reflectionReleased 2 days ago
Reflection: Beam 1.0 501B A23B
Apache-2.0 text model with 501B total and 23B active parameters; ships BF16, FP8 and NVFP4 weights.
1M context501BTool callingStructured output
Explore models.
Choose a category in More filters to see relevant price sorts.
metaReleased 3 days ago
Meta: Muse Spark Open
OpenRouter lists a 1,048,576-token context and up to 943,718 output tokens for this open-weight model aimed at agentic coding.
1M contextImage inputAudio input
NVIDIAReleased 3 days ago
Nemotron 3.5 Super VL
120B/12B-active Mamba-2 hybrid with a vision encoder; native speculative decoding and switchable thinking.
1M context120BReasoningImage input
AA IntelligenceEffort not specified26.49LiveBenchEffort: max · single run · equal mean of 7 suites51.47%
Price not listed
xiaomiReleased 27 days ago
Xiaomi: MiMo-V2.6-Pro
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...
1.1M contextImage inputAudio input
AA IntelligenceEffort not specified46.32LiveBenchEffort: high · single run · equal mean of 7 suites74.87%
$0.43in$0.87out/ 1M tokens · USDDeepInfra · via OpenRouter · 6 endpointsdeepinfra/fp8 · quantization=fp8
stepfun-aiReleased 30 days ago
Step-5-Preview
600B total and 27B active parameters; accepts images and video, with FP8 and BF16 weights for deployment.
1M contextImage inputVideo input
deepseekReleased Sep 10
DeepSeek: DeepSeek V4.1 Flash
Causal encoder-decoder activates 8B parameters for input and 16B for output, reducing the compute needed for long inputs.
1M contextImage inputTool calling
Institute of Foundation ModelsReleased Sep 3
K2 Horizon 375B A23B
524.3K context375BReasoningOpen weights
Price not listed
qwenListed Aug 26
Qwen: Qwen3.8 Flash
Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis,…
1M contextImage inputVideo input
zai-orgReleased Aug 26
GLM-5.3-Flash
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context…
1M contextImage inputVideo input
deepseek-aiListed Aug 21
DeepSeek-V4-Flash-Vision-Exp
DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and…
1M contextImage inputTool calling
$0.2156in$0.6468out/ 1M tokens · USDDeepInfra · via OpenRouter · 6 endpointsdeepinfra/fp8 · quantization=fp8
zai-orgReleased Aug 18
GLM-5.3
Reuses the GLM-5.2 base with new post-training; exposes low, high and max reasoning effort, defaulting to max.
1M contextTool callingStructured output
QwenReleased Aug 14
Qwen3.8-27B
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking…
1M context27BImage inputVideo input
AA IntelligenceEffort: xhigh · Xhigh33.68LiveBenchEffort: max · single run · equal mean of 7 suites62.66%
$0.02in$0.50out/ 1M tokens · USDTenstorrent · via OpenRouter · 28 endpointstenstorrent/fp4 · quantization=fp4
qwenListed Aug 8
Qwen: Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...
1M contextTool callingStructured output
nvidiaListed Aug 1
NVIDIA: Nemotron 3.5 Lightning
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
262.1K contextTool callingStructured output
$0.025in$0.12out/ 1M tokens · USDDarkbloom · via OpenRouter · 7 endpointsdarkbloom/int4 · quantization=int4
moonshotaiReleased Jul 16
Kimi-K3
2.8T total and 104B active parameters; combines Kimi Delta Attention with native image/video input under the Kimi K3 license.
1M contextImage inputVideo input
AA IntelligenceEffort: max · Max43.59LiveBenchEffort: max · single run · equal mean of 7 suites63.39%
$0.27in$14.00out/ 1M tokens · USDRelace · via OpenRouter · 37 endpointsrelace/fp4 · quantization=fp4
thinkingmachinesReleased Jul 15
Thinking Machines: Inkling
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and…
1M contextImage inputAudio input
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
googleListed Mar 11
Google: Gemma 4 31B
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 input
$0.10in$0.34out/ 1M tokens · USDCoreWeave · via OpenRouter · 20 endpointscoreweave/fp4 · quantization=fp4
Price not listed
Price not listed