Models

Browse and retrieve information about the AI models available through Nextbit's API. Our models are compatible with the OpenAI format.

The model object

The model object contains information about a specific AI model, including its ID, capabilities, and context window.

Properties

Name
id
Type
string
Description
Unique identifier for the model.
Name
object
Type
string
Description
Object type, always "model".
Name
created
Type
integer
Description
Unix timestamp of when the model was created.
Name
owned_by
Type
string
Description
Organization that owns the model.

GET/v1/models

List models

Retrieve a list of all available models that can be used with the API.

Request

GET

/v1/models

from openai import OpenAI

client = OpenAI(
    base_url="https://api.nextbit256.com/v1",
    api_key="your-api-key"
)

models = client.models.list()

for model in models.data:
    print(model.id)

Response

{
  "object": "list",
  "data": [
    {
      "id": "llama3.3:70b",
      "object": "model",
      "created": 1686935002,
      "owned_by": "meta"
    },
    {
      "id": "qwen2.5:72b",
      "object": "model",
      "created": 1686935002,
      "owned_by": "alibaba"
    }
  ]
}

GET/v1/models/{id}

Retrieve model

Retrieve information about a specific model by its ID.

Required attributes

Name
id
Type
string
Description
The ID of the model to retrieve.

Request

GET

/v1/models/llama3.3:70b

from openai import OpenAI

client = OpenAI(
    base_url="https://api.nextbit256.com/v1",
    api_key="your-api-key"
)

model = client.models.retrieve("llama3.3:70b")
print(model)

Response

{
  "id": "llama3.3:70b",
  "object": "model",
  "created": 1686935002,
  "owned_by": "meta"
}

Available Models

All models support both chat completions and streaming. Below is the complete list of available models with real-time pricing and specifications.

Model Name	Context / Tokens	Quantization	Pricing	Repository
alia-salamandra:40b Unknown	33K / 33K	bf16	$0.30 / $0.60 per 1M tokens	View
deepseek:v4-flash DeepSeek	1M / 1M	fp8	$0.14 / $0.28 per 1M tokens	View
deepseek:v4-flash-0731 DeepSeek	1M / 1M	fp8	$0.40 / $1.20 per 1M tokens	View
deepseek:v4-pro DeepSeek	1M / 1M	fp8	$1.74 / $3.48 per 1M tokens	View
deepseek:v4-pro-0813 DeepSeek	1M / 1M	fp8	$1.32 / $3.96 per 1M tokens	View
euryale:33-70b Unknown	131K / 16K	bf16	$0.65 / $0.75 per 1M tokens	View
gemma-2:27b-it Google	8K / 2K	int4	$0.65 / $0.65 per 1M tokens	View
gemma4:26b-a4b Google	262K / 262K	bf16	$0.10 / $0.40 per 1M tokens	View
glm:5.3-flash Unknown	1M / 128K	fp8	$0.15 / $0.50 per 1M tokens	View
kimi:k2.6 Unknown	262K / N/A	fp4	$0.95 / $4.00 per 1M tokens	View
kimi:k3 Unknown	1M / 1M	fp4	$3.75 / $18.75 per 1M tokens	View
mythomax:13b Unknown	4K / 4K	int4	$0.06 / $0.06 per 1M tokens	View
qwen3:14b Qwen	41K / 41K	int4	$0.10 / $0.22 per 1M tokens	View
remm-slerp:l2-13b Unknown	6K / 4K	bf16	$0.45 / $0.65 per 1M tokens	View
unslopnemo:12b Unknown	33K / 33K	fp8	$0.40 / $0.40 per 1M tokens	View

alia-salamandra:40b

Unknown

bf16

Context Length:33K tokens

Max Completion:33K tokens

Pricing (per 1M tokens)

Input:$0.30

Output:$0.60

View on Hugging Face

deepseek:v4-flash

DeepSeek

fp8

Context Length:1M tokens

Max Completion:1M tokens

Pricing (per 1M tokens)

Input:$0.14

Output:$0.28

View on Hugging Face

deepseek:v4-flash-0731

DeepSeek

fp8

Context Length:1M tokens

Max Completion:1M tokens

Pricing (per 1M tokens)

Input:$0.40

Output:$1.20

View on Hugging Face

deepseek:v4-pro

DeepSeek

fp8

Context Length:1M tokens

Max Completion:1M tokens

Pricing (per 1M tokens)

Input:$1.74

Output:$3.48

View on Hugging Face

deepseek:v4-pro-0813

DeepSeek

fp8

Context Length:1M tokens

Max Completion:1M tokens

Pricing (per 1M tokens)

Input:$1.32

Output:$3.96

View on Hugging Face

euryale:33-70b

Unknown

bf16

Context Length:131K tokens

Max Completion:16K tokens

Pricing (per 1M tokens)

Input:$0.65

Output:$0.75

View on Hugging Face

gemma-2:27b-it

Google

int4

Context Length:8K tokens

Max Completion:2K tokens

Pricing (per 1M tokens)

Input:$0.65

Output:$0.65

View on Hugging Face

gemma4:26b-a4b

Google

bf16

Context Length:262K tokens

Max Completion:262K tokens

Pricing (per 1M tokens)

Input:$0.10

Output:$0.40

View on Hugging Face

glm:5.3-flash

Unknown

fp8

Context Length:1M tokens

Max Completion:128K tokens

Pricing (per 1M tokens)

Input:$0.15

Output:$0.50

View on Hugging Face

kimi:k2.6

Unknown

fp4

Context Length:262K tokens

Max Completion:N/A

Pricing (per 1M tokens)

Input:$0.95

Output:$4.00

View on Hugging Face

kimi:k3

Unknown

fp4

Context Length:1M tokens

Max Completion:1M tokens

Pricing (per 1M tokens)

Input:$3.75

Output:$18.75

View on Hugging Face

mythomax:13b

Unknown

int4

Context Length:4K tokens

Max Completion:4K tokens

Pricing (per 1M tokens)

Input:$0.06

Output:$0.06

View on Hugging Face

qwen3:14b

Qwen

int4

Context Length:41K tokens

Max Completion:41K tokens

Pricing (per 1M tokens)

Input:$0.10

Output:$0.22

View on Hugging Face

remm-slerp:l2-13b

Unknown

bf16

Context Length:6K tokens

Max Completion:4K tokens

Pricing (per 1M tokens)

Input:$0.45

Output:$0.65

View on Hugging Face

unslopnemo:12b

Unknown

fp8

Context Length:33K tokens

Max Completion:33K tokens

Pricing (per 1M tokens)

Input:$0.40

Output:$0.40

View on Hugging Face

Pricing Note: All prices are displayed per 1 million tokens. Actual costs are calculated per token used. For example, processing 10,000 tokens at $0.17 per 1M costs $0.0017.