Catalog data · Updated August 12, 2026

Largest Context Window LLMs

Compare active text-generation model identities with recorded context windows of at least 128,000 tokens. Large outlier values are excluded from the ranking.

Objective catalog fields No overall quality score
546
Long-context identities
25
Providers shown
1
Data sections
6,429
Catalog records

Largest context windows

Active text-generation identities from 128,000 through 10 million tokens.

Showing 46 of 546

Model Provider offers Why listed Context Input / output price Updated
Hermes 3 Llama 3.1 405b
hermes-3-llama-3.1-405b
Venice
1 offer
128000 token context 128,000
$1.10 / $3.00
per 1M tokens, when known
June 11, 2026
Inception: Mercury 2
mercury-2
Openrouter, Venice
2 offers
128000 token context 128,000
$0.25 / $0.75
per 1M tokens, when known
June 11, 2026
Ling-1T
ling-1t
Zenmux
1 offer
128000 token context 128,000
$0.56 / $2.24
per 1M tokens, when known
October 9, 2025
Llama 3.2 11B Vision Instruct
llama-3.2-11b-vision-instruct
Cloudflare workers ai
1 offer
128000 token context 128,000
$0.05 / $0.68
per 1M tokens, when known
September 25, 2024
Llama 3.2 3B
llama-3.2-3b
Venice
1 offer
128000 token context 128,000
$0.15 / $0.60
per 1M tokens, when known
June 11, 2026
Llama 3.3 70B
llama-3.3-70b
Venice
1 offer
128000 token context 128,000
$0.70 / $2.80
per 1M tokens, when known
June 11, 2026
Magistral Medium (latest)
magistral-medium-latest
Mistral
1 offer
128000 token context 128,000
$2.00 / $5.00
per 1M tokens, when known
March 20, 2025
Magistral Small
magistral-small
Mistral
1 offer
128000 token context 128,000
$0.50 / $1.50
per 1M tokens, when known
March 17, 2025
Ministral 3B (latest)
ministral-3b-latest
Mistral
1 offer
128000 token context 128,000
$0.04 / $0.04
per 1M tokens, when known
October 4, 2024
Ministral 8B (latest)
ministral-8b-latest
Mistral
1 offer
128000 token context 128,000
$0.10 / $0.10
per 1M tokens, when known
October 4, 2024
Mistral Large
mistral-large
Openrouter
1 offer
128000 token context 128,000
$2.00 / $6.00
per 1M tokens, when known
February 26, 2024
Mistral Small 3.1 24B Instruct
mistral-small-3.1-24b-instruct
Cloudflare workers ai
1 offer
128000 token context 128,000
$0.35 / $0.56
per 1M tokens, when known
March 18, 2025
Mistral Small 3.2
mistral-small-2506
Mistral
1 offer
128000 token context 128,000
$0.10 / $0.30
per 1M tokens, when known
June 20, 2025
Mistral: Mistral Small 3.1 24B
mistralai/mistral-small-3.1-24b-instruct
Openrouter
1 offer
128000 token context 128,000
$0.35 / $0.56
per 1M tokens, when known
March 17, 2025
NVIDIA Nemotron 3 Nano 30B
nvidia-nemotron-3-nano-30b-a3b
Venice
1 offer
128000 token context 128,000
$0.08 / $0.30
per 1M tokens, when known
June 11, 2026
NVIDIA: Nemotron 3.5 Content Safety (free)
nemotron-3.5-content-safety:free
Openrouter
1 offer
128000 token context 128,000
$0.00 / $0.00
per 1M tokens, when known
June 4, 2026
NVIDIA: Nemotron Nano 12B 2 VL (free)
nvidia/nemotron-nano-12b-v2-vl:free
Openrouter
1 offer
128000 token context 128,000
$0.00 / $0.00
per 1M tokens, when known
October 28, 2025
NVIDIA: Nemotron Nano 9B V2 (free)
nemotron-nano-9b-v2:free
Openrouter
1 offer
128000 token context 128,000
$0.00 / $0.00
per 1M tokens, when known
August 18, 2025
Open Mistral Nemo
open-mistral-nemo
Mistral
1 offer
128000 token context 128,000
$0.15 / $0.15
per 1M tokens, when known
July 1, 2024
OpenAI GPT OSS 120B
openai-gpt-oss-120b
Venice
1 offer
128000 token context 128,000
$0.07 / $0.30
per 1M tokens, when known
June 11, 2026
openai/gpt-5.1-chat
gpt-5.1-chat
Zenmux
1 offer
128000 token context 128,000
$1.25 / $10.00
per 1M tokens, when known
November 13, 2025
OpenAI: GPT Audio
gpt-audio
Openrouter
1 offer
128000 token context 128,000
$2.50 / $10.00
per 1M tokens, when known
January 19, 2026
OpenAI: GPT Audio Mini
gpt-audio-mini
Openrouter
1 offer
128000 token context 128,000
$0.60 / $2.40
per 1M tokens, when known
January 19, 2026
OpenAI: GPT-4 Turbo
gpt-4-turbo
Openrouter
1 offer
128000 token context 128,000
$10.00 / $30.00
per 1M tokens, when known
April 9, 2024
OpenAI: GPT-4 Turbo Preview
gpt-4-turbo-preview
Openrouter
1 offer
128000 token context 128,000
$10.00 / $30.00
per 1M tokens, when known
January 25, 2024
OpenAI: GPT-4o
gpt-4o
Openai, Openrouter
2 offers
128000 token context 128,000
$2.50 / $10.00
per 1M tokens, when known
August 6, 2024
OpenAI: GPT-4o (2024-05-13)
gpt-4o-2024-05-13
Openrouter
1 offer
128000 token context 128,000
$5.00 / $15.00
per 1M tokens, when known
May 13, 2024
OpenAI: GPT-4o (2024-08-06)
gpt-4o-2024-08-06
Openai, Openrouter
2 offers
128000 token context 128,000
$2.50 / $10.00
per 1M tokens, when known
August 6, 2024
OpenAI: GPT-4o (2024-11-20)
gpt-4o-2024-11-20
Openai, Openrouter
2 offers
128000 token context 128,000
$2.50 / $10.00
per 1M tokens, when known
November 20, 2024
OpenAI: GPT-4o-mini
gpt-4o-mini
Openai, Openrouter
2 offers
128000 token context 128,000
$0.15 / $0.60
per 1M tokens, when known
July 18, 2024
OpenAI: GPT-4o-mini (2024-07-18)
gpt-4o-mini-2024-07-18
Openrouter
1 offer
128000 token context 128,000
$0.15 / $0.60
per 1M tokens, when known
July 18, 2024
OpenAI: GPT-5.2 Chat
gpt-5.2-chat
Openrouter
1 offer
128000 token context 128,000
$1.75 / $14.00
per 1M tokens, when known
December 10, 2025
OpenAI: GPT-5.3 Chat
gpt-5.3-chat
Openrouter, Zenmux
2 offers
128000 token context 128,000
$1.75 / $14.00
per 1M tokens, when known
March 20, 2026
Perplexity: Sonar Deep Research
sonar-deep-research
Openrouter, Perplexity
2 offers
128000 token context 128,000
$2.00 / $8.00
per 1M tokens, when known
September 1, 2025
Perplexity: Sonar Reasoning Pro
sonar-reasoning-pro
Openrouter, Perplexity
2 offers
128000 token context 128,000
$2.00 / $8.00
per 1M tokens, when known
September 1, 2025
Pixtral 12B
pixtral-12b
Mistral
1 offer
128000 token context 128,000
$0.15 / $0.15
per 1M tokens, when known
September 1, 2024
Pixtral Large (latest)
pixtral-large-latest
Mistral
1 offer
128000 token context 128,000
$2.00 / $6.00
per 1M tokens, when known
November 4, 2024
Qwen 3 235B A22B Instruct 2507
qwen3-235b-a22b-instruct-2507
Venice
1 offer
128000 token context 128,000
$0.15 / $0.75
per 1M tokens, when known
June 11, 2026
Qwen 3.5 397B
qwen3-5-397b-a17b
Venice
1 offer
128000 token context 128,000
$0.75 / $4.50
per 1M tokens, when known
June 11, 2026
Qwen: Qwen2.5 VL 72B Instruct
qwen2.5-vl-72b-instruct
Openrouter
1 offer
128000 token context 128,000
$0.25 / $0.75
per 1M tokens, when known
February 1, 2025
Ring-1T
ring-1t
Zenmux
1 offer
128000 token context 128,000
$0.56 / $2.24
per 1M tokens, when known
October 12, 2025
Sonar
sonar
Perplexity
1 offer
128000 token context 128,000
$1.00 / $1.00
per 1M tokens, when known
September 1, 2025
Upstage: Solar Pro 3
solar-pro-3
Openrouter
1 offer
128000 token context 128,000
$0.15 / $0.60
per 1M tokens, when known
January 27, 2026
Venice Role Play Uncensored
venice-uncensored-role-play
Venice
1 offer
128000 token context 128,000
$0.50 / $2.00
per 1M tokens, when known
June 11, 2026
Venice Uncensored 1.2
venice-uncensored-1-2
Venice
1 offer
128000 token context 128,000
$0.20 / $0.90
per 1M tokens, when known
June 11, 2026
Venice: Uncensored
cognitivecomputations/dolphin-mistral-24b-venice-edition
Openrouter
1 offer
128000 token context 128,000
$0.20 / $0.90
per 1M tokens, when known
July 9, 2025

How the context ranking works

The page orders active text-generation identities by their largest recorded provider context limit.

Inclusion criteria

  • The model identity has at least one offer that passes the active text-generation rules.
  • The largest recorded context window is from 128,000 through 10 million tokens.

Exclusions

  • The list excludes missing and nonnumeric context values.
  • The list excludes values above 10 million tokens as unverified outliers.

Data rules

  • Context value: A grouped identity uses the largest recorded context limit among its eligible provider offers.
  • Ordering: Model identities are ordered by context size, then name and model ID for stable output.

Limits of the data

  • A large context window does not prove strong recall, reasoning, speed, or low cost across the full window.
  • Providers can apply different context limits to the same model identity.

Read context limits with care

The advertised limit is only one part of long-context performance. Test retrieval quality, latency, and total prompt cost with data that matches your application.

Sources

  • llm_db — Source for active offers and recorded model context limits. Checked 2026-07-30.