Catalog data · Updated July 24, 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
595
Long-context identities
26
Providers shown
1
Data sections
6,154
Catalog records

Largest context windows

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

Showing 50 of 595

Model Provider offers Why listed Context Input / output price Updated
GPT-5.2
openai-gpt-52
Venice
1 offer
256000 token context 256,000
$2.19 / $17.50
per 1M tokens, when known
June 11, 2026
GPT-5.2 Codex
openai-gpt-52-codex
Venice
1 offer
256000 token context 256,000
$2.19 / $17.50
per 1M tokens, when known
June 11, 2026
Grok 4
grok-4
Zenmux
1 offer
256000 token context 256,000
$3.00 / $15.00
per 1M tokens, when known
July 9, 2025
Grok Build 0.1
grok-build-0-1
Venice
1 offer
256000 token context 256,000
$1.00 / $2.00
per 1M tokens, when known
June 11, 2026
Grok Build 0.1
grok-build-0.1
Opencode, Openrouter, Xai +1
4 offers
256000 token context 256,000
$1.00 / $2.00
per 1M tokens, when known
May 20, 2026
Grok Code Fast 1
grok-code-fast-1
Zenmux
1 offer
256000 token context 256,000
$0.20 / $1.50
per 1M tokens, when known
August 26, 2025
Kimi K2.5
kimi-k2-5
Venice
1 offer
256000 token context 256,000
$0.56 / $3.50
per 1M tokens, when known
June 11, 2026
Kimi K2.6
kimi-k2-6
Venice
1 offer
256000 token context 256,000
$0.75 / $3.50
per 1M tokens, when known
June 11, 2026
Kimi K2.7 Code
kimi-k2-7-code
Venice
1 offer
256000 token context 256,000
$0.75 / $3.50
per 1M tokens, when known
June 16, 2026
Kwaipilot: KAT-Coder-Air V2.5
kat-coder-air-v2.5
Openrouter
1 offer
256000 token context 256,000
$0.15 / $0.60
per 1M tokens, when known
July 10, 2026
Kwaipilot: KAT-Coder-Pro V2.5
kat-coder-pro-v2.5
Openrouter
1 offer
256000 token context 256,000
$0.74 / $2.96
per 1M tokens, when known
July 10, 2026
Mistral Small (latest)
mistral-small-latest
Mistral
1 offer
256000 token context 256,000
$0.15 / $0.60
per 1M tokens, when known
March 16, 2026
Mistral Small 3.2 24B Instruct
mistral-small-3-2-24b-instruct
Venice
1 offer
256000 token context 256,000
$0.09 / $0.25
per 1M tokens, when known
June 11, 2026
Mistral Small 4
mistral-small-2603
Mistral, Venice
2 offers
256000 token context 256,000
$0.15 / $0.60
per 1M tokens, when known
June 11, 2026
Mistral: Codestral 2508
codestral-2508
Openrouter
1 offer
256000 token context 256,000
$0.30 / $0.90
per 1M tokens, when known
August 1, 2025
Mistral: Mistral Small 3.2 24B
mistralai/mistral-small-3.2-24b-instruct
Openrouter
1 offer
256000 token context 256,000
$0.10 / $0.30
per 1M tokens, when known
June 20, 2025
Nemotron 3 Super 120B
@cf/nvidia/nemotron-3-120b-a12b
Cloudflare workers ai
1 offer
256000 token context 256,000
$0.50 / $1.50
per 1M tokens, when known
March 11, 2026
Nemotron Cascade 2 30B A3B
nvidia-nemotron-cascade-2-30b-a3b
Venice
1 offer
256000 token context 256,000
$0.14 / $0.80
per 1M tokens, when known
June 11, 2026
North Mini Code
north-mini-code-1-0
Cohere
1 offer
256000 token context 256,000
$0.00 / $0.00
per 1M tokens, when known
June 9, 2026
North Mini Code Free
north-mini-code-free
Opencode
1 offer
256000 token context 256,000
$0.00 / $0.00
per 1M tokens, when known
June 9, 2026
NVIDIA Nemotron 3 Ultra
nvidia-nemotron-3-ultra-550b-a55b
Venice
1 offer
256000 token context 256,000
$0.63 / $3.13
per 1M tokens, when known
June 11, 2026
NVIDIA: Nemotron 3 Nano 30B A3B (free)
nemotron-3-nano-30b-a3b:free
Openrouter
1 offer
256000 token context 256,000
$0.00 / $0.00
per 1M tokens, when known
December 15, 2025
NVIDIA: Nemotron 3 Nano Omni (free)
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
Openrouter
1 offer
256000 token context 256,000
$0.00 / $0.00
per 1M tokens, when known
April 28, 2026
Qwen 3 Coder 480B Turbo
qwen3-coder-480b-a35b-instruct-turbo
Venice
1 offer
256000 token context 256,000
$0.35 / $1.50
per 1M tokens, when known
June 11, 2026
Qwen 3 Next 80b
qwen3-next-80b
Venice
1 offer
256000 token context 256,000
$0.35 / $1.90
per 1M tokens, when known
June 11, 2026
Qwen 3.5 35B A3B
qwen3-5-35b-a3b
Venice
1 offer
256000 token context 256,000
$0.31 / $1.25
per 1M tokens, when known
June 11, 2026
Qwen 3.5 9B
qwen3-5-9b
Venice
1 offer
256000 token context 256,000
$0.10 / $0.15
per 1M tokens, when known
June 11, 2026
Qwen 3.6 27B
qwen3-6-27b
Venice
1 offer
256000 token context 256,000
$0.33 / $3.25
per 1M tokens, when known
June 11, 2026
Qwen 3.6 35B A3B
qwen3-6-35b-a3b
Venice
1 offer
256000 token context 256,000
$0.15 / $1.00
per 1M tokens, when known
July 22, 2026
Qwen3-VL 30B-A3B Instruct
Qwen3-VL-30B-A3B-Instruct
Nearai
1 offer
256000 token context 256,000
$0.15 / $0.55
per 1M tokens, when known
September 23, 2025
Relace: Relace Apply 3
relace-apply-3
Openrouter
1 offer
256000 token context 256,000
$0.85 / $1.25
per 1M tokens, when known
September 26, 2025
Relace: Relace Search
relace-search
Openrouter
1 offer
256000 token context 256,000
$1.00 / $3.00
per 1M tokens, when known
December 8, 2025
Seed 2.1 Turbo
seed-2-1-turbo
Venice
1 offer
256000 token context 256,000
$0.63 / $3.13
per 1M tokens, when known
July 24, 2026
Step 3.7 Flash (Free)
step-3.7-flash-free
Zenmux
1 offer
256000 token context 256,000
$0.00 / $0.00
per 1M tokens, when known
May 29, 2026
GLM-5
glm-5
Opencode, Zai
2 offers
204800 token context 204,800
$1.00 / $3.20
per 1M tokens, when known
February 12, 2026
GLM-5.1
glm-5.1
Ollama cloud, Opencode, Openrouter +2
5 offers
204800 token context 204,800
$0.88 / $3.51
per 1M tokens, when known
April 7, 2026
MiniMax-M2.1
MiniMax-M2.1
Minimax
1 offer
204800 token context 204,800
$0.30 / $1.20
per 1M tokens, when known
December 23, 2025
MiniMax-M2.5
MiniMax-M2.5
Friendli, Minimax, Togetherai
3 offers
204800 token context 204,800
$0.30 / $1.20
per 1M tokens, when known
February 12, 2026
MiniMax-M2.5-highspeed
MiniMax-M2.5-highspeed
Minimax
1 offer
204800 token context 204,800
$0.60 / $2.40
per 1M tokens, when known
February 13, 2026
MiniMax-M2.7
MiniMax-M2.7
Minimax, Togetherai
2 offers
204800 token context 204,800
$0.30 / $1.20
per 1M tokens, when known
March 18, 2026
MiniMax-M2.7-highspeed
MiniMax-M2.7-highspeed
Minimax
1 offer
204800 token context 204,800
$0.60 / $2.40
per 1M tokens, when known
March 18, 2026
minimax/minimax-m2.5-lightning
minimax-m2.5-lightning
Zenmux
1 offer
204800 token context 204,800
$0.60 / $4.80
per 1M tokens, when known
February 13, 2026
minimax/minimax-m2.7-highspeed
minimax-m2.7-highspeed
Zenmux
1 offer
204800 token context 204,800
$0.61 / $2.44
per 1M tokens, when known
March 20, 2026
MiniMax: MiniMax M2
minimax-m2
Openrouter, Zenmux
2 offers
204800 token context 204,800
$0.26 / $1.02
per 1M tokens, when known
October 27, 2025
MiniMax: MiniMax M2.1
minimax-m2.1
Openrouter, Zenmux
2 offers
204800 token context 204,800
$0.30 / $1.20
per 1M tokens, when known
December 23, 2025
MiniMax: MiniMax M2.5
minimax-m2.5
Ollama cloud, Opencode, Openrouter +1
4 offers
204800 token context 204,800
$0.15 / $0.90
per 1M tokens, when known
February 13, 2026
MiniMax: MiniMax M2.7
minimax-m2.7
Ollama cloud, Opencode, Openrouter +1
4 offers
204800 token context 204,800
$0.25 / $1.00
per 1M tokens, when known
March 20, 2026
Z.ai: GLM 4.6
glm-4.6
Openrouter, Zai, Zenmux
3 offers
204800 token context 204,800
$0.35 / $1.54
per 1M tokens, when known
September 30, 2025
Z.ai: GLM 4.7
glm-4.7
Openrouter, Zai, Zenmux
3 offers
204800 token context 204,800
$0.28 / $1.14
per 1M tokens, when known
December 23, 2025
Z.ai: GLM 5
z-ai/glm-5
Openrouter, Zenmux
2 offers
204800 token context 204,800
$0.58 / $2.60
per 1M tokens, when known
February 12, 2026

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.