MiniMaxAIReleased Jun 1
MiniMax-M3
MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.
1M contextImage inputOpen weights
Explore models.
Choose a category in More filters to see relevant price sorts.
minimaxListed May 31
MiniMax: MiniMax M3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
1M contextImage inputVideo inputNo reported score
No reported score
$0.224in$0.88out/ 1M tokens · USDDeepInfra · via OpenRouter · 15 endpointsdeepinfra/fp8/flex · tier=flex · quantization=fp8
Price not listed
Price not listed
stepfunListed May 23
StepFun: Step 3.7 Flash
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating…
262.1K contextImage inputVideo inputNo reported score
No reported score
No reported score
Price not listed
No reported score
Price not listed
No reported score
Price not listed
Price not listed
Price not listed
nvidiaListed Apr 28
NVIDIA: Nemotron 3 Nano Omni (free)
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
256K context30BImage inputAudio inputNo reported score
No reported score
tencentListed Apr 22
Tencent: Hy3 preview
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes,…
262.1K contextTool callingReasoningNo reported score
No reported score
$0.18in$0.60out/ 1M tokens · USDGMICloud · via OpenRouter · 2 endpointsgmicloud/bf16 · quantization=bf16
xiaomiListed Apr 22
Xiaomi: MiMo-V2.5-Pro
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as…
1.1M contextTool callingStructured outputNo reported score
No reported score
$0.3045in$0.609out/ 1M tokens · USDGMICloud · via OpenRouter · 9 endpointsgmicloud/bf16 · quantization=bf16
xiaomiListed Apr 22
Xiaomi: MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video…
1.1M contextImage inputAudio inputNo reported score
No reported score
deepseek-aiListed Apr 22
DeepSeek-V4-Pro
DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on…
1M contextTool callingStructured outputNo reported score
No reported score
$0.1775in$0.3549out/ 1M tokens · USDBaidu · via OpenRouter · 22 endpointsbaidu/fp8 · quantization=fp8
deepseek-aiListed Apr 22
DeepSeek-V4-Flash
DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up…
1M contextTool callingStructured outputNo reported score
No reported score
$0.0134in$0.45out/ 1M tokens · USDRelace · via OpenRouter · 21 endpointsrelace/fp4 · quantization=fp4
qwenListed Apr 21
Qwen: Qwen3.6 27B
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
262.1K context27BImage inputVideo inputNo reported score
No reported score
QwenListed Apr 15
Qwen3.6-35B-A3B
Qwen3.6-35B-A3B is Alibaba's latest flagship Mixture-of-Experts model, with 35B total parameters and only 3B activated per token (256 experts, 8 routed + 1 shared). Built on direct feedback from the…
262.1K context35BImage inputVideo inputNo reported score
No reported score
$0.05in$0.70out/ 1M tokens · USDDarkbloom · via OpenRouter · 15 endpointsdarkbloom/fp4 · quantization=fp4
Price not listed
Price not listed
moonshotaiListed Apr 14
MoonshotAI: Kimi K2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks…
262.1K contextImage inputTool callingNo reported score
No reported score
googleListed Apr 3
Google: Gemma 4 26B A4B (free)
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
262.1K context26BImage inputVideo inputNo reported score
No reported score
z-aiListed Apr 3
Z.ai: GLM 5.1
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work…
204.8K contextTool callingStructured outputNo reported score
No reported score
$0.9646in$3.0316out/ 1M tokens · USDBaidu · via OpenRouter · 17 endpointsbaidu/fp8 · quantization=fp8
googleListed Apr 2
Google: Gemma 4 31B (free)
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native…
262.1K context31BImage inputVideo inputNo reported score
No reported score