Explore models.

2,815 models1,617 with prices34 metricsUpdated Oct 18, 2026 ↗

Choose a category in More filters to see relevant price sorts.

8 models · newest firstPage 1 / 1

More filters

deepseek-aiListed Today

DeepSeek-V4.1-Flash-1017

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model…

1M contextImage inputTool calling

LiveBenchEffort: max · single run · equal mean of 7 suites79.2%

$0.08in$0.50out/ 1M tokens · USDInferenceNet · via OpenRouterinference-net/fp8 · quantization=fp8

+Compare

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

AA IntelligenceEffort not specified43.73 LiveBenchEffort: max · single run · equal mean of 7 suites62.01%

$1.00in$2.70out/ 1M tokens · USDInferenceNet · via OpenRouterinference-net/fp4 · quantization=fp4

+Compare

inference-netListed Sep 12

Inference.net: Schematron V2 Turbo

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a…

128K contextStructured outputPrompt cachingNo reported score

No reported score

$0.03in$0.15out/ 1M tokens · USDInferenceNet · via OpenRouterinference-net/bf16 · quantization=bf16

+Compare

inference-netListed Sep 12

Inference.net: Schematron V2 Small

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through…

128K contextStructured outputPrompt cachingNo reported score

No reported score

$0.05in$0.23out/ 1M tokens · USDInferenceNet · via OpenRouterinference-net/bf16 · quantization=bf16

+Compare

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

AA IntelligenceEffort: max · Max39.46 LiveBenchEffort: max · single run · equal mean of 7 suites78.04%

$0.103in$0.715out/ 1M tokens · USDInferenceNet · via OpenRouterinference-net/fp8 · quantization=fp8

+Compare

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

AA IntelligenceEffort: max41.81 LiveBenchEffort: max · single run · equal mean of 7 suites70.61%

$0.12in$0.388out/ 1M tokens · USDInferenceNet · via OpenRouterinference-net/fp4 · quantization=fp4

+Compare

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

AA IntelligenceEffort: max · Max44.78 LiveBenchEffort: max · single run · equal mean of 7 suites60.74%

$0.08in$4.381out/ 1M tokens · USDInferenceNet · via OpenRouterinference-net/fp4 · quantization=fp4

+Compare

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 · Max43.59 LiveBenchEffort: max · single run · equal mean of 7 suites63.39%

$0.304in$11.936out/ 1M tokens · USDInferenceNet · via OpenRouter · 2 endpointsinference-net/fp4 · quantization=fp4

+Compare