Index / providers / requesty

Requesty

UK LLM gateway routing OpenAI-compatible requests to 600+ upstream models, including Hermes 4 via Nebius and Sao10K and MythoMax fine-tunes via Novita.

Models4

Per-token price$0.050–$1.50/1M tok

Plans from—

Free tierYes

requesty.ai ↗Pending review

[ 01 ] Models & prices

BILLINGUpstream per-token rates plus a 5% pay-as-you-go markup. Free models only on the free tier (200 requests a day, no card).

Model	Method	Context	In $/1M	Out $/1M	Per 1K chats
novita/sao10k/l3-8b-stheno-v3.2Llama 3 8B · 8B	Fine-tuned	8K	$0.050	$0.050	$0.075
novita/gryphe/mythomax-l2-13bLlama 2 13B · 13B	Fine-tuned	4K	$0.090	$0.090	$0.14
novita/sao10k/l31-70b-euryale-v2.2Llama 3.1 70B · 70B · Llama 3.1 Community	Fine-tuned	16K	$1.48	$1.48	$2.22
nebius/nousresearch/hermes-4-405bLlama 3.1 405B · 405B · Llama 3.1 Community	Fine-tuned	128K	$1.00	$3.00	$2.50

Per 1K chats = cost of 1,000 messages of ~1,000 tokens in and ~500 out. Click a model to compare it across providers.All models →

[ 02 ] At a glance

Method: Fine-tuned
Access: OpenAI-compatible API
Logging: Retained
Trains on prompts: No
Guarantee: Policy only
Jurisdiction: United Kingdom
Signup: Account required
Payments: Card
Data checked: Oct 11, 2026

PRIVACYPrompt and output logging is on by default (encrypted, stored in the EU for 30 days) and can be turned off per key or organization for zero retention. Upstream policies also apply. Policy ↗

[ 03 ] Scores

Compliance

Benchmark pending

measured

Capability

Benchmark pending

measured

Privacy

38.0

from published policy & pricing

Truthfulness

Benchmark pending

measured

Cost

100.0

from published policy & pricing

Speed

Benchmark pending

measured

Composite: pending capability and compliance runs · method

[ 04 ] Notes & sources

Requesty Ltd. Its list still shows Hermes 4 70B via Nebius, which Nebius moved to dedicated-only on Aug 31, 2026, so we leave it out as likely stale. Customers can configure their own refusal guardrails.