Pricing

Start free. Pay only for what you use.

118+ open-source models are $0 input/output, capped only by the free-plan daily request limit. Premium providers (OpenAI, Anthropic, Google) bill at the provider's published rate — zero markup.

Free

$0/month

Evaluate and prototype with open-source models.

  • Unlimited NVIDIA NIM open-source access after a $5 activation (the $5 becomes spendable balance)
  • 118+ open-source models on NVIDIA NIM
  • Llama 3.1 70B, Mixtral, Nemotron, Codestral, Gemma 4
  • OpenAI-compatible and Anthropic-compatible endpoints
  • Automatic failover across providers
Get free key

Activation

$5 one-time

Cheapest path to unlock ongoing free use and any paid provider.

  • Ongoing $0 input/output access to 118+ NVIDIA NIM open models (daily request limits apply)
  • $5 becomes spendable balance — not a fee, not a subscription
  • OpenAI, Anthropic, Google, Replicate at published rates
  • Zero markup — you pay exactly what providers charge
  • One-time charge, no recurring billing
Unlock — $5 one-time

Pro· Most popular

$29/month

For developers shipping production AI features.

  • $20/month of premium-provider usage included
  • Higher daily request limits (5,000 chat / 10,000 text / 500 image-generate)
  • All 207+ models across every provider — zero markup
  • Image generation (Flux, DALL·E, Imagen)
  • Video generation (Kling, Runway, Veo)
Upgrade to Pro

Enterprise

Custom

Custom included usage, dedicated support, and compliance.

  • Custom monthly included usage and request limits
  • Custom model hosting
  • Dedicated account team
  • Priority support SLA
  • Custom DPA and compliance
Contact sales

Token prices

InferAll charges the provider's published rate with zero markup. Prices shown are per 1M tokens (input / output) as of June 2026; see each provider's website for the current rate.

NVIDIA NIM (118+ models)Free within daily request rate limits (see your plan)
OpenAI GPT-4o$2.50 / $10.00 per 1M
OpenAI GPT-4o-mini$0.15 / $0.60 per 1M
Anthropic Claude Opus 4.7$15.00 / $75.00 per 1M
Anthropic Claude Sonnet 4.6$3.00 / $15.00 per 1M
Anthropic Claude Haiku 4.5$1.00 / $5.00 per 1M
Google Gemini 2.5 Flash$0.15 / $0.60 per 1M
Google Gemini 2.5 Pro$1.25 / $10.00 per 1M

See inferall.ai/live for the full model list and pricing.

Common questions

Is the free plan actually free?

Yes. The 118+ open-source models on NVIDIA NIM are $0 input and $0 output, capped only by the free-plan daily request rate (100 chat / 50 text / 20 image-analyze / 10 image-generate / 5 video-generate per day). NIM access unlocks after the $5 starter pack settles — that $5 is not a fee, it becomes spendable balance on your account and covers premium-model usage. Premium providers (OpenAI, Anthropic, Google) bill at the provider's published per-token rate with zero markup, drawn from your balance or your plan's monthly included usage.

What does 'zero markup' mean?

When you use a premium provider (OpenAI, Anthropic, Google), you pay exactly what that provider charges per token. InferAll does not add a markup. A $0.15/M-token call to GPT-4o-mini costs $0.15/M through InferAll.

How does the monthly included usage work?

Each plan includes a monthly $-amount of premium-provider usage: $5/month on Free, $20/month on Pro, $100/month on Team. Calls to premium providers (OpenAI, Anthropic, Google) draw against your included usage first, then against any prepaid balance you've added via the $5 or $100 packs. Calls to the 118+ NVIDIA NIM open models cost $0 and don't burn included usage. Included usage resets monthly.

What's the difference between Free, the $5 activation pack, and Pro?

Free is a 200-request trial to evaluate the 118+ NVIDIA NIM open-source models. The $5 activation pack is a one-time charge that unlocks ongoing free-plan use and becomes spendable balance for premium providers (OpenAI, Anthropic, Google) at the provider's published per-token rate with zero markup. Pro ($29/mo) gives you higher daily request limits and $20/month of premium-provider usage included — the right fit if you call paid providers regularly.

Claude Opus 4 is $15/$75 per million tokens — what's the free alternative?

For Opus-class work (long-context reasoning, agentic tasks, complex analysis), the closest free-NIM alternative is nvidia/nemotron-3-super-120b-a12b — a 120B-parameter model with comparable quality on most benchmarks, billed at $0 input / $0 output. A typical Opus conversation (10K input + 4K output tokens) costs ~$0.45 on Anthropic's published Opus 4.7 rate; the same conversation through Nemotron 120B is $0. The $5 starter pack is most useful as a way to keep premium-Opus available on-demand for the few tasks where it matters, with NIM handling the bulk. For Sonnet- or Haiku-class work, the equivalents are meta/llama-3.1-70b-instruct (70B mid-class) and meta/llama-3.1-8b-instruct (8B fast class), respectively.

Get your API key — start at $0