AP
Agent Provider Depot
Opinionated picks for agents
OpenAPI

Free / Hosted open-weight model inference

Free Hosted open-weight model inference for AI agents

23 row(s) whose own record lists this job. Updated 2026-10-26 (newest row asOf). Free rows never change a Depot Pick or a score.

Run it free (23)

  • Qwen3-0.6B-Base · open_weights · oss · Apache-2.0

    Downloadable Qwen3 0.6B base weights. This row is this checkpoint only, not every Qwen model.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE file fetched 2026-10-03 is Apache License 2.0. Weights are the model repo, not this license URL. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.

  • DeepSeek-V3.2 weights · open_weights · oss · MIT

    Downloadable DeepSeek-V3.2 weights from the Hugging Face repo whose LICENSE file is MIT.

    Limits: none stored.

    Source · asOf 2026-10-25 · This is DeepSeek-V3.2, not DeepSeek-V3. V3 used a separate LICENSE-MODEL and is not indexed here. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License'.

  • Gemma models under the Gemma Terms of Use · open_weights · free · Gemma Terms of Use

    Gemma models listed in the Appendix of the Gemma Terms of Use page (for example Gemma 1, 1.1, 2, 3 and 3n, FunctionGemma, EmbeddingGemma, PaliGemma, ShieldGemma, CodeGemma, RecurrentGemma, T5Gemma, VaultGemma and TranslateGemma), usable under that license with its Section 3.2 use restrictions. Gemma 4 is not covered by these terms.

    Limits: none stored.

    Source · asOf 2026-10-26 · Terms page fetched twice 2026-10-24 (identical text; 'Last modified: April 1, 2026', footer 'Last updated 2026-04-01 UTC'): 'The terms below apply to Gemma models listed in the Appendix at bottom of this page.' and 'For Gemma 4 terms, see the Gemma 4 license'. That link points to https://ai.google.dev/gemma/apache_2, a page titled 'Apache License 2.0' (fetched twice 2026-10-24); Gemma 4 is not indexed in this row. Section 3.2: 'You must not use any of the Gemma Services: for the restricted uses set forth in the Gemma Prohibited Use Policy'. The page now also says 'This documentation is deprecated. Please visit the new documentation at gemma.ai'; the terms are still served at this URL (HTTP 200, no redirect). Download path is https://ai.google.dev/gemma/docs/get_started: 'You can download official Google Gemma model variants and community-created variants from Kaggle Models and Hugging Face'. Re-checked 2026-10-26 (v0.12.131): stored quotes still match. https://ai.google.dev/gemma/terms, https://ai.google.dev/gemma/apache_2 and https://ai.google.dev/gemma/docs/get_started were each fetched twice (~10 s apart, plain curl, no login, following redirects): HTTP 200, no redirect, HTML differs only inside inline scripts, tag-stripped text identical; the terms page still reads 'Last modified: April 1, 2026' and 'Last updated 2026-04-01 UTC'. Every quote above string-matched the whitespace-normalized text; license and values unchanged (Depot data decision to re-date only, approvalRef 'Ethan delegation 2026-10-21 19:41 ET t55u', decidedBy Agent Depo).

  • Ollama · local_runtime · oss · MIT

    Local model runner and OpenAI-compatible server. You still supply weights and your own hardware.

    Limits: none stored.

    Source · asOf 2026-10-25 · Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): the GitHub blob page answered HTTP 200 both times (page chrome differs between fetches), so the raw file https://raw.githubusercontent.com/ollama/ollama/main/LICENSE was also fetched twice (HTTP 200, byte-identical): 'MIT License' / 'Copyright (c) Ollama'. License unchanged.

  • llama.cpp · local_runtime · oss · MIT

    C/C++ GGUF inference CLI and server. Weights are not included.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE fetched 2026-10-03, copyright 2023-2026 The ggml authors. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): the GitHub blob page answered HTTP 200 both times (page chrome differs between fetches), so the raw file https://raw.githubusercontent.com/ggml-org/llama.cpp/master/LICENSE was also fetched twice (HTTP 200, byte-identical): 'MIT License' / 'Copyright (c) 2023-2026 The ggml authors'. License unchanged.

  • vLLM · local_runtime · oss · Apache-2.0

    Self-hosted GPU inference server with an OpenAI-compatible API. GPU time is your own.

    Limits: none stored.

    Source · asOf 2026-10-25 · Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): the GitHub blob page answered HTTP 200 both times (page chrome differs between fetches), so the raw file https://raw.githubusercontent.com/vllm-project/vllm/main/LICENSE was also fetched twice (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'. License unchanged.

  • Groq Free Plan chat models · free_inference · free

    Organization-level Free Plan rate limits for the chat and classifier model ids in the page payload key freeRows. Not the Developer plan table.

    Limits: scope: organization · models: [object Object]

    Source · asOf 2026-10-24 · Rate-limits page fetched twice 2026-10-24 about 10 s apart (identical HTML; the page shows no last-updated date). Parsed from the HTML payload key freeRows (the 'Free Plan Limits' tab), which is separate from devRows (Developer plan, not stored). K suffixes expanded (1K=1000, 2K=2000, 14.4K=14400). The page says: 'The following is a high level summary and there may be exceptions to these limits.' and 'You can view the current, exact rate limits for your organization on the limits page in your account settings.' 'Rate limits apply at the organization level, not individual users.' 'Cached tokens do not count towards your rate limits.' The page also says 'some organizations are also subject to separate per-minute limits on input tokens (ITPM) and output tokens (OTPM)'; no ITPM/OTPM values are published, so none are stored. Change on 2026-10-24: freeRows now reads 'openai/gpt-oss-safeguard-20b 3 1K 2K 200K' (RPM 3, TPM 2K); before 0.12.98 this row stored RPM 30 and TPM 8000 for it. The other five model ids and their values are unchanged. No Llama chat model is in freeRows.

  • Hugging Face Transformers · dev_tool · oss · Apache-2.0

    Model loading and training library. Weights keep their own licenses.

    Limits: none stored.

    Source · asOf 2026-10-25 · Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): GitHub blob page HTTP 200, no redirect (page chrome differs between fetches); raw LICENSE fetched twice too, HTTP 200, byte-identical: 'Copyright 2018- The Hugging Face team. All rights reserved.' / 'Apache License Version 2.0, January 2004'. License unchanged.

  • Qwen2.5-Coder-7B-Instruct · open_weights · oss · Apache-2.0

    Downloadable Qwen2.5-Coder 7B Instruct weights. This checkpoint only.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE file fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.

  • Qwen3-8B · open_weights · oss · Apache-2.0

    Downloadable Qwen3-8B weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE file fetched 2026-10-03 is Apache License 2.0. Not a claim about every Qwen3 checkpoint. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.

  • Phi-4 · open_weights · oss · MIT

    Downloadable Microsoft Phi-4 weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE file fetched 2026-10-03 is the MIT License. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License'.

  • gpt-oss-20b · open_weights · oss · Apache-2.0

    Downloadable OpenAI gpt-oss-20b weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE file fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.

  • DeepSeek-R1 weights · open_weights · oss · MIT

    Downloadable DeepSeek-R1 weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE file fetched 2026-10-03 is the MIT License. This is DeepSeek-R1, not DeepSeek-V3. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License'.

  • SmolLM2-1.7B-Instruct · open_weights · oss · Apache-2.0

    Downloadable SmolLM2 1.7B Instruct weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · Model card front matter fetched 2026-10-03 says license: apache-2.0. A separate LICENSE file was not in the repo (404). README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice).

  • OLMo-2-1124-7B-Instruct · open_weights · oss · Apache-2.0

    Downloadable Allen Institute OLMo-2 7B Instruct weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · Model card front matter fetched 2026-10-03 says license: apache-2.0. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice).

  • Mistral-7B-Instruct-v0.3 · open_weights · oss · Apache-2.0

    Downloadable Mistral-7B-Instruct-v0.3 weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · Model card front matter fetched 2026-10-03 says license: apache-2.0. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice).

  • Qwen2.5-VL-7B-Instruct · open_weights · oss · Apache-2.0

    Downloadable Qwen2.5-VL 7B Instruct weights for image-text tasks.

    Limits: none stored.

    Source · asOf 2026-10-25 · Model card front matter fetched 2026-10-03 says license: apache-2.0. The 3B checkpoint uses a different Qwen Research LICENSE and is not this row. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE 404 (twice). The 3B README fetched the same day says 'license_name: qwen-research'.

  • GLM-4-9B-Chat · open_weights · free · glm-4-9b License

    Downloadable GLM-4-9B-Chat weights under the glm-4-9b license. Academic use is stated as free. Commercial use requires registration.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE fetched 2026-10-03 grants royalty-free academic research and says commercial use requires registration at open.bigmodel.cn, after which commercial use is described as free. Not Apache. Military and illegal uses are prohibited in the same text. Re-fetched twice 2026-10-25: https://huggingface.co/THUDM/glm-4-9b-chat/raw/main/LICENSE now answers HTTP 307 to /zai-org/glm-4-9b-chat/raw/main/LICENSE (HTTP 200, byte-identical), so sourceUrl moved to the redirect target. Text still says 'The glm-4-9b License', 'For users who wish to use the models for commercial purposes, please do so [here](https://open.bigmodel.cn/mla/form)' and 'Registered users are free to use this model for commercial activities'.

  • Granite-3.1-8B-Instruct · open_weights · oss · Apache-2.0

    Downloadable IBM Granite 3.1 8B Instruct weights.

    Limits: none stored.

    Source · asOf 2026-10-25 · Model card fetched 2026-10-03 says license: apache-2.0 and links the Apache 2.0 text. A separate LICENSE file was 404. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0' and '- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)'; raw/main/LICENSE still 404 (twice).

  • MLX · local_runtime · oss · MIT

    Apple's open-source array framework for on-device model inference.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE fetched 2026-10-03 is MIT, copyright 2023 Apple Inc. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'MIT License' / 'Copyright © 2023 Apple Inc.'. License unchanged.

  • SGLang · local_runtime · oss · Apache-2.0

    Open-source serving runtime for LLMs.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE fetched 2026-10-03 is Apache License 2.0. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'Apache License Version 2.0, January 2004'. License unchanged.

  • llamafile · local_runtime · oss · Apache-2.0

    Mozilla's open-source single-file local LLM runtime.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE fetched 2026-10-03 is Apache License 2.0, copyright 2023 Mozilla Foundation. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'The Apache 2.0 License' / 'Copyright 2023 Mozilla Foundation'. License unchanged.

  • exo · local_runtime · oss · Apache-2.0

    Open-source runtime for running models across your own machines.

    Limits: none stored.

    Source · asOf 2026-10-25 · LICENSE fetched 2026-10-03 is Apache License 2.0. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'Apache License Version 2.0, January 2004'. License unchanged.

Reference (docs, public datasets and benchmarks) (0)

None.