Llama 4 Scout
Oct 4, 2026Meta
- Context
- 10,000,000
- Max output
- —
- Family
- Llama 4
- Input
- Text, Image
0 mapped APIsView model →
Reference view
Model Context Windows
Compare the documented context and output limits of indexed models, with provider, family, modality and API context from the iilib knowledge graph.
A larger context window is a capacity limit, not a quality score. Effective usable context, pricing, latency, tool behavior and provider-specific restrictions can differ by workload and API.
Indexed models
34
With context data
34
Largest mapped context
10,000,000
Multimodal input
20
Specification table
Context and output limits
Rows are sorted by documented context-window size. Missing values remain visible as unknown rather than inferred.
GPT-5.6 Luna
Oct 4, 2026OpenAI
- Context
- 1,050,000
- Max output
- 128,000
- Family
- GPT-5.6
- Input
- Text, Image
1 mapped APIView model →
GPT-5.6 Sol
Oct 3, 2026OpenAI
- Context
- 1,050,000
- Max output
- 128,000
- Family
- GPT-5.6
- Input
- Text, Image
1 mapped APIView model →
GPT-5.6 Terra
Oct 3, 2026OpenAI
- Context
- 1,050,000
- Max output
- 128,000
- Family
- GPT-5.6
- Input
- Text, Image
1 mapped APIView model →
GPT-6 Astra
Oct 3, 2026OpenAI
- Context
- 1,050,000
- Max output
- 128,000
- Family
- GPT-6
- Input
- Text, Image
1 mapped APIView model →
GPT-6 Luna
Oct 6, 2026OpenAI
- Context
- 1,050,000
- Max output
- 128,000
- Family
- GPT-6
- Input
- Text, Image
1 mapped APIView model →
GPT-6 Sol
Oct 6, 2026OpenAI
- Context
- 1,050,000
- Max output
- 128,000
- Family
- GPT-6
- Input
- Text, Image
1 mapped APIView model →
GPT-6.1 Sol
Oct 3, 2026OpenAI
- Context
- 1,050,000
- Max output
- 128,000
- Family
- GPT-6
- Input
- Text, Image
1 mapped APIView model →
GLM-5.3
Oct 5, 2026Z.ai
- Context
- 1,048,576
- Max output
- —
- Family
- GLM-5.3
- Input
- Text
0 mapped APIsView model →
GLM-5.3-Flash
Oct 5, 2026Z.ai
- Context
- 1,048,576
- Max output
- —
- Family
- GLM-5.3
- Input
- Text, Image, Video
0 mapped APIsView model →
Kimi K3
Oct 5, 2026Moonshot AI
- Context
- 1,048,576
- Max output
- —
- Family
- Kimi K3
- Input
- Text, Image, Video
0 mapped APIsView model →
Claude Fable 5.1
Oct 3, 2026Anthropic
- Context
- 1,000,000
- Max output
- 128,000
- Family
- Claude 5.1
- Input
- Text, Image
1 mapped APIView model →
Claude Opus 5.5
Oct 3, 2026Anthropic
- Context
- 1,000,000
- Max output
- 128,000
- Family
- Claude 5.5
- Input
- Text, Image
1 mapped APIView model →
Claude Sonnet 5.5
Oct 3, 2026Anthropic
- Context
- 1,000,000
- Max output
- 128,000
- Family
- Claude 5.5
- Input
- Text, Image
1 mapped APIView model →
DeepSeek V4 Pro
Oct 3, 2026DeepSeek
- Context
- 1,000,000
- Max output
- 384,000
- Family
- DeepSeek V4
- Input
- Text
1 mapped APIView model →
DeepSeek V4.1 Flash
Oct 3, 2026DeepSeek
- Context
- 1,000,000
- Max output
- 384,000
- Family
- DeepSeek V4
- Input
- Text, Image
1 mapped APIView model →
Gemini 3.8 Flash
Oct 3, 2026Google
- Context
- 1,000,000
- Max output
- 64,000
- Family
- Gemini 3
- Input
- Text, Image, Audio, Video, File
1 mapped APIView model →
Llama 4 Maverick
Oct 4, 2026Meta
- Context
- 1,000,000
- Max output
- —
- Family
- Llama 4
- Input
- Text, Image
0 mapped APIsView model →
Nemotron 3.5 Lightning
Oct 5, 2026NVIDIA
- Context
- 1,000,000
- Max output
- —
- Family
- Nemotron 3.5
- Input
- Text
0 mapped APIsView model →
Qwen3-Coder-Plus
Oct 3, 2026Alibaba Cloud
- Context
- 1,000,000
- Max output
- 65,536
- Family
- Qwen3-Coder
- Input
- Text
1 mapped APIView model →
Grok 4.7
Oct 3, 2026SpaceXAI
- Context
- 500,000
- Max output
- —
- Family
- Grok 4
- Input
- Text, Image
1 mapped APIView model →
Gemma 4 12B
Oct 4, 2026Google
- Context
- 256,000
- Max output
- —
- Family
- Gemma 4
- Input
- Text, Image, Audio
0 mapped APIsView model →
Gemma 4 26B A4B
Oct 4, 2026Google
- Context
- 256,000
- Max output
- —
- Family
- Gemma 4
- Input
- Text, Image
0 mapped APIsView model →
Mistral Medium 3.5
Oct 3, 2026Mistral AI
- Context
- 256,000
- Max output
- —
- Family
- Mistral Medium
- Input
- Text, Image
1 mapped APIView model →
gpt-oss-120b
Oct 3, 2026OpenAI
- Context
- 131,072
- Max output
- —
- Family
- gpt-oss
- Input
- Text
1 mapped APIView model →
DeepSeek-R1-0528
Oct 4, 2026DeepSeek
- Context
- 128,000
- Max output
- —
- Family
- DeepSeek R1
- Input
- Text
0 mapped APIsView model →
DeepSeek-V3-0324
Oct 4, 2026DeepSeek
- Context
- 128,000
- Max output
- —
- Family
- DeepSeek V3
- Input
- Text
0 mapped APIsView model →
Qwen3-235B-A22B
Oct 4, 2026Alibaba Cloud
- Context
- 128,000
- Max output
- —
- Family
- Qwen3
- Input
- Text
0 mapped APIsView model →
Qwen3-30B-A3B
Oct 4, 2026Alibaba Cloud
- Context
- 128,000
- Max output
- —
- Family
- Qwen3
- Input
- Text
0 mapped APIsView model →
Oct 5, 2026
- Context
- 65,536
- Max output
- —
- Family
- Olmo 3
- Input
- Text
0 mapped APIsView model →
Oct 5, 2026
- Context
- 65,536
- Max output
- —
- Family
- Olmo 3
- Input
- Text
0 mapped APIsView model →
Qwen3-4B
Oct 4, 2026Alibaba Cloud
- Context
- 32,000
- Max output
- —
- Family
- Qwen3
- Input
- Text
0 mapped APIsView model →
Qwen3-Embedding-0.6B
Oct 4, 2026Alibaba Cloud
- Context
- 32,000
- Max output
- —
- Family
- Qwen3 Embedding
- Input
- Text
0 mapped APIsView model →
Qwen3-Reranker-0.6B
Oct 4, 2026Alibaba Cloud
- Context
- 32,000
- Max output
- —
- Family
- Qwen3 Reranker
- Input
- Text
0 mapped APIsView model →
Coverage
14 models with output-limit data
Unknown values are not filled from estimates. The table changes only when the underlying model record is updated from a primary source.
Cost context
Context size is only one constraint
For token pricing alongside these limits, use the graph-derived pricing reference.
Open LLM API Pricing →