vLLM & SGLang Compatible Models

Open-weight models with a published vLLM or SGLang serve command for single or multi-GPU production serving. Each page lists VRAM needs and GPU fits.

39 available on LLM API · 74 listed

Model

Released

Input / 1M

Output / 1M

Context

DeepSeek V4.1 Flash

Sep 10, 2026

$0.3

$1.2

1M

Try it

Qwen3.8 Flash Next

Aug 27, 2026

$0.201

$0.5

262.1K

Try it

DeepSeek V4 Flash 0731

Jul 31, 2026

$0.14

$0.28

1M

Try it

Kimi K3

Jul 16, 2026

$3

$15

1M

Try it

Kimi K2.7-Code

Jun 12, 2026

$0.74

$3.5

262.1K

Try it

MiniMax M3

May 28, 2026

$0.6

$2.4

1M

Try it

DeepSeek V4 Flash

Apr 25, 2026

$0.19

$0.51

1M

Try it

DeepSeek V4 Pro

Apr 25, 2026

$1.74

$3.48

1M

Try it

MiMo V2.5 Pro

Apr 22, 2026

$0.522

$1.044

1M

Try it

Kimi K2.6

Apr 20, 2026

$0.95

$4

262.1K

Try it

Qwen 3.5 9B

Mar 2, 2026

$0.1

$0.15

262.1K

Try it

Qwen 3.5 397B A17B

Feb 16, 2026

$0.6

$3.6

262.1K

Try it

MiniMax M2.1

Dec 23, 2025

$0.27

$1.08

204.8K

Try it

DeepSeek V3.2

Dec 1, 2025

$0.25

$0.5

163.8K

Try it

MiniMax M2

Oct 23, 2025

$0.2

$1

196.6K

Try it

Qwen3 VL 8B Instruct

Oct 15, 2025

$0.08

$0.5

131.1K

Try it

Qwen3 VL 30B A3B Instruct

Oct 4, 2025

$0.2

$0.7

131.1K

Try it

Qwen3 VL 235B A22B Instruct

Sep 23, 2025

$0.5

$2

131.1K

Try it

Qwen3 VL 235B A22B Thinking

Sep 23, 2025

$0.5

$2

131.1K

Try it

Qwen3 Next 80B A3B Instruct

Sep 10, 2025

$0.5

$2

131.1K

Try it

Qwen3 Next 80B A3B Thinking

Sep 10, 2025

$0.5

$6

131.1K

Try it

Kimi K2.5

Sep 1, 2025

$0.5

$2.8

262.1K

Try it

MiniMax M2.7

Aug 1, 2025

$0.3

$1.2

204.8K

Try it

Qwen3 Coder Next

Aug 1, 2025

$0.108

$0.675

262.1K

Try it

Qwen3 235B A22B Instruct 2507

Jul 1, 2025

$0.2

$0.6

262K

Try it

Qwen3 30B A3B Instruct 2507

Jul 1, 2025

$0.1

$0.3

262K

Try it

Qwen3 30B A3B Thinking 2507

Jul 1, 2025

$0.1

$0.3

262K

Try it

Qwen3 Coder 30B A3B Instruct

Jul 1, 2025

$0.07

$0.27

262K

Try it

Eleven v3

Jun 5, 2025

$0.12/1K chars

—

Try it

MiniMax M2.5

Jun 1, 2025

$0.3

$1.2

204.8K

Try it

Qwen3 235B A22B FP8

Apr 29, 2025

$0.2

$0.8

41K

Try it

Qwen3 30B A3B FP8

Apr 29, 2025

$0.09

$0.45

41K

Try it

MiniMax Text 01

Jan 15, 2025

$0.2

$1.1

1M

Try it

Qwen2.5 VL 32B Instruct

Jan 1, 2025

$1.4

$4.2

131.1K

Try it

Llama 3.3 70B Instruct

Dec 6, 2024

$0.13

$0.4

131.1K

Try it

Llama 3.1 70B Instruct

Jul 23, 2024

$0.72

$0.72

128K

Try it

Llama 3.1 8B Instruct

Jul 23, 2024

$0.22

$0.22

128K

Try it

Custom Model

—

—

—

Try it

Gemma 4 31B

Apr 2, 2026

$0.14

$0.4

262K

View model

Qwen2.5-VL-72B-Instruct

—

$0.25

$0.75

128K

Try it

DeepSeek R1 0528

—

$0.5

$2.15

164K

View model

Olmo 3 32B Think

—

Free

Free

65,536

View model

DeepSeek V3.1 Terminus

—

$0.27

$1

164K

View model

DeepSeek V3.1

—

$0.25

$0.95

164K

View model

DeepSeek V3 0324

—

$0.25

$1

164K

View model

Reka Edge

—

$0.1

$0.1

16K tokens

View model

LFM2-24B-A2B

—

Free

Free

~32K

View model

Granite 4.0 Micro

—

$0.017

$0.112

131K tokens

View model

Ling-2.6-flash

—

Free

Free

~16K

View model

DeepSeek V3.1 Nex N1

—

~$0.70

~$2.80

~128K

View model

Qwen3.5-27B

—

$0.195

$1.56

262K tokens

View model

Qwen3.5-35B-A3B

—

$0.163

$1.3

262K tokens

View model

Rnj 1 Instruct

—

$0.15

$0.15

32K

View model

DeepSeek V3.2 Exp

—

$0.27

$0.41

164K tokens

View model

Step 3.7 Flash

—

$0.2

$1.15

262K tokens

View model

Qwen3.6 27B

—

$0.3

$2

262K tokens

View model

Trinity Mini

—

$0.045

$0.150

131K

View model

Hy3 preview

—

$0.18

$0.6

262K tokens

View model

MiMo-V2.5

—

$0.14

$0.28

1.1M tokens

View model

Qwen3.6 35B A3B

—

$0.1

$0.9

262K tokens

View model

Qwen3 VL 30B A3B Thinking

—

$0.2

$2.4

262K tokens

View model

Qwen3 VL 8B Thinking

—

$0.18

$2.1

131K tokens

View model

ERNIE 4.5 21B A3B Thinking

—

~$0.80

~$2.40

~32K

View model

Granite 4.1 8B

—

Free

Free

~128K

View model

Qwen3.5-122B-A10B

—

$0.26

$2.08

262K tokens

View model

Qwen3 VL 32B Instruct

—

$0.104

$0.416

131K tokens

View model

INTELLECT-3

—

~$0.80

~$2.40

~32K

View model

MiMo-V2-Flash

—

Free

Free

~8K

View model

Trinity Large Thinking

—

$0.25

$0.8

262K tokens

View model

Step 3.5 Flash

—

$0.1

$0.3

262K tokens

View model

Kimi K2 Thinking

—

$0.6

$2.5

262K tokens

View model

Phi 4 Mini Instruct

—

Free

Free

~128K

View model

Ling-2.6-1T

—

$0.075

$0.625

262K

View model

Ring-2.6-1T

—

$0.07

$0.63

262K

View model