LLM Perks
RU

Free models for coding

Updated:

Models for code generation, explanation, refactoring, IDE use, and coding agents, with free API context and limit comparisons.

Read more

Large repositories benefit from context, autocomplete from low latency, and coding agents from reliable tool calling. The same coding LLM can have different free quotas across providers.

64 models found

Power
№ ↕ Model ↕ Power ↕ Provider ↕ Parameters ↕ Context ↕ Limit ↕
1 Cohere: North Mini Code (free) ⚡ OpenRouter ? 256K Free tier Open
2 Qwen3.8 27b ⚖️ Groq 27B 131K 14,400 req/day Open
3 Codestral Mamba ⚡ Mistral AI ? 256K 1 req/min · 500 tok/min Open
4 DeepSeek R1 Distill Qwen 7B ⚡ Together AI 7B 131K Fair Use (По мере нагрузки серверов) Open
5 Cogito V1 Preview Qwen 32B ⚖️ Together AI 32B 131K Fair Use (По мере нагрузки серверов) Open
6 Cogito V1 Preview Qwen 14B ⚖️ Together AI 14B 131K Fair Use (По мере нагрузки серверов) Open
7 Qwen2.5 32B ⚖️ Together AI 32B 131K Fair Use (По мере нагрузки серверов) Open
8 Qwen2.5 72B 🚀 Together AI 72B 131K Fair Use (По мере нагрузки серверов) Open
9 Qwen2.5 3B Instruct ⚡ Together AI 3B 33K Fair Use (По мере нагрузки серверов) Open
10 Qwen2.5 1.5B Instruct ⚡ Together AI 1.5B 33K Fair Use (По мере нагрузки серверов) Open
11 Qwen2.5 14B ⚖️ Together AI 14B 131K Fair Use (По мере нагрузки серверов) Open
12 Qwen2.5 7B ⚡ Together AI 7B 131K Fair Use (По мере нагрузки серверов) Open
13 Qwen2.5 1.5B ⚡ Together AI 1.5B 131K Fair Use (По мере нагрузки серверов) Open
14 Qwen2.5 7B Instruct ⚡ Together AI 7B 33K Fair Use (По мере нагрузки серверов) Open
15 Qwen2.5 32B Instruct ⚖️ Together AI 32B 33K Fair Use (По мере нагрузки серверов) Open
16 Deepcoder 14B Preview ⚖️ Together AI 14B 131K Fair Use (По мере нагрузки серверов) Open
17 Devstral Small 2505 ⚖️ Together AI ? 131K Fair Use (По мере нагрузки серверов) Open
18 Qwen3 8B ⚡ Together AI 8B 41K Fair Use (По мере нагрузки серверов) Open
19 Qwen3 14B ⚖️ Together AI 14B 2K Fair Use (По мере нагрузки серверов) Open
20 Qwen3 0.6B ⚡ Together AI 0.6B 41K Fair Use (По мере нагрузки серверов) Open
21 Qwen3 1.7B ⚡ Together AI 1.7B 41K Fair Use (По мере нагрузки серверов) Open
22 Qwen3 30B A3b ⚖️ Together AI 30B 41K Fair Use (По мере нагрузки серверов) Open
23 Qwen3 32B ⚖️ Together AI 32B 41K Fair Use (По мере нагрузки серверов) Open
24 Qwen3 235B A22b Instruct 2507 Fp8 🚀 Together AI 235B 262K Fair Use (По мере нагрузки серверов) Open
25 Qwen3 Coder 30B A3b Instruct ⚖️ Together AI 30B 262K Fair Use (По мере нагрузки серверов) Open
26 Qwen3 4B Instruct 2507 ⚡ Together AI 4B 262K Fair Use (По мере нагрузки серверов) Open
27 Qwen3 Next 80B A3b Instruct Fp8 🚀 Together AI 80B ? Fair Use (По мере нагрузки серверов) Open
28 Qwen3-VL-235B-A22B-Instruct-FP8 🚀 Together AI 235B 262K Fair Use (По мере нагрузки серверов) Open
29 Qwen3.5 9B Fp8 ⚡ Together AI 9B 262K Fair Use (По мере нагрузки серверов) Open
30 Qwen3.5 35B A3b ⚖️ Together AI 35B 262K Fair Use (По мере нагрузки серверов) Open
31 Deepseek OCR 2 ⚖️ Together AI ? 8K Fair Use (По мере нагрузки серверов) Open
32 Qwen3.5 122B A10b Fp8 🚀 Together AI 122B 262K Fair Use (По мере нагрузки серверов) Open
33 Qwen3 8B Lora ⚡ Together AI 8B 41K Fair Use (По мере нагрузки серверов) Open
34 Qwen3 30B A3B Instruct 2507 Lora ⚖️ Together AI 30B 262K Fair Use (По мере нагрузки серверов) Open
35 Qwen3.6 35B A3b Fp8 ⚖️ Together AI 35B 262K Fair Use (По мере нагрузки серверов) Open
36 Qwen3.5 35B A3B Lora ⚖️ Together AI 35B 262K Fair Use (По мере нагрузки серверов) Open
37 Qwen3.5 2B Lora ⚡ Together AI 2B 262K Fair Use (По мере нагрузки серверов) Open
38 Qwen3.6 35B A3B Lora ⚖️ Together AI 35B 262K Fair Use (По мере нагрузки серверов) Open
39 Qwen 3.8 27b ⚖️ Cerebras 27B ? 14,400 req/day · 30 req/min Open
40 Qwen 1.5 14B Chat ⚖️ Cloudflare 14B 33K 10,000 req/day Open
41 DeepSeek: DeepSeek V4 Flash (Free) 🚀 OrcaRouter ? ? Free tier Open
42 Codegemma 1.1 7b ⚡ NVIDIA Build 7B ? Free serverless inference for development; limits and model availability may change. Open
43 Codegemma 7b ⚡ NVIDIA Build 7B ? Free serverless inference for development; limits and model availability may change. Open
44 Codellama 70b 🚀 NVIDIA Build 70B ? Free serverless inference for development; limits and model availability may change. Open
45 Codestral 22b Instruct V0.1 ⚖️ NVIDIA Build 22B ? Free serverless inference for development; limits and model availability may change. Open
46 Deepseek Coder 6.7b Instruct ⚡ NVIDIA Build 6.7B ? Free serverless inference for development; limits and model availability may change. Open
47 Deepseek V4 Flash 0731 🚀 NVIDIA Build ? ? Free serverless inference for development; limits and model availability may change. Open
48 Granite 34b Code Instruct ⚖️ NVIDIA Build 34B ? Free serverless inference for development; limits and model availability may change. Open
49 Granite 8b Code Instruct ⚡ NVIDIA Build 8B ? Free serverless inference for development; limits and model availability may change. Open
50 Starcoder2 15b ⚖️ NVIDIA Build 15B ? Free serverless inference for development; limits and model availability may change. Open
51 Codestral Latest ⚡ UnoRouter ? 256K No-card free models use shared capacity and per-model limits; availability can change. Open
52 Deepseek R1 Distill Llama 70b 🚀 UnoRouter 70B 131K No-card free models use shared capacity and per-model limits; availability can change. Open
53 Deepseek V4 Flash 0731 🚀 UnoRouter ? 1.0M No-card free models use shared capacity and per-model limits; availability can change. Open
54 Deepseek V4 Pro 🚀 UnoRouter ? 1.0M No-card free models use shared capacity and per-model limits; availability can change. Open
55 Kat Coder Air V1 ⚡ UnoRouter ? 128K No-card free models use shared capacity and per-model limits; availability can change. Open
56 North Mini Code ⚡ UnoRouter ? 256K No-card free models use shared capacity and per-model limits; availability can change. Open
57 QWEN Sea Lion V4 32b It ⚖️ UnoRouter 32B 33K No-card free models use shared capacity and per-model limits; availability can change. Open
58 QWEN Sea Lion V4.5 27b It ⚖️ UnoRouter 27B 262K No-card free models use shared capacity and per-model limits; availability can change. Open
59 Qwen2.5 Vl 7b Instruct Awq ⚡ UnoRouter 7B 131K No-card free models use shared capacity and per-model limits; availability can change. Open
60 Qwen3 Next 80b A3b Instruct 🚀 UnoRouter 80B 131K No-card free models use shared capacity and per-model limits; availability can change. Open
61 Qwen3.5 122b A10b 🚀 UnoRouter 122B 262K No-card free models use shared capacity and per-model limits; availability can change. Open
62 Qwen3.5 4b ⚡ UnoRouter 4B 262K No-card free models use shared capacity and per-model limits; availability can change. Open
63 Qwen3.6 35b A3b ⚖️ UnoRouter 35B 262K No-card free models use shared capacity and per-model limits; availability can change. Open
64 Qwen3.8 27b ⚖️ UnoRouter 27B 66K No-card free models use shared capacity and per-model limits; availability can change. Open