Explore models.

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

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

4 models · newest firstPage 1 / 1

More filters

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

$0.25in$1.00out/ 1M tokens · USDNebius · via OpenRouternebius/fp8 · quantization=fp8

metaReleased 3 days ago

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

$1.25in$4.25out/ 1M tokens · USDNebius · via OpenRouternebius/fp4 · quantization=fp4

deepseekReleased Sep 10

Causal encoder-decoder activates 8B parameters for input and 16B for output, reducing the compute needed for long inputs.

1M contextImage inputTool calling

$0.30in$1.20out/ 1M tokens · USDNebius · via OpenRouternebius/fp8 · quantization=fp8

zai-orgReleased Aug 18

Reuses the GLM-5.2 base with new post-training; exposes low, high and max reasoning effort, defaulting to max.

1M contextTool callingStructured output

$1.40in$4.40out/ 1M tokens · USDNebius · via OpenRouternebius/fp4 · quantization=fp4