Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text

Pokee-Isaac 28B

Pokee-Isaac is a 28B agentic model with function calling and OpenAI-compatible structured output. It accepts up to 250,000 input tokens here, within what Pokee serves reliably; Pokee advertises about 10 million. Pokee bills in $0.01 increments, rounding each non-zero request up to the next cent.

  • Reasoning
  • Tool Calling
  • Structured Output

Added Aug 4, 2026

Pricing

Auto routing · per 1M tokens
Input
$0.15
Output
$1.00
Cache read
$0.075
Compare provider prices

Specifications

Context window
250K
Max output
60K
Parameters
28B

Benchmarks

No public benchmark scores for this model yet.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (Anonymized)
$0.15$1.00$0.075N/AN/A
Pokee
Pokee
US
$0.157$1.05N/AN/AN/A
Privacy:No training on prompts

Related text models

Compare Pokee-Isaac 28B with similar models from the same provider or model family.

Clover 2

kitani/clover-2

Clover 2 is Kitani's MoLE (Mixture of LoRA Experts) model: a base model with seven LoRA experts and trained per-token routing between them. Text chat with reasoning off by default (Clover 2 Thinking turns it on). It supports function calling and a 200,000-token context window shared by input and output, with up to 8,192 output tokens. Free during its first week, until November 24, 2026 03:33 UTC.

Clover 2 Thinking

kitani/clover-2:thinking

Clover 2 is Kitani's MoLE (Mixture of LoRA Experts) model: a base model with seven LoRA experts and trained per-token routing between them. This variant thinks before answering. It supports function calling and a 200,000-token context window shared by input and output, with up to 8,192 output tokens. Free during its first week, until November 24, 2026 03:33 UTC.

DeepSeek V4.1 Flash 1017 Abliterated

deepseek/deepseek-v4.1-flash-1017-abliterated

An abliterated (refusal-removed) version of DeepSeek V4.1 Flash 1017. Text only, with tool calling, optional reasoning and a 1M-token context window. Its behavior may differ from DeepSeek V4.1 Flash 1017. Served by a single host; it may be unavailable while that host is down.

DeepSeek V4.1 Flash 1017 Abliterated Thinking

deepseek/deepseek-v4.1-flash-1017-abliterated:thinking

An abliterated (refusal-removed) version of DeepSeek V4.1 Flash 1017. Text only, with tool calling, optional reasoning and a 1M-token context window. Its behavior may differ from DeepSeek V4.1 Flash 1017. Served by a single host; it may be unavailable while that host is down.

Kimi K3.1 Pro Abliterated (Lyber)

lyber/kimi-k3.1-pro-abliterated

Kimi K3.1 Pro Abliterated served by Lyber.ai.

Qwen 4 Max

qwen/qwen4-max

Qwen 4 Max is Alibaba's flagship multimodal model for coding, knowledge work, data analysis, and long-running agent workflows. It accepts text, image, and video input, supports selectable reasoning, tool calling, structured output, and a 1M-token context window.