All Coding Research Images Video Audio 3D Free API access Open weights ✓ Has benchmark results✓ Has pricingSR Provider: Sail Research × Has benchmark results × Has pricing × Clear filters Choose a category in More filters to see relevant price sorts.
Model / what’s different Benchmark results API price Explore
deepseek Released Sep 10
Causal encoder-decoder activates 8B parameters for input and 16B for output, reducing the compute needed for long inputs.
1M context Image input Tool calling
$0.101in $0.15out / 1M tokens · USD Sail Research · via OpenRouter · 2 endpoints sail-research/fp4/us · quantization=fp4 zai-org Released Aug 26
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 context Image input Video input
$0.09in $0.15out / 1M tokens · USD Sail Research · via OpenRouter · 2 endpoints sail-research/us · quantization=fp4 zai-org Released Aug 18
Reuses the GLM-5.2 base with new post-training; exposes low, high and max reasoning effort, defaulting to max.
1M context Tool calling Structured output
$0.75in $1.00out / 1M tokens · USD Sail Research · via OpenRouter · 2 endpoints sail-research/us · quantization=fp8 moonshotai Released Jul 16
2.8T total and 104B active parameters; combines Kimi Delta Attention with native image/video input under the Kimi K3 license.
1M context Image input Video input
$1.20in $5.50out / 1M tokens · USD Sail Research · via OpenRouter · 2 endpoints sail-research/fp4/us · quantization=fp4