | 8K | Text | ~40 RPM |
| Llama 3.1 Nemotron Safety Guard 8B v3 | 128K | - | text | - |
| meta/llama-3.3-70b-instruct | 128K | 4K | Text | ~40 RPM |
| mistralai/mistral-large-2-instruct | 128K | 4K | Text | ~40 RPM |
| mistralai/mistral-nemotron | 128K | 8K | Text | ~40 RPM |
| Nemotron Mini 4B Instruct | 128K | 8K | text | - |
| Nemotron Nano 12B v2 VL | 128K | - | vision + reasoning | - |
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 128K | 4K | Text | ~40 RPM |
| nvidia/nemotron-3-nano-30b-a3b | 128K | 32K | Text | ~40 RPM |
| nvidia/nemotron-3.5-content-safety | 128K | 8K | text + image + reasoning | Up to 40 RPM |
| meta/llama-3.2-1b-instruct | 60K | - | text | Up to 40 RPM |
| google/diffusiongemma-26b-a4b-it | 8K | 128K | - | - |
| meta/llama-3.1-8b-instruct | 8K | 16K | - | - |
| meta/llama-3.2-90b-vision-instruct | 8K | - | - | - |
| mistralai/mistral-large-3-675b-instruct-2512 | 8K | - | - | - |
| nvidia/ising-calibration-1.5-31b | 8K | - | - | - |
| nvidia/llama-3.1-nemoguard-8b-content-safety | 8K | - | - | - |
| nvidia/llama-3.1-nemoguard-8b-topic-control | 8K | - | - | - |
| nvidia/llama-3.1-nemotron-nano-8b-v1 | 8K | 16K | - | - |
| nvidia/llama-3.1-nemotron-nano-vl-8b-v1 | 8K | 16K | - | - |
| nvidia/nvidia-nemotron-nano-9b-v2 | 8K | - | - | - |
| nvidia/riva-translate-4b-instruct-v1.1 | 8K | 4K | - | - |
| nvidia/riva-translate-4b-instruct-v2 | 8K | - | - | - |
| nvidia/embed-qa-4 | - | - | embedding | Up to 40 RPM |
| nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1 | - | - | embedding + rerank | Up to 40 RPM |
| nvidia/llama-3.2-nv-embedqa-1b-v1 | - | - | embedding | Up to 40 RPM |
| nvidia/llama-nemotron-embed-1b-v2 | - | - | embedding + text + image | Up to 40 RPM |
| nvidia/llama-nemotron-embed-vl-1b-v2 | 32K | 2K | embedding + text + image | Up to 40 RPM |
| nvidia/nemoretriever-parse | - | - | rerank | Up to 40 RPM |
| nvidia/nemotron-3-embed-1b | - | - | embedding | Up to 40 RPM |
| nvidia/nv-embed-v1 | 32K | 2K | embedding + text | Up to 40 RPM |
| nvidia/nv-embedcode-7b-v1 | 32K | 2K | embedding + text | Up to 40 RPM |
| nvidia/nv-embedqa-e5-v5 | - | - | embedding | Up to 40 RPM |
| nvidia/nv-embedqa-mistral-7b-v2 | - | - | embedding | Up to 40 RPM |
| snowflake/arctic-embed-l | - | - | embedding | Up to 40 RPM |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31
- models.dev (https://models.dev) — synced 2026-07-31

## Ollama Cloud

URL: https://ollama.com/settings/keys
Base URL: https://api.ollama.com

Free tier with qualitative usage limits. 400+ models from Ollama library. Not OpenAI SDK-compatible; uses Ollama API.

Modalitas: text, code

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| kimi-k2:1t-cloud | 262K | Model-dependent | Text | Session/weekly limits (unpublished) |
| deepseek-r1:cloud | 128K | Model-dependent | Text (reasoning) | Session/weekly limits (unpublished) |
| deepseek-v3.1:671b-cloud | 128K | Model-dependent | Text | Session/weekly limits (unpublished) |
| glm-4.6:cloud | 128K | Model-dependent | Text | Session/weekly limits (unpublished) |
| gpt-oss:120b-cloud | 128K | Model-dependent | Text | Session/weekly limits (unpublished) |
| qwen3-coder:480b-cloud | 128K | Model-dependent | Text (code) | Session/weekly limits (unpublished) |

30 more cloud models

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-29

## OpenCode Zen

URL: https://opencode.ai/docs/zen/

AI gateway with curated models.

Modalitas: text, vision, audio

| Model | Context | Max Output | Modality |
| --- | --- | --- | --- |
| DeepSeek V4 Flash | 1.0M | - | reasoning |
| Laguna S 2.1 | 1.0M | - | reasoning |
| MiMo-V2.5 | 1.0M | - | vision + audio + reasoning |
| Nemotron 3 Ultra 550B A55B | 1.0M | - | reasoning |
| North Mini Code | 256K | 64K | reasoning |
| ling-3.0-flash-free | 8K | - | - |
| big-pickle | 200K | 32K | - |
| Nemotron 3 Ultra Free | 1M | 128K | - |

Sumber:
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31
- models.dev (https://models.dev) — synced 2026-07-31

## OpenRouter

URL: https://openrouter.ai/settings/keys
Base URL: https://openrouter.ai/api/v1

~22 free models (marked with :free suffix). OpenAI SDK-compatible.

Modalitas: text, vision, image, audio, video, code

Gratis: ~22 model free

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| NVIDIA: Nemotron 3 Ultra (free) | 1M | 66K | Text | 200 req/day (free tier) |
| Google: Gemma 4 26B A4B  (free) | 262K | 33K | Text + Vision + Video | 20 RPM, 50 RPD |
| Google: Gemma 4 31B (free) | 262K | 33K | Text + Vision + Video | 20 RPM, 50 RPD |
| Ling-3.0-flash (free) | 262K | 33K | Text | 20 RPM, 50 RPD |
| NVIDIA: Nemotron 3 Super (free) | 262K | 262K | Text | 20 RPM, 50 RPD |
| Poolside: Laguna S 2.1 (free) | 262K | 33K | Text | 20 RPM, 50 RPD |
| Poolside: Laguna XS 2.1 (free) | 262K | 33K | Text | 20 RPM, 50 RPD |
| Cohere: North Mini Code (free) | 256K | 64K | Text | 20 RPM, 50 RPD |
| NVIDIA: Nemotron 3 Nano 30B A3B (free) | 256K | - | Text | 20 RPM, 50 RPD |
| NVIDIA: Nemotron 3 Nano Omni (free) | 256K | 66K | Text + Vision + Audio + Video | 200 req/day (free tier) |
| OpenAI: gpt-oss-20b (free) | 131K | 33K | Text | 20 RPM, 50 RPD |
| NVIDIA: Nemotron 3.5 Content Safety (free) | 128K | 8K | Text + Vision | 200 req/day (free tier) |
| NVIDIA: Nemotron Nano 12B 2 VL (free) | 128K | 128K | Text + Vision + Video | 20 RPM, 50 RPD |
| NVIDIA: Nemotron Nano 9B V2 (free) | 128K | - | Text | 20 RPM, 50 RPD |

Sumber:
- openrouter.ai/api/v1/models (https://openrouter.ai/api/v1/models) — synced 2026-07-31
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31
- cheahjs/free-llm-api-resources (https://github.com/cheahjs/free-llm-api-resources) — synced 2026-07-31

## OVHcloud AI Endpoints

URL: https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/
Base URL: https://oai.endpoints.kepler.ai.cloud.ovh.net/v1

Free anonymous tier (no API key, no signup): 2 RPM per IP per model. 20+ open-weight models hosted in EU. OpenAI SDK-compatible.

Modalitas: text, vision, code

Gratis: 2 RPM/IP

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| Qwen3-Coder-30B-A3B-Instruct | 262K | ~32K | Text (code) | 2 RPM (anonymous) |
| Meta-Llama-3_3-70B-Instruct | 131K | ~4K | Text | 2 RPM (anonymous) |
| Qwen3-32B | 131K | ~32K | Text | 2 RPM (anonymous) |
| Qwen3.5-397B-A17B | 131K | ~32K | Text | 2 RPM (anonymous) |
| Qwen3.5-9B | 131K | ~8K | Text | 2 RPM (anonymous) |
| Qwen3.6-27B | 131K | ~32K | Text | 2 RPM (anonymous) |
| gpt-oss-120b | 128K | ~32K | Text | 2 RPM (anonymous) |
| gpt-oss-20b | 128K | ~8K | Text | 2 RPM (anonymous) |
| Mistral-Nemo-Instruct-2407 | 128K | ~4K | Text | 2 RPM (anonymous) |
| Mistral-Small-3.2-24B-Instruct | 128K | ~4K | Text | 2 RPM (anonymous) |
| Qwen2.5-VL-72B-Instruct | 128K | ~8K | Text + Vision | 2 RPM (anonymous) |
| Mistral-7B-Instruct-v0.3 | 32K | ~4K | Text | 2 RPM (anonymous) |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31

## SambaNova

URL: https://cloud.sambanova.ai/apis
Base URL: https://api.sambanova.ai/v1

Free tier, no credit card. Ultra-fast RDU inference. 20 RPM, 200K tokens/day.

Modalitas: text, image, video

Gratis: 200K token/hari

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| DeepSeek-V3.1 | 128K | ~8K | Text | 20 RPM, 20 RPD, 200K TPD |
| DeepSeek-V3.2 (Preview) | 128K | ~8K | Text | 20 RPM, 20 RPD, 200K TPD |
| gemma-4-31B-it (Preview) | 128K | ~128K | Text + Image + Video | 20 RPM, 20 RPD, 200K TPD |
| gpt-oss-120b | 128K | ~128K | Text | 20 RPM, 20 RPD, 200K TPD |
| Meta-Llama-3.3-70B-Instruct | 128K | ~3K | Text | 20 RPM, 20 RPD, 200K TPD |
| MiniMax-M2.7 | 128K | ~192K | Text | 20 RPM, 20 RPD, 200K TPD |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31

## SiliconFlow

URL: https://cloud.siliconflow.cn/account/ak
Base URL: https://api.siliconflow.cn/v1

Permanently free models, no credit card required. 200+ paid models also available.

Modalitas: text

Gratis: Free (permanen)

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | 131K | Configurable | Text (reasoning) | 30 RPM, 60K TPM |
| Qwen/Qwen3-8B | 131K | 131K | Text | 30 RPM, 60K TPM |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31

## Grok (xAI)

Modalitas: text

| Model | Context | Modality | Rate Limit |
| --- | --- | --- | --- |
| Grok-2 | 131K | text | $25/month free credits, resets monthly |
| Grok-2 Mini | 131K | text | $25/month free credits, resets monthly |

Sumber:
- freellm.net (https://freellm.net) — synced 2026-07-31

## Z AI (Zhipu AI)

URL: https://open.bigmodel.cn/usercenter/apikeys
Base URL: https://open.bigmodel.cn/api/paas/v4

Permanent free models, no credit card required.

Modalitas: text, image

Gratis: Free (permanen)

| Model | Context | Max Output | Modality | Rate Limit |
| --- | --- | --- | --- | --- |
| GLM-4.7-Flash | 200K | 128K | Text (reasoning) | 1 concurrent request |
| GLM-4.5-Air | 131K | - | reasoning | - |
| GLM-4.5-Flash | 128K | ~96K | Text (reasoning) | 1 concurrent request |
| GLM-4.6V-Flash | 128K | ~4K | Text + Image | 1 concurrent request |

Sumber:
- mnfst/awesome-free-llm-apis (https://github.com/mnfst/awesome-free-llm-apis) — synced 2026-07-31
- freellm.net (https://freellm.net) — synced 2026-07-31