Explore models.

2,827 models1,620 with prices34 metricsUpdated Oct 20, 2026 ↗

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

4 models · newest firstPage 1 / 1

More filters

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

LiveBenchEffort: max · single run · equal mean of 7 suites78.04%

$0.09in$0.18out/ 1M tokens · USDDecart · via OpenRouterdecart/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%

$0.84in$2.68out/ 1M tokens · USDDecart · via OpenRouterdecart/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%

$1.65in$8.25out/ 1M tokens · USDDecart · via OpenRouterdecart/mxfp4 · quantization=mxfp4

+Compare

zai-orgListed Jun 16

GLM-5.2 is Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on…

1M contextTool callingStructured outputNo reported score

No reported score

$2.50in$9.00out/ 1M tokens · USDDecart · via OpenRouterdecart/fast · tier=priority · quantization=fp4

+Compare