HASTATAgent stack guide novita-ai
NovitaAI
All current catalogue offerings from this provider. Documentation remains authoritative.
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
107 offerings
| Model | Context / output | Capabilities | Lowest input | Providers |
|---|---|---|---|---|
| DeepSeek V4 Flashdeepseek-v4-flash · deepseek-flash | 1.05MOutput 1.05M | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 55fresh |
| DeepSeek V4 Prodeepseek-v4-pro · deepseek-thinking | 1.05MOutput 1.05M | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 55fresh |
| Kimi K2.7 Codekimi-k2.7-code · kimi-k2 | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 47fresh |
| Kimi K2.5kimi-k2.5 · kimi-k2 | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 49fresh |
| GLM 5.2glm-5.2 · glm | 1.05MOutput 1.05M | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 65fresh |
| GLM-5.1glm-5.1 · glm | 205KOutput 205K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 47fresh |
| MiniMax-M2.5minimax-m2.5 · minimax | 223KOutput 204K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 45fresh |
| Qwen3.5 35B A3Bqwen3.5-35b-a3b · qwen | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.057out $0.46 | 14fresh |
| Qwen3.5 397B A17Bqwen3.5-397b-a17b | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 26fresh |
| Qwen3.5 27Bqwen3.5-27b · qwen | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.086out $0.69 | 13fresh |
| Qwen3.5 122B-A10Bqwen3.5-122b-a10b · qwen | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 17fresh |
| Qwen 2.5 VL 72B Instructqwen2.5-vl-72b-instruct | 128KOutput 128K | Tool callingReasoningImage inputJSONOpen weights | $0.25out $0.70 | 8fresh |
| DeepSeek-V3-0324deepseek-v3-0324 | 160KOutput 160K | Tool callingJSONOpen weights | $0.20out $0.77 | 11fresh |
| Qwen3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507 | 256KOutput 256K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 15fresh |
| DeepSeek-V3.1deepseek-v3.1 | 164KOutput 164K | Tool callingReasoningJSONOpen weights | $0.20out $0.70 | 15fresh |
| DeepSeek-R1-0528deepseek-r1-0528 | 164KOutput 164K | Tool callingReasoningJSONOpen weights | $0.40out $1.70 | 14fresh |
| gpt-oss-120bgpt-oss-120b | 128KOutput 128K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 55fresh |
| Qwen3 Next 80B A3B Thinkingqwen3-next-80b-a3b-thinking | 256KOutput 128K | Tool callingReasoningJSONOpen weights | $0.14out $0.65 | 15fresh |
| Qwen3 Coder 480B A35B Instructqwen3-coder-480b-a35b-instruct | 256KOutput 256K | Tool callingJSONOpen weights | $0.00out $0.00 | 15fresh |
| Qwen3 Maxqwen3-max | 256KOutput 64K | Tool callingReasoningJSON | $0.00out $0.00 | 19fresh |
| Qwen3 235b A22B Instruct 2507qwen3-235b-a22b-instruct-2507 | 256KOutput 256K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 20fresh |
| Qwen3 Next 80B A3B Instructqwen3-next-80b-a3b-instruct | 256KOutput 256K | Tool callingImage inputJSONOpen weights | $0.00out $0.00 | 19fresh |
| Mimo-V2-Flashmimo-v2-flash · mimo | 256KOutput 256K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 7fresh |
| GLM 4.5 Airglm-4.5-air | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.10out $0.29 | 18fresh |
| Qwen3-Vl 30b A3b Thinkingqwen3-vl-30b-a3b-thinking | 256KOutput 262K | Tool callingReasoningImage inputJSONOpen weights | $0.20out $1.00 | 6fresh |
| gpt-oss-20bgpt-oss-20b | 128KOutput 128K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 34fresh |
| GLM 4.5glm-4.5 | 128KOutput 96K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 18fresh |
| GLM-4.6glm-4.6 · glm | 200KOutput 200K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 26fresh |
| GLM-4.7glm-4.7 · glm | 205KOutput 198K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 36fresh |
| GLM-5glm-5 · glm | 205KOutput 205K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 43fresh |
| DeepSeek V3.1 Terminusdeepseek-v3.1-terminus · deepseek | 164KOutput 164K | Tool callingReasoningJSONOpen weights | $0.25out $0.70 | 11fresh |
| DeepSeek/DeepSeek-V3.2-Expdeepseek/deepseek-v3.2-exp | 160KOutput 64K | Tool callingReasoningJSONOpen weights | $0.22out $0.33 | 5fresh |
| Kimi-K2-0905kimi-k2-0905 · kimi-k2 | 256KOutput 256K | Tool callingJSONOpen weights | $0.00out $0.00 | 8fresh |
| Kimi K2 Thinkingkimi-k2-thinking · kimi-thinking | 256KOutput 256K | Tool callingReasoningJSONOpen weights | $0.40out $2.00 | 19fresh |
| MiniMax-M2.5-highspeedminimax-m2.5-highspeed · minimax | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 10fresh |
| MiniMax-M2minimax-m2 · minimax | 1MOutput 400K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 18fresh |
| MiniMax-M2.1minimax-m2.1 · minimax | 1MOutput 196K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 23fresh |
| Kimi K3kimi-k3 · kimi-k3 | 1.05MOutput 1.05M | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 50fresh |
| Kimi K2.6kimi-k2.6 · kimi-k2 | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 61fresh |
| Gemma 4 26B A4B ITgemma-4-26b-a4b-it · gemma | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.060out $0.30 | 18fresh |
| Llama 3.2 3B Instructllama-3.2-3b-instruct · llama | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 10fresh |
| Llama 4 Scout 17B 16E Instructllama-4-scout-17b-16e-instruct · llama | 320KOutput 128K | Tool callingImage inputJSONOpen weights | $0.10out $0.30 | 6fresh |
| DeepSeek R1 Distill Qwen 32Bdeepseek-r1-distill-qwen-32b · qwen | 80KOutput 80K | Tool callingReasoningOpen weights | $0.29out $0.30 | 4fresh |
| GLM-4.7-Flashglm-4.7-flash · glm-flash | 203KOutput 203K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 19fresh |
| DeepSeek-V3.2-Expdeepseek-v3.2 · deepseek | 164KOutput 164K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 32fresh |
| Llama-3.3-70B-Instructllama-3.3-70b-instruct · llama | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 26fresh |
| Gemma 4 31B ITgemma-4-31b-it · gemma | 256KOutput 256K | Tool callingReasoningImage inputJSONOpen weights | $0.00out $0.00 | 29fresh |
| MiniMax-M2.7-highspeedminimax-m2.7-highspeed · minimax | 200KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 13fresh |
| MiniMax-M2.7minimax-m2.7 · minimax | 256KOutput 192K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 35fresh |
| Google Gemma 3 12Bgemma-3-12b-it · gemma | 128KOutput 128K | Tool callingImage inputJSONOpen weights | $0.00out $0.00 | 6fresh |
| Llama-3.1-8B-Instructllama-3.1-8b-instruct · llama | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 12fresh |
| Qwen3-Coder 30B-A3B Instructqwen3-coder-30b-a3b-instruct · qwen | 256KOutput 256K | Tool callingJSONOpen weights | $0.00out $0.00 | 19fresh |
| Qwen3 Coder Nextqwen3-coder-next · qwen | 256KOutput 256K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 15fresh |
| gemma-3-27b-itgemma-3-27b-it | 256KOutput 128K | Tool callingReasoningImage inputJSONOpen weights | $0.080out $0.16 | 8fresh |
| Qwen3.7 Maxqwen3.7-max · qwen | 1MOutput 500K | Tool callingReasoningJSON | $0.00out $0.00 | 27fresh |
| Qwen3 VL 235B A22B Thinkingqwen3-vl-235b-a22b-thinking | 262KOutput 262K | Tool callingReasoningImage inputJSONOpen weights | $0.40out $3.50 | 7fresh |
| MiniMax M1 80Kminimaxai/minimax-m1-80k · minimax | 1MOutput 128K | Tool callingReasoningOpen weights | $0.55out $2.20 | 3fresh |
| WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b · gpt | 64KOutput 8K | Open weights | $0.49out $0.49 | 4fresh |
| GLM-4.5Vglm-4.5v · glm | 128KOutput 96K | Tool callingReasoningImage inputJSONOpen weights | $0.29out $0.86 | 12fresh |
| DeepSeek Prover v2 671Bdeepseek/deepseek-prover-v2-671b · deepseek | 160KOutput 160K | Open weights | $0.70out $2.50 | 2fresh |
| Kimi K2 Instructmoonshotai/kimi-k2-instruct · kimi-k2 | 256KOutput 128K | Tool callingJSONOpen weights | $0.40out $1.80 | 4fresh |
| Sao10K Stheno 8bsao10k/l3-8b-stheno-v3.2 · llama | 16KOutput 32K | Tool callingOpen weights | $0.050out $0.050 | 2fresh |
| Qwen3 VL 235B A22B Instructqwen3-vl-235b-a22b-instruct · qwen | 256KOutput 256K | Tool callingImage inputJSONOpen weights | $0.20out $0.88 | 10fresh |
| Qwen2.5 72Bqwen/qwen-2.5-72b-instruct · qwen | 128KOutput 16K | Tool callingJSONOpen weights | $0.36out $0.40 | 4fresh |
| MiMo-V2.5-Promimo-v2.5-pro · mimo | 1.05MOutput 256K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 22fresh |
| GLM-4.6Vglm-4.6v · glm | 200KOutput 64K | Tool callingReasoningImage inputJSONOpen weights | $0.14out $0.42 | 13fresh |
| MythoMax 13Bgryphe/mythomax-l2-13b · llama | 8KOutput 4K | JSONOpen weights | $0.060out $0.060 | 4fresh |
| Ring 2.6 1Tinclusionai/ring-2.6-1t · ring | 256KOutput 64K | Tool callingReasoningJSONOpen weights | $0.075out $0.63 | 5fresh |
| Ling 2.6 1Tinclusionai/ling-2.6-1t · ling | 256KOutput 32K | Tool callingJSONOpen weights | $0.075out $0.63 | 4fresh |
| Ling 2.6 Flashinclusionai/ling-2.6-flash · ling | 256KOutput 32K | Tool callingJSONOpen weights | $0.010out $0.030 | 4fresh |
| MiMo-V2-Promimo-v2-pro · mimo | 1.05MOutput 256K | Tool callingReasoningJSONOpen weights | $0.00out $0.00 | 8fresh |
| Llama-4-Maverick-17B-128E-Instruct-FP8llama-4-maverick-17b-128e-instruct-fp8 · llama | 1.05MOutput 43K | Tool callingImage inputJSONOpen weights | $0.00out $0.00 | 9fresh |
| Qwen3 235B A22B FP8qwen3-235b-a22b-fp8 · qwen | 40KOutput 20K | Tool callingReasoningJSONOpen weights | $0.20out $0.80 | 3fresh |
| Qwen3 32Bqwen/qwen3-32b-fp8 · qwen | 40KOutput 20K | ReasoningOpen weights | $0.10out $0.45 | 2fresh |
| Qwen3 30B A3Bqwen/qwen3-30b-a3b-fp8 · qwen | 40KOutput 20K | ReasoningOpen weights | $0.090out $0.45 | 2fresh |
| ERNIE 4.5 VL 424B A47Bernie-4.5-vl-424b-a47b · ernie | 123KOutput 123K | Tool callingReasoningImage inputOpen weights | $0.42out $1.25 | 5fresh |
| ERNIE 4.5 300B A47Bbaidu/ernie-4.5-300b-a47b-paddle · ernie | 123KOutput 12K | Tool callingJSONOpen weights | $0.28out $1.10 | 2fresh |
| DeepSeek R1 Distill Llama 70Bdeepseek-r1-distill-llama-70b · deepseek-thinking | 128KOutput 128K | Tool callingReasoningJSONOpen weights | $0.030out $0.13 | 7fresh |
| Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct · qwen | 256KOutput 262K | Tool callingImage inputJSONOpen weights | $0.080out $0.46 | 5fresh |
| Qwen3 VL 30B A3B Instructqwen3-vl-30b-a3b-instruct · qwen | 256KOutput 262K | Tool callingImage inputJSONOpen weights | $0.13out $0.52 | 7fresh |
| Mistral Nemomistral-nemo · mistral-nemo | 128KOutput 128K | Tool callingImage inputJSONOpen weights | $0.019out $0.030 | 6fresh |
| DeepSeek OCR 2deepseek-ocr-2 | 8KOutput 8K | Image inputOpen weights | $0.00out $0.00 | 3fresh |
| Qwen-MT Plusqwen-mt-plus · qwen | 16KOutput 8K | Open weights | $0.25out $0.75 | 3fresh |
| DeepSeek R1 Distill Qwen 14Bdeepseek-r1-distill-qwen-14b · qwen | 32KOutput 16K | Tool callingReasoningOpen weights | $0.14out $0.15 | 2fresh |
| Hermes 2 Pro Llama 3 8Bhermes-2-pro-llama-3-8b · llama | 128KOutput 128K | Tool callingJSONOpen weights | $0.14out $0.14 | 2fresh |
| Baidu Ernie 4.5 21B A3B Thinkingernie-4.5-21b-a3b-thinking · ernie | 128KOutput 64K | ReasoningOpen weights | $0.070out $0.28 | 2fresh |
| Qwen/Qwen2.5-7B-Instructqwen/qwen2.5-7b-instruct · qwen | 33KOutput 32K | Tool callingJSONOpen weights | $0.050out $0.050 | 3fresh |
| DeepSeek-OCRdeepseek/deepseek-ocr | 8KOutput 8K | Image inputJSONOpen weights | $0.030out $0.030 | 1fresh |
| DeepSeek V3 (Turbo) deepseek/deepseek-v3-turbo | 64KOutput 16K | Tool callingOpen weights | $0.40out $1.30 | 1fresh |
| DeepSeek R1 0528 Qwen3 8Bdeepseek/deepseek-r1-0528-qwen3-8b | 128KOutput 32K | ReasoningOpen weights | $0.060out $0.090 | 1fresh |
| DeepSeek R1 (Turbo) deepseek/deepseek-r1-turbo | 64KOutput 16K | Tool callingReasoningOpen weights | $0.70out $2.50 | 1fresh |
| PaddleOCR-VLpaddlepaddle/paddleocr-vl | 16KOutput 16K | Image inputOpen weights | $0.020out $0.020 | 1fresh |
| baichuan-m2-32bbaichuan/baichuan-m2-32b · baichuan | 128KOutput 128K | Open weights | $0.070out $0.070 | 1fresh |
| Qwen3 4Bqwen/qwen3-4b-fp8 | 128KOutput 20K | ReasoningOpen weights | $0.030out $0.030 | 1fresh |
| Qwen3 8Bqwen/qwen3-8b-fp8 | 128KOutput 20K | ReasoningOpen weights | $0.035out $0.14 | 1fresh |
| Qwen3 Omni 30B A3B Instructqwen/qwen3-omni-30b-a3b-instruct · qwen | 64KOutput 16K | Tool callingImage inputJSONOpen weights | $0.25out $0.97 | 1fresh |
| Qwen3 Omni 30B A3B Thinkingqwen/qwen3-omni-30b-a3b-thinking | 64KOutput 16K | Tool callingReasoningImage inputJSONOpen weights | $0.25out $0.97 | 1fresh |
| L31 70B Euryale V2.2sao10k/l31-70b-euryale-v2.2 | 8KOutput 8K | Tool callingOpen weights | $1.48out $1.48 | 1fresh |
| Sao10k L3 8B Lunaris sao10k/l3-8b-lunaris | 8KOutput 8K | JSONOpen weights | $0.050out $0.050 | 1fresh |
| L3 70B Euryale V2.1 sao10k/l3-70b-euryale-v2.1 | 8KOutput 8K | Tool callingOpen weights | $1.48out $1.48 | 1fresh |
| AutoGLM-Phone-9B-Multilingualzai-org/autoglm-phone-9b-multilingual | 64KOutput 64K | Image inputOpen weights | $0.035out $0.14 | 1fresh |
| Llama 3 70B Instructllama-3-70b-instruct · llama | 8KOutput 8K | JSONOpen weights | $0.51out $0.74 | 2fresh |
| Llama 3 8B Instructmeta-llama/llama-3-8b-instruct · llama | 8KOutput 8K | Open weights | $0.040out $0.040 | 1fresh |
| ERNIE-4.5-VL-28B-A3B-Thinkingbaidu/ernie-4.5-vl-28b-a3b-thinking | 128KOutput 64K | Tool callingReasoningImage inputJSONOpen weights | $0.39out $0.39 | 1fresh |
| ERNIE 4.5 VL 28B A3Bbaidu/ernie-4.5-vl-28b-a3b | 30KOutput 8K | Tool callingReasoningImage inputOpen weights | $0.14out $0.56 | 1fresh |
| ERNIE 4.5 21B A3Bbaidu/ernie-4.5-21b-a3b · ernie | 120KOutput 8K | Tool callingOpen weights | $0.070out $0.28 | 1fresh |
| Kat Coder Prokwaipilot/kat-coder-pro | 256KOutput 128K | Tool callingJSONOpen weights | $0.30out $1.20 | 1fresh |