Index / providers / nextbit

NextBit

Spanish inference provider with OpenAI- and Anthropic-compatible APIs and an EU-only endpoint on its own hardware, serving Euryale and ReMM SLERP.

Models2

Per-token price$0.50–$0.68/1M tok

Plans from—

Free tier—

nextbit256.com ↗Pending review

[ 01 ] Models & prices

BILLINGPay per token by card (Stripe) or through AWS Marketplace.

Model	Method	Context	In $/1M	Out $/1M	Per 1K chats
remm-slerp:l2-13bLlama 2 13B · 13B	Fine-tuned	6K	$0.45	$0.65	$0.78
euryale:33-70bLlama 3.3 70B · 70B · Llama 3.3 Community	Fine-tuned	131K	$0.65	$0.75	$1.02

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: No logs
Trains on prompts: No
Guarantee: Policy only
Jurisdiction: Spain, EU
Signup: Account required
Payments: Card, Other
Data checked: Oct 11, 2026

PRIVACYZero-data-retention terms say request content is never written to storage or logs (metadata only). The EU endpoint runs on its own hardware in Spain; the global endpoint may use third-party cloud outside the EEA. Policy ↗

[ 03 ] Scores

Compliance

Benchmark pending

measured

Capability

Benchmark pending

measured

Privacy

58.0

from published policy & pricing

Truthfulness

Benchmark pending

measured

Cost

61.6

from published policy & pricing

Speed

Benchmark pending

measured

Composite: pending capability and compliance runs · method

[ 04 ] Notes & sources

NEXTBIT 256, S.L. Serves in BF16. It is OpenRouter's only upstream for Llama 3.3 Euryale 70B. Users must be 18+. The zero-retention terms allow a 30-day legal-hold exception.