All Coding Research Images Video Audio 3D Free API access ✓ Open weights✓ Has benchmark resultsHas pricing IN Provider: InferenceNet × Open weights × Has benchmark results × Clear filters Choose a category in More filters to see relevant price sorts.
Model / what’s different Benchmark results API price Explore
deepseek-ai Released 4 days ago
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 context Image input Tool calling
$0.08in $0.50out / 1M tokens · USD InferenceNet · via OpenRouter · 2 endpoints inference-net/us · quantization=fp8 stepfun-ai Released Sep 18
600B total and 27B active parameters; accepts images and video, with FP8 and BF16 weights for deployment.
1M context Image input Video input
$1.00in $2.70out / 1M tokens · USD InferenceNet · via OpenRouter inference-net/fp4 · quantization=fp4 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
$0.103in $0.715out / 1M tokens · USD InferenceNet · via OpenRouter inference-net/fp8 · quantization=fp8 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
$0.12in $0.388out / 1M tokens · USD InferenceNet · via OpenRouter inference-net/fp4 · 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
$0.08in $4.381out / 1M tokens · USD InferenceNet · via OpenRouter inference-net/fp4 · quantization=fp4 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
$0.239in $11.936out / 1M tokens · USD InferenceNet · via OpenRouter · 2 endpoints inference-net/fp4 · quantization=fp4