---
title: "Free LLM API models: 6 at zero price, plus 3 free tiers"
description: "Which LLM APIs are free: 6 models listed at zero price by 4 providers and 3 free tiers that name models, with stated limits, check dates and sources."
url: https://broadrouter.com/llm-api-pricing/free/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Free LLM API models and free tiers

Updated 2026-11-14

6 models have a listed price of zero at 4 providers in our data (checked 2026-11-14), plus 3 provider free tiers that name specific models (Cerebras, Google Gemini API and Groq). Limits appear only where the provider states them. BroadRouter is BroadNet's site; BroadNet offers a $5 starting credit, not a free price.

**Three lists, kept apart:** models a provider prices at zero, provider free tiers and trial credits, and BroadNet's own starting credit. BroadRouter is BroadNet's site; BroadNet's offer is labelled as ours and is not in the first two lists.

Jump to: models at zero price · provider free tiers and credits · BroadNet's starting credit · how we decide.

## Which models have a listed API price of zero?

6 models at 4 providers: a standard-tier row with 0 input, 0 output and 0 cached input per 1M tokens, read from the provider's own pricing page. Free rows are not ranked against each other.

LLM API models listed at a price of zero
| Model | Provider | Limits the source states | Checked | Links |
| --- | --- | --- | --- | --- |
| [Command A+](https://broadrouter.com/llm-api-pricing/command-a-plus/) Cohere `command-a-plus-05-2026` | Cohere | Not stated on the pricing page | 2026-11-14 | [price page](https://broadrouter.com/llm-api-pricing/command-a-plus/) · [provider source](https://cohere.com/pricing) |
| [Apodex 1.1 Mini](https://broadrouter.com/llm-api-pricing/apodex-1.1-mini/) Apodex `apodex/apodex-1.1-mini` | Novita AI | Not stated on the pricing page | 2026-11-14 | [price page](https://broadrouter.com/llm-api-pricing/apodex-1.1-mini/) · [provider source](https://novita.ai/pricing) |
| [Ternary Bonsai 27B](https://broadrouter.com/llm-api-pricing/ternary-bonsai-27b/) Prism ML | Together AI | Not stated on the pricing page | 2026-11-14 | [price page](https://broadrouter.com/llm-api-pricing/ternary-bonsai-27b/) · [provider source](https://www.together.ai/pricing) |
| [GLM 4.7 Flash](https://broadrouter.com/llm-api-pricing/glm-4.7-flash/) Z.ai `GLM-4.7-Flash` | Z.ai | Not stated on the pricing page | 2026-11-14 | [price page](https://broadrouter.com/llm-api-pricing/glm-4.7-flash/) · [provider source](https://docs.z.ai/guides/overview/pricing) |
| [GLM-4.5-Flash](https://broadrouter.com/llm-api-pricing/glm-4.5-flash/) Z.ai `GLM-4.5-Flash` | Z.ai | Not stated on the pricing page | 2026-11-14 | [price page](https://broadrouter.com/llm-api-pricing/glm-4.5-flash/) · [provider source](https://docs.z.ai/guides/overview/pricing) |
| [GLM-4.6V-Flash](https://broadrouter.com/llm-api-pricing/glm-4.6v-flash/) Z.ai `GLM-4.6V-Flash` | Z.ai | Not stated on the pricing page | 2026-11-14 | [price page](https://broadrouter.com/llm-api-pricing/glm-4.6v-flash/) · [provider source](https://docs.z.ai/guides/overview/pricing) |

Together AI's own billing page says: ""Together AI doesn't currently offer free trials." A minimum credit purchase of 15 USD is required to use the platform." ([source](https://docs.together.ai/docs/billing), checked 2026-11-14). Its pricing page lists Ternary Bonsai 27B as free. Both are shown as we read them; check with Together AI before you build on it.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20the%20free%20LLM%20API%20models%20page&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Ffree%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## Which providers offer a free tier or trial credit?

5 providers in our [free-tier and rate-limit dataset](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) state free API access or a free credit. This is a separate list from the one above: a tier covers only the models its provider names, and the "Models it names" column shows those we also price. An empty cell means the tier names no model in our price data, not that it covers every model.

Provider free tiers and trial credits
| Provider | Offer as stated | Limits as stated | Models it names | Card needed | Free-tier data used for training | Checked |
| --- | --- | --- | --- | --- | --- | --- |
| Cerebras · $5 credit | 5 USD in Free Trial credits after adding a verified payment method; they expire 30 days after they are granted. ([source](https://inference-docs.cerebras.ai/support/rate-limits)) | 5 requests a minute and 30,000 tokens a minute for `gpt-oss-120b` (Free Trial) ([source](https://inference-docs.cerebras.ai/support/rate-limits)) Free Trial: 30K uncached TPM (90K total TPM) and 1M tokens a day. qwen-3.8-27b: 300 RPM. | [OpenAI GPT OSS 120B](https://broadrouter.com/llm-api-pricing/gpt-oss-120b/) | yes | no | 2026-11-14 |
| Google Gemini API | Free tier: many models show "Free of charge" on the pricing page, including Gemini 4 Hydrogen, Gemini 3.8 Flash and Gemini 3.5 Flash-Lite. ([source](https://aistudio.google.com/docs/pricing)) | Per-model free-tier limits are shown only in Google AI Studio: "Rate limits depend on a variety of factors (such as your usage tier) and can be viewed in Google AI Studio." The one model with published free-tier numbers is Gemini Decision 1 (200 RPM, 50,000 TPM, 10,000 RPD). | [Gemini 3.5 Flash-Lite](https://broadrouter.com/llm-api-pricing/gemini-3.5-flash-lite/), [Gemini 3.8 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.8-flash/), [Gemini 4 Hydrogen](https://broadrouter.com/llm-api-pricing/gemini-4-hydrogen/) | not stated | yes | 2026-11-14 |
| Groq | Free plan with per-model limits; the Developer plan raises them. ([source](https://console.groq.com/docs/rate-limits)) | 30 requests a minute, 8,000 tokens a minute and 1,000 requests a day for `openai/gpt-oss-120b` (Free plan) ([source](https://console.groq.com/docs/rate-limits)) Free plan, also 200,000 tokens a day. Whisper models: 20 RPM and 2,000 requests a day. | [OpenAI GPT OSS 120B](https://broadrouter.com/llm-api-pricing/gpt-oss-120b/) | not stated | no | 2026-11-14 |
| Cohere | Trial (evaluation) keys are "free but limited in usage": 1,000 API calls a month. ([source](https://docs.cohere.com/docs/rate-limits)) | 20 requests a minute for `Command A (Chat)` (Trial key) ([source](https://docs.cohere.com/docs/rate-limits)) Trial: 20 requests a minute on Chat models and 1,000 calls a month; production keys 500 RPM on Command A. | none in our price data | not stated | not stated | 2026-11-14 |
| OpenRouter | Free model variants (IDs ending in :free). "All new users receive a small free allowance to test out OpenRouter." ([source](https://openrouter.ai/docs/api-reference/limits)) | 20 requests a minute and 50 requests a day for `:free models` (Free models, under 10 credits purchased) ([source](https://openrouter.ai/docs/api-reference/limits)) 20 RPM; 50 requests a day with under 10 credits purchased, 1,000 a day with at least 10. | none in our price data | not stated | not stated | 2026-11-14 |

No free API access, as the provider states it: Mistral AI (Free mode includes a monthly usage budget for trying Vibe and Studio, but "It doesn't include API access." Creating API keys requires billing activation and pay as you go) and Together AI ("Together AI doesn't currently offer free trials." A minimum credit purchase of 15 USD is required to use the platform). No free tier or credit stated on the pages we read: OpenAI, Anthropic, Fireworks AI, DeepInfra, DeepSeek and xAI. Their paid entry tiers and default limits are in the [dataset](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/), with CSV and JSON.

## BroadNet's own offer: a starting credit

BroadRouter is BroadNet's site, so this is our own offer, listed apart from the providers above. It is a starting credit, not a free price or a free tier.

-   New BroadNet Inference accounts start with **$5 of credit**, no card needed ([pricing page](https://inference.broadnet.ai/pricing?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-free&utm_content=free-broadnet), checked 2026-11-14).
-   The credit can be spent on [BroadNet Gemma 4 VL 26B](https://broadrouter.com/models/gemma-4-vl-26b/), [BroadNet Transcribe Arabic](https://broadrouter.com/models/cohere-transcribe-arabic/) and [BroadNet Transcribe](https://broadrouter.com/models/cohere-transcribe/) at their listed prices.
-   [DeepSeek V4.1 Flash](https://broadrouter.com/models/deepseek-v4.1-flash/), [GLM 5.3](https://broadrouter.com/models/glm-5.3/) and [Qwen3.8 27B](https://broadrouter.com/models/qwen3.8-27b/) are for paid accounts only and need a top-up first (`paid_only` in [pricing.json](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-free&utm_content=free-broadnet), synced 2026-11-14).
-   Pay-as-you-go keys: 30 requests a minute and 4 requests in flight ([docs](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-free&utm_content=free-broadnet), checked 2026-11-14).

More on how the credit works: [what the starting credit covers](https://broadrouter.com/blog/free-llm-api-credit/) and [BroadNet Inference pricing](https://broadrouter.com/pricing/).

## How we decide what counts as free

-   **Zero-price rows:** a standard-tier row with 0 input, 0 output and 0 (or no) cached price, copied from the provider's own pricing page with a verbatim quote. Batch, flex and other tiers do not count.
-   **Free tiers:** read from each provider's own docs on the date shown. A tier is linked to a model only when its row names that model, by its model ID or in the offer text. A general free tier is not shown as covering models it does not name.
-   **Limits:** shown only when the provider's page states them, in its own units. We do not estimate missing limits or convert per-second or concurrency limits into requests a minute.
-   **Freshness:** free offers change without notice. Each row carries the date we read it; check the provider's page before you build on a free offer.

[All LLM API prices by model](https://broadrouter.com/llm-api-pricing/) · [Free tiers and rate limits (open data)](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) · [Pricing methodology](https://broadrouter.com/llm-api-pricing/methodology/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### Which LLM APIs are free?

In our data (checked 2026-11-14), 6 models are listed at 0 input and 0 output per 1M tokens on a standard tier: Command A+ (Cohere), Apodex 1.1 Mini (Novita AI), Ternary Bonsai 27B (Together AI) and GLM 4.7 Flash, GLM-4.5-Flash and GLM-4.6V-Flash (Z.ai). Separately, 5 providers in our [free-tier dataset](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) state free API access or a free credit; 3 of those name specific models in our price data. A free tier covers only what its provider names.

### Is there a free DeepSeek, GLM or Qwen API?

DeepSeek: no provider in our data lists a DeepSeek model at a price of zero (26 DeepSeek models priced, checked 2026-11-14). DeepSeek's own docs: no free tier or free credit mentioned on the rate-limit page (checked 2026-11-14). GLM: yes. Z.ai lists [GLM 4.7 Flash](https://broadrouter.com/llm-api-pricing/glm-4.7-flash/), [GLM-4.5-Flash](https://broadrouter.com/llm-api-pricing/glm-4.5-flash/) and [GLM-4.6V-Flash](https://broadrouter.com/llm-api-pricing/glm-4.6v-flash/) at 0 input and 0 output (checked 2026-11-14). Qwen: no provider in our data lists a Qwen model at a price of zero (61 Qwen models priced, checked 2026-11-14). BroadNet Inference serves DeepSeek V4.1 Flash, GLM 5.3 and Qwen3.8 27B to paid accounts only, so its starting credit does not cover them (rate card synced 2026-11-14).

### Are free tiers rate-limited?

Where the provider states it, yes. Cerebras: 5 requests a minute and 30,000 tokens a minute for `gpt-oss-120b` (Free Trial). Groq: 30 requests a minute, 8,000 tokens a minute and 1,000 requests a day for `openai/gpt-oss-120b` (Free plan). Cohere: 20 requests a minute for `Command A (Chat)` (Trial key). OpenRouter: 20 requests a minute and 50 requests a day for `:free models` (Free models, under 10 credits purchased). Google Gemini API: Per-model free-tier limits are shown only in Google AI Studio: "Rate limits depend on a variety of factors (such as your usage tier) and can be viewed in Google AI Studio." The one model with published free-tier numbers is Gemini Decision 1 (200 RPM, 50,000 TPM, 10,000 RPD). None of the 6 zero-price rows states a limit on the pricing page we read, so check the provider's console before you rely on one.

### Does BroadNet have a free tier?

No free price and no free tier. New BroadNet Inference accounts start with $5 of credit and no card (pricing page, checked 2026-11-14). It can be spent on BroadNet Gemma 4 VL 26B, BroadNet Transcribe Arabic and BroadNet Transcribe; DeepSeek V4.1 Flash, GLM 5.3 and Qwen3.8 27B need a top-up first (paid\_only in pricing.json, synced 2026-11-14). Pay-as-you-go keys allow 30 requests a minute and 4 in flight (docs, checked 2026-11-14). BroadRouter is BroadNet's site.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-free&utm_content=page-cta) ·

**Sources**

-   [Cohere: pricing (checked 2026-11-14)](https://cohere.com/pricing)
-   [Novita AI: pricing (checked 2026-11-14)](https://novita.ai/pricing)
-   [Together AI: pricing (checked 2026-11-14)](https://www.together.ai/pricing)
-   [Z.ai: pricing (checked 2026-11-14)](https://docs.z.ai/guides/overview/pricing)
-   [Cerebras: inference-docs.cerebras.ai/support/rate-limits (checked 2026-11-14)](https://inference-docs.cerebras.ai/support/rate-limits)
-   [Cerebras: www.cerebras.ai/terms-of-service (checked 2026-11-14)](https://www.cerebras.ai/terms-of-service)
-   [Cerebras: www.cerebras.ai/privacy-policy (checked 2026-11-14)](https://www.cerebras.ai/privacy-policy)
-   [Google Gemini API: aistudio.google.com/docs/pricing (checked 2026-11-14)](https://aistudio.google.com/docs/pricing)
-   [Google Gemini API: aistudio.google.com/docs/rate-limits (checked 2026-11-14)](https://aistudio.google.com/docs/rate-limits)
-   [Groq: console.groq.com/docs/rate-limits (checked 2026-11-14)](https://console.groq.com/docs/rate-limits)
-   [Groq: console.groq.com/docs/legal/services-agreement (checked 2026-11-14)](https://console.groq.com/docs/legal/services-agreement)
-   [Groq: console.groq.com/docs/your-data (checked 2026-11-14)](https://console.groq.com/docs/your-data)
-   [Cohere: docs.cohere.com/docs/rate-limits (checked 2026-11-14)](https://docs.cohere.com/docs/rate-limits)
-   [OpenRouter: openrouter.ai/docs/api-reference/limits (checked 2026-11-14)](https://openrouter.ai/docs/api-reference/limits)
-   [OpenRouter: openrouter.ai/docs/faq (checked 2026-11-14)](https://openrouter.ai/docs/faq)
-   [OpenRouter: openrouter.ai/docs/guides/privacy/provider-logging (checked 2026-11-14)](https://openrouter.ai/docs/guides/privacy/provider-logging)
-   [BroadNet Inference pricing page (checked 2026-11-14)](https://inference.broadnet.ai/pricing?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-free&utm_content=sources)
-   [BroadNet Inference rate card, pricing.json (synced 2026-11-14)](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-free&utm_content=sources)
-   [BroadNet Inference docs: key limits (checked 2026-11-14)](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-free&utm_content=sources)
