reflectionReleased 1 day 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 2 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
googleReleased 11 days ago
Google: Nano Banana 2.1
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...
65.5K contextImage inputTool calling
googleReleased 17 days ago
Google: Gemini 4 Argon
Long decode can use the unified 1M-token budget for output; reads video, audio and PDFs, with implicit-only caching.
1M contextImage inputAudio input
AA IntelligenceEffort: high · High52.56LiveBenchEffort: high · single run · equal mean of 7 suites84.1%
$1.00in$5.00out/ 1M tokens · USDGoogle AI Studio · via OpenRouter · 8 endpointsgoogle-ai-studio/flex · tier=flex
openaiReleased 18 days ago
OpenAI: GPT-6.1 Sol
Requires Responses API for tools; offers Ultrafast inference with US or EU data residency.
1.1M contextImage inputTool calling
AA IntelligenceEffort: max · Max51.83LiveBenchEffort: max · single run · equal mean of 7 suites85.41%
$1.00in$5.00out/ 1M tokens · USDOpenAI · via OpenRouter · 10 endpointsopenai/flex · tier=flex · prompt ≤ 272000 tokens
anthropicReleased 19 days ago
Anthropic: Claude Sonnet 5.5
Tuned for quick iteration on scoped fixes and documents; Anthropic favors Opus 5.5 for open-ended work needing sustained judgment.
1M contextImage inputTool calling
anthropicReleased 25 days ago
Anthropic: Claude Opus 5.5
Always-on adaptive thinking defaults to medium effort; built for sustained work across large codebases and professional documents.
1M contextImage inputTool calling
openaiReleased 25 days ago
OpenAI: GPT-6 Luna
Can turn reasoning off for high-volume requests; Chat Completions tool calls require reasoning_effort=none.
1.1M contextImage inputTool calling
AA IntelligenceEffort: max · Max38.12LiveBenchEffort: max · single run · equal mean of 7 suites69.4%
$0.05in$0.25out/ 1M tokens · USDOpenAI · via OpenRouter · 9 endpointsopenai/flex · tier=flex · prompt ≤ 272000 tokens
xiaomiReleased 26 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 29 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
openaiReleased Sep 3
OpenAI: GPT-6 Astra
Accepts mid-turn steering and async tool calls, so agents can take new instructions while other tools are still running.
1.1M contextImage inputTool calling
AA IntelligenceEffort: max · Max52.67LiveBenchEffort: max · single run · equal mean of 7 suites86.14%
$5.00in$25.00out/ 1M tokens · USDOpenAI · via OpenRouter · 9 endpointsopenai/flex · tier=flex · prompt ≤ 272000 tokens
anthropicReleased Sep 1
Anthropic: Claude Fable 5.1
Beta controls change effort per message without invalidating the prompt cache and report progress between tool calls.
1M contextImage inputTool calling
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