Price not listed
Explore models.
Choose a category in More filters to see relevant price sorts.
rekaaiListed Mar 20
Reka Edge
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading…
16.4K contextImage inputVideo inputNo reported score
No reported score
minimaxListed Mar 18
MiniMax: MiniMax M2.7
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates…
204.8K contextTool callingStructured outputNo reported score
No reported score
$0.21in$0.84out/ 1M tokens · USDGMICloud · via OpenRouter · 10 endpointsgmicloud/fp8 · quantization=fp8
mistralaiListed Mar 16
Mistral: Mistral Small 4
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
262.1K contextImage inputTool callingNo reported score
No reported score
mistralaiListed Mar 16
Mistral: Mistral Small 4 (batch)
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
262.1K contextImage inputTool callingNo reported score
No reported score
googleListed Mar 11
Google: Gemma 4 26B A4B
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
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
nvidiaListed Mar 11
NVIDIA: Nemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid…
262.1K context120BTool callingStructured outputNo reported score
No reported score
$0.08in$0.45out/ 1M tokens · USDDekaLLM · via OpenRouter · 4 endpointsdekallm/fp8 · quantization=fp8
nvidiaListed Mar 11
NVIDIA: Nemotron 3 Super (free)
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid…
262.1K context120BTool callingStructured outputNo reported score
No reported score
fish-audioReleased Mar 10
Fish Audio: S2 Pro
S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited for expressive narration and multi-speaker dialogue, with natural-language controls for speaking style and emotion.
Open weights
Price not listed
Price not listed
Price not listed
QwenListed Feb 27
Qwen3.5-9B
Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool…
262.1K context9BImage inputVideo inputNo reported score
No reported score
$0.08in$0.13out/ 1M tokens · USDDarkbloom · via OpenRouter · 12 endpointsdarkbloom/fp4 · quantization=fp4
Price not listed
nvidiaListed Feb 25
NVIDIA: Llama Nemotron Embed VL 1B V2 (free)
The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text...
131.1K context1BImage inputOpen weightsNo reported score
No reported score
qwenListed Feb 24
Qwen: Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference…
262.1K context122BImage inputVideo inputNo reported score
No reported score
QwenListed Feb 24
Qwen3.5-27B
Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M),…
262.1K context27BImage inputVideo inputNo reported score
No reported score
$0.25in$2.00out/ 1M tokens · USDSiliconFlow · via OpenRouter · 11 endpointssiliconflow/fp8 · quantization=fp8
QwenListed Feb 24
Qwen3.5-35B-A3B
Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M…
262.1K context35BImage inputVideo inputNo reported score
No reported score
$0.065in$0.75out/ 1M tokens · USDDarkbloom · via OpenRouter · 11 endpointsdarkbloom/fp4 · quantization=fp4
QwenListed Feb 16
Qwen3.5-397B-A17B
Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M…
262.1K context397BImage 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
No reported score
Price not listed
minimaxListed Feb 12
MiniMax: MiniMax M2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
204.8K contextTool callingStructured outputNo reported score
No reported score