What models are supported?

We support the latest and most capable models from all leading platforms, including OpenAI, Anthropic, Google, Meta, and DeepSeek. Our system is designed to integrate new models within hours of their public release.

How does the credit system work?

Each plan comes with a set amount of monthly credits. Credits are consumed based on the token usage of the models you interact with. We bill in micro-credits to ensure you only pay for what you actually use.

How does the credit system translate to tokens?

Credits map directly to raw token consumption. For example, $10 of credits corresponds to roughly 1 million input tokens of GPT-4o, or up to 60 million input tokens on our open-source models. View the Benchmarks section for detailed conversion rates.

Is there a free trial?

Yes! Every new account automatically starts with a 7-day Developer plan trial at no cost — 200 credits included. You get full access to multi-model comparison, API key support, and cost visibility. After 7 days, choose Personal ($10/mo) or Developer ($20/mo) to continue.

Can I cancel my subscription at any time?

Absolutely. You can manage your subscription through our billing portal and cancel at any time. Your credits will remains active until the end of your billing cycle.

Migrating off Llama 3.3 70B

Llama 3.3 70B (Groq) — shuts down 2026-08-16. Source · Verified 2026-08-08.

Groq is decommissioning Llama 3.3 70B on its LPU inference platform. This isn't a Meta model deprecation — Llama 3.3 70B's weights aren't going anywhere — it's Groq specifically pulling the model from its hosted API, which is the only place we route requests for it.

What actually changes

	Llama 3.3 70B	—
Blended $/M	$0.64	—
Context window	128,000 tokens	—
Max output	32,768 tokens	—
Modalities	text	—
Tokens / sec	unchanged / not measured	not measured

Pricing from our live pricing registry; speed from our benchmark leaderboard where measured.

Gotchas

There is no first-party Groq successor for this exact model at shutdown time. Meta's own Model API (Muse Spark 1.1) is the intended long-term replacement, but it requires a separate API key we don't yet have configured — it isn't selectable through our gateway.
Llama 3.3 70B has no native reasoning/thinking mode. If you route to a reasoning-capable replacement (GPT-OSS 120B, DeepSeek V4 Pro), expect a different response shape if you were parsing raw completions rather than using our unified response format.
Groq is known for aggressive rate limits during high-demand windows relative to token-metered providers — moving to a token-billed model (rather than another Groq-hosted one) changes your cost predictability at scale, not just your per-token price.
If you were relying on Groq's sub-100ms time-to-first-token for a latency-sensitive path, GPT-OSS 120B on Groq is the closest speed match; moving off Groq entirely will very likely be slower even if it's cheaper.

Alternatives beyond the obvious successor

GPT-OSS 120B$0.26/M blended

Also Groq-hosted — keeps the same LPU latency profile, adds reasoning mode.

Full head-to-head comparison →

Qwen 3.8 30B$1.20/M blended

Groq-hosted multimodal alternative with vision support Llama 3.3 70B lacked.

DeepSeek V4 Flash$0.17/M blended

Off Groq entirely — token-billed, no LPU rate-limit exposure.

FAQ

Is Llama 3.3 70B being shut down?

Yes — it shuts down on 2026-08-16. Source: https://console.groq.com/docs/deprecations.

What should I switch to from Llama 3.3 70B?

There is no direct 1:1 successor — see the alternatives section for cross-provider options.

Will switching cost more or less?

See the pricing comparison table below for exact numbers.