Llama 3.1 70b Model Hosting

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

meta-llama/Llama-3.1-70B-Instruct

907

717,618

M

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

meta-llama/Meta-Llama-3.1-70B-Instruct

907

717,618

M

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

meta-llama/Llama-3.1-70B

413

119,664

M

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

meta-llama/Meta-Llama-3.1-70B

413

119,664

M

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

2,064

8,981

N

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

NousResearch/Meta-Llama-3.1-70B-Instruct

13

3,706

N

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

unsloth/Meta-Llama-3.1-70B-Instruct

4

3,430

U

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

OpenPipe/Llama-3.1-70B-Instruct

0

3,375

O

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

0xA50C1A1/Llama-3.3-70B-Instruct-Heretic

2

2,531

0

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

Naphula/Cthulhu-70B-v1

5

2,333

N

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

Skywork/Skywork-Critic-Llama-3.1-70B

12

2,297

S

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

Salesforce/Llama-xLAM-2-70b-fc-r

51

2,234

S

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

NousResearch/Hermes-4-70B

185

1,637

N

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

SicariusSicariiStuff/Assistant_Pepe_70B

37

1,253

S

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

NousResearch/Meta-Llama-3.1-70B

7

1,112

N

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

aisingapore/Llama-SEA-LION-v3-70B-IT

5

997

A

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

NeverSleep/Lumimaid-v0.2-70B

48

979

N

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

marcelbinz/Llama-3.1-Centaur-70B

82

796

M

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

Sahabat-AI/Llama-Sahabat-AI-v2-70B-IT

13

694

S

Warm

{ "id": "llama31-70b", "created_at": "2025-10-15T03:53:00.000Z", "updated_at": "2026-01-27T07:58:09.462Z", "concurrency_cost": 4, "size": 70, "family": "llama31", "context_length": 32768, "grid_model_class_id": "llama31-70b-16k", "reference_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "backend": { "id": "router-s1", "created_at": "2026-01-27T07:14:25.523Z", "updated_at": "2026-01-27T07:14:25.523Z", "apiBaseURL": "https://router-s1.recursal-dev.com", "apiKey": null }, "secondary_backend": { "id": "router-g1", "created_at": "2025-11-28T07:38:36.083Z", "updated_at": "2025-11-28T07:38:36.083Z", "apiBaseURL": "https://router-g1.recursal-dev.com", "apiKey": null }, "family_name": "Llama 3.1" }

huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated

92

661

H