Clef
- Context
- 66K
- Released
- 2w ago
- Parameters
- 27B
- Input / 1M tokens
- $0.04
- Output / 1M tokens
- $0.00
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Cloudflare
- Model family
- Clef
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- October 1, 2026
- Model ID
cloudflare/clef- Openness
- Open weights
- License
- —
- Parameters
- 27B
- Input modalities
- text, image
- Output modalities
- decisions
- Modality
- text+image->decisions
- Native context
- 256K
- Tokenizer
- Qwen
- Max output tokens
- 15K
- Hugging Face
- Cloudflare/clef
- Source freshness
- Endpoints synced Oct 15, 2026, 1:31 AM UTC
Open-weight builds
Ollama variants
Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.
| Variant | Parameters | Type | Quantization | Size | Context | Input |
|---|---|---|---|---|---|---|
| clef:27b-mlx-bf16 | 27B | — | BF16 | 55 GB | 256K | text + image |
| clef:27b-q4_k_m | 27B | — | Q4_K_M | 18 GB | 256K | text + image |
| clef:27b-q8_0 | 27B | — | Q8_0 | 30 GB | 256K | text + image |
| clef:27b-mxfp8 | 27B | — | — | 31 GB | 256K | text + image |
| clef:27b-nvfp4 | 27B | — | — | 18 GB | 256K | text + image |
| clef:latest | 27B | — | — | 18 GB | 256K | text + image |
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| primeintellect | 16K | $0.04 | $0.00 | — | — | 100.00% | ZDR: Yes | |
| deepinfra/bf16 | 66K | $0.12 | $0.00 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| cloudflare | 66K | $0.24 | $0.00 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.