DeepSeek-V4.1-Flash-bf16
PrimeIntellect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 ↗DISCOVER & COMPARE
Explore AI models 20
DeepSeek-V4-Flash-0731-bf16
PrimeIntellectA bfloat16 re-export of deepseek-ai/DeepSeek-V4-Flash-0731. The weights are the published ones, dequantized: the dense linears from fp8 (e4m3 with ue8m0 scales over 128x128 blocks) and the routed experts from MXFP4, both to plain bfloat16. 43 layers, 114 safetensors shards. The upstream `config.json` carries `quantization_config` and `expert_dtype = "fp4"`. An inference engine reading those fields allocates fp8 linear parameters and MXFP4 expert parameters, which bfloat16 weights cannot fill. The routed experts at least fail loudly, in vLLM's `_load_w13`, where the packed MXFP4 shape does not match. The fp8 linears fail silently: a bfloat16 tensor has the same shape as the fp8 parameter it is loaded into, so `copy_` casts it elementwise and no dequantization scale is ever applied. Serving bfloat16 weights therefore requires a checkpoint whose config carries neither field, which is what this repo is. There is no Jinja chat template, by upstream design. Use the bundled `encoding/` directory, which is copied verbatim from upstream and is the reference implementation for turning OpenAI-format messages into an input string and for parsing completions back.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DeepSeek-V4-Flash-Base-bf16
PrimeIntellect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 ↗GLM-0.5B
PrimeIntellect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 ↗INTELLECT-1
PrimeIntellect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 ↗INTELLECT-1-Instruct
PrimeIntellect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 ↗INTELLECT-2
PrimeIntellect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 ↗INTELLECT-3.1
PrimeIntellect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 ↗INTELLECT-MATH
PrimeIntellect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 ↗llama-150m-fresh
PrimeIntellect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-2m-fresh
PrimeIntellect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 ↗Meta-Llama-3.1-405B-Instruct-FP8
PrimeIntellect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 ↗Qwen3-0.6B
PrimeIntellectThis is a clone of `Qwen/Qwen3-0.6B` with a multi-turn, tool-call compatible chat template.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-0.6B-Reverse-Text-RL
PrimeIntellect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 ↗Qwen3-0.6B-Reverse-Text-SFT
PrimeIntellectA SFT fine-tune of `PrimeIntellect/Qwen3-0.6B`. Details here.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-0.6B-untied
PrimeIntellect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 ↗Qwen3-1.7B
PrimeIntellectThis is a clone of `Qwen/Qwen3-1.7B` with a multi-turn, tool-call compatible chat template.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-1.7B-Wordle-SFT
PrimeIntellect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 ↗Qwen3-4B-Instruct-2507-untied
PrimeIntellect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 ↗qwen3-moe-tiny
PrimeIntellectA small (~670M parameter) Qwen3 MoE model for testing only. It is generally compatible with vLLM and HuggingFace Transformers but is meant to be used with prime-rl. Fine-tuned on PrimeIntellect/Reverse-Text-SFT to provide a non-trivial distribution for KL divergence during RL.
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.