OvisOCR3
ATH-MaaS基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 84991
MicroGlot
athanzli基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Embedding
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tinyllama-cpt
atharvanighot基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗slm-tavenel-10m
athenista基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗slm-tavenel-1m
athenista基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗slm-tavenel-25m
athenista基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Llama-3-11b-Instruct
athirdpath基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗colqwen3.5-4.5B-v3
athrael-soju> **Note on embed dim.** Projection head is 320-dim (trained). `config.json` sets `dim: 320` (read by `ColQwen3_5`) with `embed_dim: 320` as a synonym for cross-ecosystem tools, so `ColQwen3_5.from_pretrained(...)` loads correctly by default. Leaderboard columns showing `128` reflect the colpali-engine class default (`self.dim = getattr(config, "dim", 128)`) and not the actual output dim. V3 builds on V2 with automated hyperparameter search and evolutionary model soup merging. The search identified an optimal LoRA config (r=16, alpha=64) with cosine scheduling, and the final checkpoint is a per-layer evolutionary merge with V2. The result is a +0.0219 improvement over V2 across benchmarks. _Rankings on the live ViDoRe V3 leaderboard drift as new submissions land. At release, v3 held **#3 overall**; figures below were captured on 2026-04-20, where v3 sits at **#6 on Mean (Task)** and remains **top-3 among 4B-class models**._
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗ColUltraVBERT
athrael-soju基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Selene-1-Llama-3.3-70B
AtlaAI基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗JEV-27B-VL-GGUF
Atlas3DGGUF builds of autotrust/JEV-27B-VL for llama.cpp's native decision endpoint `/v1/systemone`, with JEV's own readout: false/true for yes/no, the digits 0–5 for scores, and letters for choices, plus its decision-head bias and calibrated temperatures. These are also the builds for **older GPUs such as V100s**, which cannot run FP8/FP4 checkpoints. > **Requires a patched llama.cpp (for now).** The `jev` decision type is not in upstream llama.cpp yet. > Apply `llama.cpp-jev.patch` (made against upstream `bed0a85`) and build. It adds the converter class, > the GGUF metadata keys and the server readout. > ⚠️ **Q4_K_M is less accurate.** About 1 decision in 14 differs from full precision. Prefer Q8_0 when it > fits. Q4_K_M is for 24 GB-class cards.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DeepSeek-V4-Flash-0731-FP8-DSpark
AtlasCloudRouted MoE experts converted MXFP4/FP4 -> block FP8 via lossless `cast_e2m1fn_to_e4m3fn` (`tmp/scripts/convert_hf_mxfp4_experts_to_fp8.py`). `expert_dtype` removed from `config.json`; other fields (including `dspark_*` if present) kept.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DeepSeek-V4-Flash-Vision-Exp-FP8-DSpark
AtlasCloud基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗moulsot.v0.3
atlasia基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Audio→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗fermi-512
atomic-canyon基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Cyber-Ornith-1.5-9B-GGUF
Atomic-Germ基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Gemma4-26B-A4B-Instruct-QAT-GGUF
Atomic-Germ基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MiniCPM-V-4.6-NPU2
Atomic-Germ基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MiniCPM5-2B-OpenNPU2
Atomic-Germ基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Ornith-1.0-9B-NPU2
Atomic-Germ基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Ornith-1.5-35B-A3B-REAP50-GGUF
Atomic-Germ基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.