StartLux-Decision-v1-0.8B
startlux-models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 ↗DISCOVER & COMPARE
Explore AI models 37
StartLux-Decision-v1-0.8B-BF16-GGUF
startlux-models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 ↗StartLux-Decision-v1-0.8B-Q4_K_M-GGUF
startlux-models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 ↗StartLux-Decision-v1-0.8B-Q8_0-GGUF
startlux-modelsStartLux-Decision-v1-0.8B in Q8_0 (8-bit) as a GGUF file for llama.cpp. The decision server in this repository turns it into the same typed decisions, with a probability for every option, as the original model. "Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the `startlux_decision` package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix. At this size Q4_K_M changes noticeably more answers (93.1% the same), so Q8_0 is the better choice. `-ngl 99` puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer).
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-0.8B-Instant
startlux-models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 ↗StartLux-Decision-v1.1-0.8B-Instant-GGUF
startlux-models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 ↗StartLux-Decision-v1.1-27B-AutoThink
startlux-models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 ↗StartLux-Decision-v1.1-27B-AutoThink-GGUF
startlux-modelsFormats: BF16 · **GGUF** · MLX 8-bit · MLX 4-bit · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Decision Index 0.3, public subset, as of 11 October 2026: the StartLux-Decision Instant models against other decision models of each size. Figure 1 of the technical report . The DecisionPivot column is the mean chance-corrected accuracy over the seven layers of the benchmark's scorer on its 7,800 core items, from the report's measurements: the GGUF files on llama.cpp (release b11549), the BF16 weights on vLLM. For an AutoThink model the rows therefore also compare two engines. The Q8_0 file scored 2.7 points above BF16 (95% interval +1.3 to +4.1), but as the two runs used different engines, the difference does not isolate the format. Q8_0 is the recommended file; Q4_K_M lost up to 3.8 points across the sizes.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-27B-Instant
startlux-modelsStartLux-Decision-v1.1-27B-Instant is a 27B decision model. You give it a state (text or JSON, with up to 8 images) and typed questions about it: pick one of several options (`choice`), yes or no (`noul`), or a level on a scale of 2 to 10 (`score`). It returns a probability for every option of every question from one forward pass, without generating text. The request and response format is compatible with the System One `/v1/systemone` API. Formats: **BF16** · GGUF · MLX 8-bit · MLX 4-bit · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Family: 0.8B Instant · 2B Instant · 4B Instant · 4B AutoThink · 9B Instant · 9B AutoThink · **27B Instant** · 27B AutoThink
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-27B-Instant-GGUF
startlux-modelsFormats: BF16 · **GGUF** · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Decision Index 0.3, public subset, as of 11 October 2026: the StartLux-Decision Instant models against other decision models of each size. Figure 1 of the technical report . The DecisionPivot column is the mean chance-corrected accuracy over the seven layers of the benchmark's scorer on its 7,800 core items, from the report's measurements: the GGUF files on llama.cpp (release b11549), the BF16 weights on vLLM. Q8_0 is the recommended file; Q4_K_M lost up to 3.8 points across the sizes.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-2B-Instant
startlux-models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 ↗StartLux-Decision-v1.1-2B-Instant-GGUF
startlux-models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 ↗StartLux-Decision-v1.1-4B-AutoThink
startlux-models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 ↗StartLux-Decision-v1.1-4B-AutoThink-GGUF
startlux-modelsStartLux-Decision-v1.1-4B-AutoThink as GGUF files for llama.cpp, in Q8_0 (8-bit) and Q4_K_M (4-bit). StartLux-Decision-v1.1-4B-AutoThink is a 4B decision model that thinks only where its one-pass answer is uncertain. Given a state (text or JSON) and typed questions about it (pick an option, yes or no, or a level on a scale of 2 to 10), it reads a probability for every option from the option letters in one pass; where the top probability is below 0.90 it writes a thought of at most 4,096 tokens and reads the answer again, and the default answer is 0.25 × the first read-out + 0.75 × the second. Requests and responses use the TypeSafe `/v1/systemone` format. Formats: BF16 · **GGUF** · MLX 8-bit · MLX 4-bit · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Decision Index 0.3, public subset, as of 11 October 2026: the StartLux-Decision Instant models against other decision models of each size. Figure 1 of the technical report .
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-4B-Instant
startlux-models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 ↗StartLux-Decision-v1.1-4B-Instant-GGUF
startlux-modelsFormats: BF16 · **GGUF** · MLX 8-bit · MLX 4-bit · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Decision Index 0.3, public subset, as of 11 October 2026: the StartLux-Decision Instant models against other decision models of each size. Figure 1 of the technical report . The DecisionPivot column is the mean chance-corrected accuracy over the seven layers of the benchmark's scorer on its 7,800 core items, from the report's measurements: the GGUF files on llama.cpp (release b11549), the BF16 weights on vLLM. Q8_0 is the recommended file; Q4_K_M lost up to 3.8 points across the sizes.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-9B-AutoThink
startlux-models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 ↗StartLux-Decision-v1.1-9B-AutoThink-GGUF
startlux-modelsStartLux-Decision-v1.1-9B-AutoThink as GGUF files for llama.cpp, in Q8_0 (8-bit) and Q4_K_M (4-bit). StartLux-Decision-v1.1-9B-AutoThink is a 9B decision model that thinks only where its one-pass answer is uncertain. Given a state (text or JSON) and typed questions about it (pick an option, yes or no, or a level on a scale of 2 to 10), it reads a probability for every option from the option letters in one pass; where the top probability is below 0.90 it writes a thought of at most 4,096 tokens and reads the answer again, and the default answer is 0.25 × the first read-out + 0.75 × the second. Requests and responses use the TypeSafe `/v1/systemone` format. Formats: BF16 · **GGUF** · MLX 8-bit · MLX 4-bit · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Decision Index 0.3, public subset, as of 11 October 2026: the StartLux-Decision Instant models against other decision models of each size. Figure 1 of the technical report .
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-9B-Instant
startlux-modelsStartLux-Decision-v1.1-9B-Instant is a 9B decision model. You give it a state (text or JSON, with up to 8 images) and typed questions about it: pick one of several options (`choice`), yes or no (`noul`), or a level on a scale of 2 to 10 (`score`). It returns a probability for every option of every question from one forward pass, without generating text. The request and response format is compatible with the System One `/v1/systemone` API. Formats: **BF16** · GGUF · MLX 8-bit · MLX 4-bit · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Family: 0.8B Instant · 2B Instant · 4B Instant · 4B AutoThink · **9B Instant** · 9B AutoThink · 27B Instant · 27B AutoThink
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1.1-9B-Instant-GGUF
startlux-modelsStartLux-Decision-v1.1-9B-Instant as GGUF files for llama.cpp, in Q8_0 (8-bit) and Q4_K_M (4-bit). StartLux-Decision-v1.1-9B-Instant is a 9B decision model. Given a state (text or JSON) and typed questions about it (pick an option, yes or no, or a level on a scale of 2 to 10), it returns a probability for every option of every question from one forward pass, without generating text. Requests and responses use the TypeSafe `/v1/systemone` format. Formats: BF16 · **GGUF** · MLX 8-bit · MLX 4-bit · Code: StartLuxLabs/StartLux-Decision · Paper: arXiv 2610.17309 Decision Index 0.3, public subset, as of 11 October 2026: the StartLux-Decision Instant models against other decision models of each size. Figure 1 of the technical report .
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1-27B
startlux-models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 ↗StartLux-Decision-v1-27B-BF16-GGUF
startlux-modelsStartLux-Decision-v1-27B in BF16 (16-bit) as a GGUF file for llama.cpp. The decision server in this repository turns it into the same typed decisions, with a probability for every option, as the original model. "Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the `startlux_decision` package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix. `-ngl 99` puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer).
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1-27B-Q4_K_M-GGUF
startlux-modelsStartLux-Decision-v1-27B in Q4_K_M (4-bit) as a GGUF file for llama.cpp. The decision server in this repository turns it into the same typed decisions, with a probability for every option, as the original model. "Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the `startlux_decision` package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix. `-ngl 99` puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer).
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗StartLux-Decision-v1-27B-Q8_0-GGUF
startlux-modelsStartLux-Decision-v1-27B in Q8_0 (8-bit) as a GGUF file for llama.cpp. The decision server in this repository turns it into the same typed decisions, with a probability for every option, as the original model. "Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the `startlux_decision` package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix. `-ngl 99` puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer).
Input Not verified→ Output Not verified
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.