Back to providers

Synap by Linkrra

HealthyTelemetry updated 43m ago

OpenAI-compatible API offering Linkrra-operated GPU deployments and separate brokered models. The listed GPT-OSS 20B, Gemma 4 26B A4B and Qwen3 Coder 30B A3B deployments have public token prices and served context limits. Linkrra reports native MXFP4 for GPT-OSS and AWQ 4-bit for Gemma and Qwen3 Coder; this Gemma deployment accepts text input only. As disclosed on 2026-10-21, requests for these three models can still be forwarded to OpenRouter and rejected when Linkrra nodes are unavailable, pending a gateway fix. This listing does not guarantee exclusively local request handling or zero retention. Data handling policy: https://synap.linkrra.com/privacy.

API Base URL

https://pool.linkrra.com/v1

Authentication

bearer

Uptime (24h)

100.0%

Uptime (7d)

100.0%

Supported Regions

global

Latency (TTFT)

Time to first token percentiles

No latency data available

Health History

Uptime over the last 7 days

7-Day Uptime100.00% — Excellent
24-Hour Uptime100.00% — Excellent

Current Status

Healthy

Last Checked

43m ago

Supported Models (3)

Models available through this provider. Select a model to view details.

Qwen3 Coder 30B A3B Instruct

qwen3-coder-30b-a3b

Pricing (per 1M)
In: $0.07
Out: $0.27
Rate Limits
N/A RPM
N/A TPM
Regions
global

Gemma 4 26B

gemma-4-26b

Pricing (per 1M)
In: $0.04
Out: $0.21
Rate Limits
N/A RPM
N/A TPM
Regions
global

GPT-OSS 20B

gpt-oss-20b

Pricing (per 1M)
In: $0.02
Out: $0.09
Rate Limits
N/A RPM
N/A TPM
Regions
global