Access
- API base URL
- https://api.novita.ai/openai
- SDK
- @ai-sdk/openai-compatible
- Environment variables
- NOVITA_API_KEY
Models
53 of 53 model versions
| Model | Organization | Family | Provider model ID | Protocol | Streaming | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Pricing | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 moonshotai/kimi/k3 | Moonshot AI | Kimi | moonshotai/kimi-k3 | Openai chat | Yes | 1M | 131K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $3/M · cache read $0.3/M output $15/M | 2026-07-16 | 2026-07-30 | |
| Kimi K2.7 Code moonshotai/kimi/k2-7-code | Moonshot AI | Kimi | moonshotai/kimi-k2.7-code | Openai chat | Yes | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $0.95/M · cache read $0.19/M output $4/M | 2026-06-12 | 2026-07-22 | |
| Qwen3.7 Max alibaba/qwen/qwen3-7-max | Alibaba | Qwen | qwen/qwen3.7-max | Openai chat | Yes | 1M | 66K | Text | Text | Yes | Yes | Yes | Yes | Closed | input $1.25/M · cache read $0.25/M output $3.75/M · cache write $1.5625/M | 2026-05-21 | 2026-07-22 | |
| Ring-2.6-1T inclusionai/ring/2-6-1t | Inclusionai | Ring | inclusionai/ring-2.6-1t | Openai chat | Yes | 262K | 66K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.06/M output $2.5/M | 2026-05-08 | 2026-05-27 | |
| DeepSeek V4 Flash deepseek/deepseek/v4-flash | DeepSeek | DeepSeek | deepseek/deepseek-v4-flash | Openai chat | Yes | 1M | 384K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.14/M · cache read $0.028/M output $0.28/M | 2026-04-24 | 2026-07-31 | |
| DeepSeek V4 Pro deepseek/deepseek/v4-pro | DeepSeek | DeepSeek | deepseek/deepseek-v4-pro | Openai chat | Yes | 1M | 384K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $1.6/M · cache read $0.135/M output $3.2/M | 2026-04-24 | 2026-07-22 | |
| Ling-2.6-1T inclusionai/ling/2-6-1t | Inclusionai | Ling | inclusionai/ling-2.6-1t | Openai chat | Yes | 262K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.3/M · cache read $0.06/M output $2.5/M | 2026-04-23 | 2026-06-29 | |
| Kimi K2.6 moonshotai/kimi/k2-6 | Moonshot AI | Kimi | moonshotai/kimi-k2.6 | Openai chat | Yes | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Open weight | input $0.8/M · cache read $0.16/M output $3.4/M | 2026-04-21 | 2026-07-22 | |
| Ling-2.6-flash inclusionai/ling/2-6-flash | Inclusionai | Ling | inclusionai/ling-2.6-flash | Openai chat | Yes | 262K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.1/M · cache read $0.02/M output $0.3/M | 2026-04-21 | 2026-04-24 | |
| Gemma 4 26B A4B IT google/gemma/4-26b-a4b-it | Gemma | google/gemma-4-26b-a4b-it | Openai chat | Yes | 262K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0.13/M output $0.4/M | 2026-04-02 | 2026-07-22 | ||
| Gemma 4 31B IT google/gemma/4-31b-it | Gemma | google/gemma-4-31b-it | Openai chat | Yes | 262K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0.14/M output $0.4/M | 2026-04-02 | 2026-04-30 | ||
| MiniMax-M2.7 minimax/minimax/m2-7 | MiniMax | Minimax | minimax/minimax-m2.7 | Openai chat | Yes | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.06/M output $1.2/M | 2026-03-18 | 2026-07-22 | |
| MiniMax-M2.7-highspeed minimax/minimax/m2-7-highspeed | MiniMax | Minimax | minimax/minimax-m2.7-highspeed | Openai chat | Yes | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M · cache read $0.06/M output $2.4/M · cache write $0.375/M | 2026-03-18 | 2026-05-27 | |
| Qwen3.5 122B-A10B alibaba/qwen/qwen3-5-122b-a10b | Alibaba | Qwen | qwen/qwen3.5-122b-a10b | Openai chat | Yes | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.4/M output $3.2/M | 2026-02-23 | 2026-03-18 | |
| Qwen3.5 27B alibaba/qwen/qwen3-5-27b | Alibaba | Qwen | qwen/qwen3.5-27b | Openai chat | Yes | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.3/M output $2.4/M | 2026-02-23 | 2026-03-18 | |
| Qwen3.5 35B-A3B alibaba/qwen/qwen3-5-35b-a3b | Alibaba | Qwen | qwen/qwen3.5-35b-a3b | Openai chat | Yes | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.25/M output $2/M | 2026-02-23 | 2026-06-11 | |
| Qwen3.5 397B-A17B alibaba/qwen/qwen3-5-397b-a17b | Alibaba | Qwen | qwen/qwen3.5-397b-a17b | Openai chat | Yes | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.6/M output $3.6/M | 2026-02-15 | 2026-06-11 | |
| MiniMax-M2.5-highspeed minimax/minimax/m2-5-highspeed | MiniMax | Minimax | minimax/minimax-m2.5-highspeed | Openai chat | Yes | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M · cache read $0.03/M output $2.4/M | 2026-02-13 | 2026-02-14 | |
| MiniMax-M2.5 minimax/minimax/m2-5 | MiniMax | Minimax | minimax/minimax-m2.5 | Openai chat | Yes | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.03/M output $1.2/M | 2026-02-12 | 2026-04-16 | |
| Qwen3 Coder Next alibaba/qwen/qwen3-coder-next | Alibaba | Qwen | qwen/qwen3-coder-next | Openai chat | Yes | 262K | 262K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.2/M output $1.5/M | 2026-02-04 | 2026-02-04 | |
| Kimi K2.5 moonshotai/kimi/k2-5 | Moonshot AI | Kimi | moonshotai/kimi-k2.5 | Openai chat | Yes | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $0.6/M · cache read $0.1/M output $3/M | 2026-01 | 2026-07-22 | |
| MiniMax-M2.1 minimax/minimax/m2-1 | MiniMax | Minimax | minimax/minimax-m2.1 | Openai chat | Yes | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.03/M output $1.2/M | 2025-12-23 | 2026-01-01 | |
| DeepSeek V3.2 deepseek/deepseek/v3-2 | DeepSeek | DeepSeek | deepseek/deepseek-v3.2 | Openai chat | Yes | 164K | 66K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.269/M · cache read $0.1345/M output $0.4/M | 2025-12-01 | 2025-12-05 | |
| Kimi K2 Thinking moonshotai/kimi/k2-thinking | Moonshot AI | Kimi | moonshotai/kimi-k2-thinking | Openai chat | Yes | 262K | 262K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M · cache read $0.15/M output $2.5/M | 2025-11-06 | 2026-06-29 | |
| MiniMax-M2 minimax/minimax/m2 | MiniMax | Minimax | minimax/minimax-m2 | Openai chat | Yes | 197K | 128K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.03/M output $1.2/M | 2025-10-27 | 2025-10-28 | |
| Qwen3 VL 8B Instruct alibaba/qwen/qwen3-vl-8b-instruct | Alibaba | Qwen | qwen/qwen3-vl-8b-instruct | Openai chat | Yes | 262K | 33K | ImageText | Text | -No | Yes | Yes | Yes | Open weight | input $0.08/M output $0.5/M | 2025-10-14 | 2025-10-17 | |
| Qwen3 VL 30B A3B Instruct alibaba/qwen/qwen3-vl-30b-a3b-instruct | Alibaba | Qwen | qwen/qwen3-vl-30b-a3b-instruct | Openai chat | Yes | 262K | 33K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | input $0.2/M output $0.7/M | 2025-10-06 | 2025-10-11 | |
| Qwen3 VL 30B A3B Thinking alibaba/qwen/qwen3-vl-30b-a3b-thinking | Alibaba | Qwen | qwen/qwen3-vl-30b-a3b-thinking | Openai chat | Yes | 262K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0.2/M output $1/M | 2025-10-06 | 2025-10-11 | |
| DeepSeek V3.2 Exp deepseek/deepseek/v3-2-exp | DeepSeek | DeepSeek | deepseek/deepseek-v3.2-exp | Openai chat | Yes | 164K | 66K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.27/M output $0.41/M | 2025-09-29 | 2025-09-29 | |
| Qwen3 Max alibaba/qwen/qwen3-max | Alibaba | Qwen | qwen/qwen3-max | Openai chat | Yes | 262K | 66K | Text | Text | -No | Yes | Yes | Yes | Closed | input $2.11/M output $8.45/M | 2025-09-23 | 2026-01-23 | |
| Qwen3 VL 235B A22B Instruct alibaba/qwen/qwen3-vl-235b-a22b-instruct | Alibaba | Qwen | qwen/qwen3-vl-235b-a22b-instruct | Openai chat | Yes | 262K | 33K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | input $0.3/M output $1.5/M | 2025-09-23 | 2025-09-24 | |
| Qwen3 VL 235B A22B Thinking alibaba/qwen/qwen3-vl-235b-a22b-thinking | Alibaba | Qwen | qwen/qwen3-vl-235b-a22b-thinking | Openai chat | Yes | 131K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0.98/M output $3.95/M | 2025-09-23 | 2025-09-24 | |
| DeepSeek V3.1 Terminus deepseek/deepseek/v3-1-terminus | DeepSeek | DeepSeek | deepseek/deepseek-v3.1-terminus | Openai chat | Yes | 164K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.27/M · cache read $0.135/M output $1/M | 2025-09-22 | 2025-09-22 | |
| Kimi K2 0905 moonshotai/kimi/k2-0905 | Moonshot AI | Kimi | moonshotai/kimi-k2-0905 | Openai chat | Yes | 262K | 100K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.6/M output $2.5/M | 2025-09-04 | 2026-01-01 | |
| Qwen3-Next 80B-A3B (Thinking) alibaba/qwen/qwen3-next-80b-a3b-thinking | Alibaba | Qwen | qwen/qwen3-next-80b-a3b-thinking | Openai chat | Yes | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.15/M output $1.5/M | 2025-09 | 2026-01-01 | |
| Qwen3-Next 80B-A3B Instruct alibaba/qwen/qwen3-next-80b-a3b-instruct | Alibaba | Qwen | qwen/qwen3-next-80b-a3b-instruct | Openai chat | Yes | 131K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.15/M output $1.5/M | 2025-09 | 2026-07-22 | |
| GPT OSS 120B openai/gpt/oss-120b | OpenAI | GPT | openai/gpt-oss-120b | Openai chat | Yes | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.05/M output $0.25/M | 2025-08-05 | 2026-07-22 | |
| GPT OSS 20B openai/gpt/oss-20b | OpenAI | GPT | openai/gpt-oss-20b | Openai chat | Yes | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.04/M output $0.15/M | 2025-08-05 | 2026-03-01 | |
| Qwen3 235B A22B Thinking 2507 alibaba/qwen/qwen3-235b-a22b-thinking-2507 | Alibaba | Qwen | qwen/qwen3-235b-a22b-thinking-2507 | Openai chat | Yes | 262K | - | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M output $3/M | 2025-07-25 | 2026-01-01 | |
| ERNIE 4.5 VL 424B A47B baidu/ernie/4-5-vl-424b-a47b | BABaidu | Ernie | baidu/ernie-4.5-vl-424b-a47b | Openai chat | Yes | 123K | 16K | ImageText | Text | Yes | -No | -No | Yes | Open weight | input $0.42/M output $1.25/M | 2025-06-30 | 2026-01-01 | |
| R1 0528 deepseek/deepseek/r1-0528 | DeepSeek | DeepSeek | deepseek/deepseek-r1-0528 | Openai chat | Yes | 164K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.7/M · cache read $0.35/M output $2.5/M | 2025-05-28 | 2026-01-01 | |
| Qwen3-Coder 30B-A3B Instruct alibaba/qwen/qwen3-coder-30b-a3b-instruct | Alibaba | Qwen | qwen/qwen3-coder-30b-a3b-instruct | Openai chat | Yes | 262K | 66K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.07/M output $0.27/M | 2025-04 | 2026-03-17 | |
| Gemma 3 12B google/gemma/3-12b-it | Gemma | google/gemma-3-12b-it | Openai chat | Yes | 131K | 16K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | input $0.05/M output $0.1/M | 2025-03-13 | 2025-03-13 | ||
| Gemma 3 27B google/gemma/3-27b-it | Gemma | google/gemma-3-27b-it | Openai chat | Yes | 262K | 131K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | input $0.119/M output $0.2/M | 2025-03-12 | 2026-02-04 | ||
| R1 Distill Llama 70B deepseek/deepseek/r1-distill-llama-70b | DeepSeek | DeepSeek | deepseek/deepseek-r1-distill-llama-70b | Openai chat | Yes | 8.2K | 8.2K | Text | Text | Yes | -No | -No | Yes | Open weight | input $0.8/M output $0.8/M | 2025-01-23 | 2025-01-27 | |
| Llama-3.3-70B-Instruct meta/llama/3-3-70b-instruct | Meta | Llama | meta-llama/llama-3.3-70b-instruct | Openai chat | Yes | 128K | 4.1K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.135/M output $0.4/M | 2024-12-06 | 2026-07-22 | |
| Llama 3.2 3B Instruct meta/llama/3-2-3b-instruct | Meta | Llama | meta-llama/llama-3.2-3b-instruct | Openai chat | Yes | 131K | 131K | Text | Text | -No | -No | Yes | Yes | Open weight | input $0.03/M output $0.05/M | 2024-09-25 | 2024-09-25 | |
| Qwen2.5 72B Instruct alibaba/qwen/2-5-72b-instruct | Alibaba | Qwen | qwen/qwen-2.5-72b-instruct | Openai chat | Yes | 33K | 16K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.38/M output $0.4/M | 2024-09-19 | 2025-07-03 | |
| Qwen2.5-VL 72B Instruct alibaba/qwen/qwen2-5-vl-72b-instruct | Alibaba | Qwen | qwen/qwen2.5-vl-72b-instruct | Openai chat | Yes | 131K | 8.2K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | input $0.8/M output $0.8/M | 2024-09 | 2025-08-05 | |
| Llama 3.1 8B Instruct meta/llama/3-1-8b-instruct | Meta | Llama | meta-llama/llama-3.1-8b-instruct | Openai chat | Yes | 131K | 131K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.02/M output $0.05/M | 2024-07-23 | 2024-07-24 | |
| Mistral Nemo mistral/mistral/nemo | Mistral AI | Mistral | mistralai/mistral-nemo | Openai chat | Yes | 128K | 128K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.04/M output $0.17/M | 2024-07-01 | 2024-07-30 | |
| WizardLM-2 8x22B microsoft/wizardlm/2-8x22b | Microsoft | Wizardlm | microsoft/wizardlm-2-8x22b | Openai chat | Yes | 66K | 8K | Text | Text | -No | -No | -No | Yes | Open weight | input $0.62/M output $0.62/M | 2024-04-16 | 2025-04-15 | |
| MythoMax 13B gryphe/mythomax/l2-13b | GRGryphe | Mythomax | gryphe/mythomax-l2-13b | Openai chat | Yes | 8.2K | 4.1K | Text | Text | -No | -No | Yes | Yes | Open weight | input $0.09/M output $0.09/M | 2023-07-02 | 2024-04-25 |