🌐All Models💬Text Generation💻Code & Reasoning👁️Vision & Multimodal🎨Image Generation🎙️Audio & Speech🤖Agents & Tools📄Long Context🆓Free & Open🧠Reasoning🌍Multilingual
📄 Long Context
408 models · Page 1 of 12
Qwen2.5 1.5B
qwen
Qwen2.5 1.5B — Alibaba's Qwen series language model with strong multilingual and coding capabilities.
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Qwen3.5 397B A17b Fp8
qwen
Qwen3.5 397B A17b Fp8 — Alibaba's Qwen series language model with strong multilingual and coding capabilities.
textfreelong-context
262,144 ctxFree in
Explore specs and pricingView details →
Ministral 3 14B Instruct 2512
mistralai
textinstructcheap
262,144 ctx$0.20/1M in
Explore specs and pricingView details →
Minimax M1 40K
minimaxai
textfreelong-context
1,048,576 ctxFree in
Explore specs and pricingView details →
Llama 4 Maverick 17B 128E
meta-llama
textfreelong-context
262,144 ctxFree in
Explore specs and pricingView details →
Nvidia Nemotron Nano 9B V2
nvidia
textcheaplong-context
131,072 ctx$0.06/1M in
Explore specs and pricingView details →
Meta Llama 3.2 3B
meta-llama
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Qwen QwQ-32B
qwen
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks,...
textreasoninglong-context
131,072 ctx$1.20/1M in
Explore specs and pricingView details →
Nvidia Nemotron 3 Super 120B A12b Fp8
nvidia
textfreelong-context
262,144 ctxFree in
Explore specs and pricingView details →
Deepcoder 14B Preview
agentica-org
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Deepseek V3.1 Terminus
deepseek-ai
textfreelong-context
163,840 ctxFree in
Explore specs and pricingView details →
MiniMax M2
minimaxai
textfreelong-context
196,608 ctxFree in
Explore specs and pricingView details →
Nvidia Nemotron 3 Nano 30B A3b Bf16
nvidia
textfreelong-context
262,144 ctxFree in
Explore specs and pricingView details →
Qwen2.5 7B
qwen
Qwen2.5 7B — Alibaba's Qwen series language model with strong multilingual and coding capabilities.
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Qwen3.5 9B Fp8
qwen
textfreelong-context
262,144 ctxFree in
Explore specs and pricingView details →
Minimax M1 80K
minimaxai
textfreelong-context
1,048,576 ctxFree in
Explore specs and pricingView details →
Meta Llama 3.2 1B Instruct
meta-llama
textinstructcheap
131,072 ctx$0.06/1M in
Explore specs and pricingView details →
Qwen3-VL-235B-A22B-Instruct-FP8
qwen
textinstructfree
262,144 ctxFree in
Explore specs and pricingView details →
Qwen2.5 14B
qwen
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
DeepSeek R1 0528
deepseek-ai
textlong-context
163,840 ctx$3.00/1M in
Explore specs and pricingView details →
Qwen2.5 72B
qwen
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Glm 4.5 Air Fp8
zai-org
textcheaplong-context
131,072 ctx$0.20/1M in
Explore specs and pricingView details →
Qwen2.5 72B Instruct Turbo
qwen
textinstructlong-context
131,072 ctx$1.20/1M in
Explore specs and pricingView details →
Kimi K2 Thinking
moonshotai
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
textreasoningagents
262,144 ctx$1.20/1M in
Explore specs and pricingView details →
Qwen3 30B A3B Instruct 2507 Lora
qwen
textinstructfree
262,144 ctxFree in
Explore specs and pricingView details →
Nvidia Nemotron 3 Super 120B A12b Bf16
nvidia
textfreelong-context
262,144 ctxFree in
Explore specs and pricingView details →
Deepseek V3.2
deepseek-ai
textfreelong-context
163,840 ctxFree in
Explore specs and pricingView details →
Deepseek V3.2 Exp
deepseek-ai
textfreelong-context
163,840 ctxFree in
Explore specs and pricingView details →
DeepSeek R1 (Original)
deepseek-ai
textfreelong-context
163,840 ctxFree in
Explore specs and pricingView details →
Llama 4 Maverick Instruct (17Bx128E) FP8
meta-llama
textinstructcheap
1,048,576 ctx$0.27/1M in
Explore specs and pricingView details →
Llama 3.2 1B
meta-llama
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Qwen3 4B Instruct 2507
qwen
textinstructfree
262,144 ctxFree in
Explore specs and pricingView details →
Meta Llama 3.1 8B Instruct Turbo
meta-llama
textinstructcheap
131,072 ctx$0.18/1M in
Explore specs and pricingView details →
Llama 3.1 405B
meta-llama
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Devstral Small 2505
mistralai
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →
Llama 3.1 70B
meta-llama
Llama 3.1 70B — Meta's Llama open-source language model, one of the most widely deployed open models.
textfreelong-context
131,072 ctxFree in
Explore specs and pricingView details →