Atlas / Models / Prime Intellect / Prime Intellect: INTELLECT-3

Prime Intellect: INTELLECT-3✓ Catalog verified

prime-intellect/intellect-3

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math, code, science, and general reasoning, consistently outperforming many larger frontier models. Designed for strong multi-step problem solving, it maintains high accuracy on structured tasks while remaining efficient at inference thanks to its MoE architecture.

Input price
$0.20 /1M
Output price
$1.10 /1M
Context
131K
Modalities
text
Released
Nov 27, 2025
Tool calling
✓ Yes
Atlas signal
91/100
01

Overview

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math, code, science, and general reasoning, consistently outperforming many larger frontier models. Designed for strong multi-step problem solving, it maintains high accuracy on structured tasks while remaining efficient at inference thanks to its MoE architecture.

Access: available through the official Prime Intellect API. Context window: 131K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifierprime-intellect/intellect-3
ProviderPrime Intellect
Model typeText LLM
Context window131K catalog
Input modalitiestext
Output modalitiestext
ReleasedNov 27, 2025
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": null,
  "temperature": 0.6,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for prime-intellect/intellect-3 as published in the catalog.

$0.20
Input /1M
$1.10
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$2e-7$0.20 / 1MPer input token
Completion tokens$0.0000011$1.10 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.32Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Prime Intellect: INTELLECT-3
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
97signal
Math Signal (GSM8K proxy)
92signal
Science Signal (GPQA proxy)
79signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Prime Intellect: INTELLECT-3 through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="prime-intellect/intellect-3",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Prime Intellect: INTELLECT-3 cost?

$0.20 per 1M input tokens and $1.10 per 1M output tokens on the official Prime Intellect API.

What is the context window of Prime Intellect: INTELLECT-3?

Prime Intellect: INTELLECT-3 supports up to 131K tokens of context.

Does Prime Intellect: INTELLECT-3 support tool / function calling?

Yes, Prime Intellect: INTELLECT-3 supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Prime Intellect: INTELLECT-3?

Use the official Prime Intellect API with the model id `prime-intellect/intellect-3`. See the Quick start section above for code examples.