All Providers
107Models
22Families
1.0MMax Context
$0.02–$3Input Cost/MTok
$0.02–$15Output Cost/MTok
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Setup
Set the following environment variable to use NovitaAI:
NOVITA_API_KEYModels (107)
| Model | Model ID | Input Cost | Output Cost | Context | Capabilities |
|---|---|---|---|---|---|
| PaddleOCR VL | paddlepaddle/paddleocr-vl | $0.02/MTok | $0.02/MTok | 16.4K | Open |
| Llama 3.1 8B Instructllama | meta-llama/llama-3.1-8b-instruct | $0.02/MTok | $0.05/MTok | 16.4K | Open |
| Qwen3 4B | qwen/qwen3-4b-fp8 | $0.03/MTok | $0.03/MTok | 128K | ReasoningOpen |
| DeepSeek OCR | deepseek/deepseek-ocr | $0.03/MTok | $0.03/MTok | 8.2K | Open |
| deepseek deepseek ocr 2 | deepseek/deepseek-ocr-2 | $0.03/MTok | $0.03/MTok | 8.2K | Open |
| Llama 3.2 3B Instructllama | meta-llama/llama-3.2-3b-instruct | $0.03/MTok | $0.05/MTok | 32.8K | Open |
| Qwen3 8B | qwen/qwen3-8b-fp8 | $0.04/MTok | $0.14/MTok | 128K | ReasoningOpen |
| AutoGLM Phone 9B Multilingual | zai-org/autoglm-phone-9b-multilingual | $0.04/MTok | $0.14/MTok | 65.5K | Open |
| Mistral Nemomistral-nemo | mistralai/mistral-nemo | $0.04/MTok | $0.17/MTok | 60.3K | Open |
| Llama 3 8B Instructllama | meta-llama/llama-3-8b-instruct | $0.04/MTok | $0.04/MTok | 8.2K | Open |
| GPT OSS 20B | openai/gpt-oss-20b | $0.04/MTok | $0.15/MTok | 131.1K | ReasoningOpen |
| Gemma 3 12Bgemma | google/gemma-3-12b-it | $0.05/MTok | $0.10/MTok | 131.1K | Open |
| OpenAI GPT OSS 120B | openai/gpt-oss-120b | $0.05/MTok | $0.25/MTok | 131.1K | ReasoningToolsOpen |
| Sao10k L3 8B Lunaris | sao10K/l3-8b-lunaris | $0.05/MTok | $0.05/MTok | 8.2K | Open |
| L3 8B Stheno V3.2llama | sao10K/L3-8B-stheno-v3.2 | $0.05/MTok | $0.05/MTok | 8.2K | ToolsOpen |
| DeepSeek R1 0528 Qwen3 8B | deepseek/deepseek-r1-0528-qwen3-8b | $0.06/MTok | $0.09/MTok | 128K | ReasoningOpen |
| Qwen3 Coder 30b A3B Instruct | qwen/qwen3-coder-30b-a3b-instruct | $0.07/MTok | $0.27/MTok | 160K | ToolsOpen |
| Qwen 2.5 7B Instruct | qwen/qwen2.5-7b-instruct | $0.07/MTok | $0.07/MTok | 32K | ToolsOpen |
| ERNIE 4.5 21B A3B Thinkingernie | baidu/ernie-4.5-21B-a3b-thinking | $0.07/MTok | $0.28/MTok | 131.1K | ReasoningOpen |
| ERNIE 4.5 21B A3Bernie | baidu/ernie-4.5-21B-a3b | $0.07/MTok | $0.28/MTok | 120K | ToolsOpen |
| GLM 4.7 Flashglm-flash | zai-org/glm-4.7-flash | $0.07/MTok | $0.40/MTok | 200K | ReasoningToolsOpen |
| baichuan m2 32bbaichuan | baichuan/baichuan-m2-32b | $0.07/MTok | $0.07/MTok | 131.1K | Open |
| qwen qwen3 vl 8b instruct | qwen/qwen3-vl-8b-instruct | $0.08/MTok | $0.50/MTok | 131.1K | ToolsOpen |
| Qwen3 30B A3B | qwen/qwen3-30b-a3b-fp8 | $0.09/MTok | $0.45/MTok | 41.0K | ReasoningOpen |
| Qwen3 235B A22B Instruct 2507qwen | qwen/qwen3-235b-a22b-instruct-2507 | $0.09/MTok | $0.58/MTok | 131.1K | ToolsOpen |
| Mythomax L2 13B | gryphe/mythomax-l2-13b | $0.09/MTok | $0.09/MTok | 4.1K | Open |
| Qwen3 32B | qwen/qwen3-32b-fp8 | $0.10/MTok | $0.45/MTok | 41.0K | ReasoningOpen |
| Ling 2.6 flashling | inclusionai/ling-2.6-flash | $0.10/MTok | $0.30/MTok | 262.1K | ToolsOpen |
| XiaomiMiMo MiMo V2 Flashmimo | xiaomimimo/mimo-v2-flash | $0.10/MTok | $0.30/MTok | 262.1K | ReasoningToolsOpen |
| Gemma 3 27Bgemma | google/gemma-3-27b-it | $0.12/MTok | $0.20/MTok | 98.3K | Open |
| Gemma 4 26B A4Bgemma | google/gemma-4-26b-a4b-it | $0.13/MTok | $0.40/MTok | 262.1K | ReasoningToolsOpen |
| GLM 4.5 Airglm-air | zai-org/glm-4.5-air | $0.13/MTok | $0.85/MTok | 131.1K | ReasoningToolsOpen |
| Llama 3.3 70B Instructllama | meta-llama/llama-3.3-70b-instruct | $0.14/MTok | $0.40/MTok | 131.1K | ToolsOpen |
| ERNIE 4.5 VL 28B A3B | baidu/ernie-4.5-vl-28b-a3b | $0.14/MTok | $0.56/MTok | 30K | ReasoningToolsOpen |
| Gemma 4 31Bgemma | google/gemma-4-31b-it | $0.14/MTok | $0.40/MTok | 262.1K | ReasoningToolsOpen |
| DeepSeek V4 Flashdeepseek-flash | deepseek/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1.0M | ReasoningToolsOpen |
| Hermes 2 Pro Llama 3 8B | nousresearch/hermes-2-pro-llama-3-8b | $0.14/MTok | $0.14/MTok | 8.2K | Open |
| Qwen3 Next 80B A3B Thinking | qwen/qwen3-next-80b-a3b-thinking | $0.15/MTok | $1.50/MTok | 131.1K | ReasoningToolsOpen |
| Qwen3 Next 80B A3B Instruct | qwen/qwen3-next-80b-a3b-instruct | $0.15/MTok | $1.50/MTok | 131.1K | ToolsOpen |
| DeepSeek R1 Distill Qwen 14Bdeepseek-thinking | deepseek/deepseek-r1-distill-qwen-14b | $0.15/MTok | $0.15/MTok | 32.8K | Open |
| Llama 4 Scout Instruct | meta-llama/llama-4-scout-17b-16e-instruct | $0.18/MTok | $0.59/MTok | 131.1K | Open |
| Qwen3 235B A22B | qwen/qwen3-235b-a22b-fp8 | $0.20/MTok | $0.80/MTok | 41.0K | ReasoningOpen |
| Qwen3 Coder Nextqwen | qwen/qwen3-coder-next | $0.20/MTok | $1.50/MTok | 262.1K | ToolsOpen |
| qwen qwen3 vl 30b a3b instruct | qwen/qwen3-vl-30b-a3b-instruct | $0.20/MTok | $0.70/MTok | 131.1K | ToolsOpen |
| qwen qwen3 vl 30b a3b thinking | qwen/qwen3-vl-30b-a3b-thinking | $0.20/MTok | $1/MTok | 131.1K | ToolsOpen |
| Qwen3 Omni 30B A3B Instructqwen | qwen/qwen3-omni-30b-a3b-instruct | $0.25/MTok | $0.97/MTok | 65.5K | ToolsOpen |
| Qwen 3.5 35B A3Bqwen | qwen/qwen3.5-35b-a3b | $0.25/MTok | $2/MTok | 262.1K | ReasoningToolsOpen |
| Qwen3 Omni 30B A3B Thinking | qwen/qwen3-omni-30b-a3b-thinking | $0.25/MTok | $0.97/MTok | 65.5K | ReasoningToolsOpen |
| Qwen MT Plus | qwen/qwen-mt-plus | $0.25/MTok | $0.75/MTok | 16.4K | Open |
| Deepseek V3.2deepseek | deepseek/deepseek-v3.2 | $0.27/MTok | $0.40/MTok | 163.8K | ReasoningToolsOpen |
| Deepseek V3.2 Exp | deepseek/deepseek-v3.2-exp | $0.27/MTok | $0.41/MTok | 163.8K | ReasoningToolsOpen |
| Deepseek V3.1 Terminusdeepseek | deepseek/deepseek-v3.1-terminus | $0.27/MTok | $1/MTok | 131.1K | ReasoningToolsOpen |
| DeepSeek V3 0324deepseek | deepseek/deepseek-v3-0324 | $0.27/MTok | $1.12/MTok | 163.8K | ToolsOpen |
| DeepSeek V3.1deepseek | deepseek/deepseek-v3.1 | $0.27/MTok | $1/MTok | 131.1K | ReasoningToolsOpen |
| Llama 4 Maverick Instruct | meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | $0.27/MTok | $0.85/MTok | 1.0M | Open |
| ERNIE 4.5 300B A47B | baidu/ernie-4.5-300b-a47b-paddle | $0.28/MTok | $1.10/MTok | 123K | Open |
| Qwen3 235B A22b Thinking 2507qwen | qwen/qwen3-235b-a22b-thinking-2507 | $0.30/MTok | $3/MTok | 131.1K | ReasoningToolsOpen |
| Qwen 3.5 27Bqwen | qwen/qwen3.5-27b | $0.30/MTok | $2.40/MTok | 262.1K | ReasoningToolsOpen |
| Qwen3 VL 235B A22B Instruct | qwen/qwen3-vl-235b-a22b-instruct | $0.30/MTok | $1.50/MTok | 131.1K | ToolsOpen |
| Kat Coder Pro | kwaipilot/kat-coder-pro | $0.30/MTok | $1.20/MTok | 256K | ToolsOpen |
| Minimax M2.1minimax | minimax/minimax-m2.1 | $0.30/MTok | $1.20/MTok | 204.8K | ToolsOpen |
| MiniMax M2minimax | minimax/minimax-m2 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningToolsOpen |
| MiniMax M2.7minimax-m2.7 | minimax/minimax-m2.7 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningToolsOpen |
| MiniMax M2.5minimax | minimax/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningTools |
| GLM 4.6Vglmv | zai-org/glm-4.6v | $0.30/MTok | $0.90/MTok | 131.1K | ReasoningToolsOpen |
| DeepSeek R1 Distill Qwen 32Bdeepseek-thinking | deepseek/deepseek-r1-distill-qwen-32b | $0.30/MTok | $0.30/MTok | 64K | Open |
| Ring 2.6 1Tring | inclusionai/ring-2.6-1t | $0.30/MTok | $2.50/MTok | 262.1K | ReasoningTools |
| Ling 2.6 1Tling | inclusionai/ling-2.6-1t | $0.30/MTok | $2.50/MTok | 262.1K | ToolsOpen |
| Qwen 2.5 72B Instructqwen | qwen/qwen-2.5-72b-instruct | $0.38/MTok | $0.40/MTok | 32K | ToolsOpen |
| Qwen3 Coder 480B A35B Instructqwen | qwen/qwen3-coder-480b-a35b-instruct | $0.38/MTok | $1.55/MTok | 262.1K | ToolsOpen |
| ERNIE 4.5 VL 28B A3B Thinking | baidu/ernie-4.5-vl-28b-a3b-thinking | $0.39/MTok | $0.39/MTok | 131.1K | ReasoningToolsOpen |
| Qwen 3.5 122B A10Bqwen | qwen/qwen3.5-122b-a10b | $0.40/MTok | $3.20/MTok | 262.1K | ReasoningToolsOpen |
| DeepSeek V3 (Turbo) | deepseek/deepseek-v3-turbo | $0.40/MTok | $1.30/MTok | 64K | ToolsOpen |
| ERNIE 4.5 VL 424B A47B | baidu/ernie-4.5-vl-424b-a47b | $0.42/MTok | $1.25/MTok | 123K | ReasoningOpen |
| Llama3 70B Instructllama | meta-llama/llama-3-70b-instruct | $0.51/MTok | $0.74/MTok | 8.2K | Open |
| MiMo V2.5 Promimo | xiaomimimo/mimo-v2.5-pro | $0.52/MTok | $1.04/MTok | 1.0M | ReasoningToolsOpen |
| GLM 4.6glm | zai-org/glm-4.6 | $0.55/MTok | $2.20/MTok | 204.8K | ReasoningToolsOpen |
| MiniMax M1minimax | minimaxai/minimax-m1-80k | $0.55/MTok | $2.20/MTok | 1M | ReasoningToolsOpen |
| Kimi K2 Instruct | moonshotai/kimi-k2-instruct | $0.57/MTok | $2.30/MTok | 131.1K | ToolsOpen |
| Qwen 3.5 397B A17Bqwen | qwen/qwen3.5-397b-a17b | $0.60/MTok | $3.60/MTok | 262.1K | ReasoningToolsOpen |
| MiniMax M2.7 highspeedminimax | minimax/minimax-m2.7-highspeed | $0.60/MTok | $2.40/MTok | 204.8K | ReasoningToolsOpen |
| MiniMax M2.5 Highspeedminimax-m2.5 | minimax/minimax-m2.5-highspeed | $0.60/MTok | $2.40/MTok | 204.8K | ReasoningTools |
| GLM 4.7glm | zai-org/glm-4.7 | $0.60/MTok | $2.20/MTok | 204.8K | ReasoningToolsOpen |
| GLM 4.5glm | zai-org/glm-4.5 | $0.60/MTok | $2.20/MTok | 131.1K | ReasoningToolsOpen |
| GLM 4.5Vglmv | zai-org/glm-4.5v | $0.60/MTok | $1.80/MTok | 65.5K | ReasoningToolsOpen |
| Kimi K2 0905kimi-k2 | moonshotai/kimi-k2-0905 | $0.60/MTok | $2.50/MTok | 262.1K | ToolsOpen |
| Kimi K2 Thinkingkimi-thinking | moonshotai/kimi-k2-thinking | $0.60/MTok | $2.50/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.5kimi-k2 | moonshotai/kimi-k2.5 | $0.60/MTok | $3/MTok | 262.1K | ReasoningToolsOpen |
| Wizardlm 2 8x22B | microsoft/wizardlm-2-8x22b | $0.62/MTok | $0.62/MTok | 65.5K | Open |
| Deepseek Prover V2 671B | deepseek/deepseek-prover-v2-671b | $0.70/MTok | $2.50/MTok | 160K | Open |
| DeepSeek R1 0528deepseek-thinking | deepseek/deepseek-r1-0528 | $0.70/MTok | $2.50/MTok | 163.8K | ReasoningToolsOpen |
| DeepSeek R1 (Turbo) | deepseek/deepseek-r1-turbo | $0.70/MTok | $2.50/MTok | 64K | ReasoningToolsOpen |
| Qwen 2.5 VL 72B Instructqwen | qwen/qwen2.5-vl-72b-instruct | $0.80/MTok | $0.80/MTok | 32.8K | Open |
| DeepSeek R1 Distill LLama 70Bdeepseek-thinking | deepseek/deepseek-r1-distill-llama-70b | $0.80/MTok | $0.80/MTok | 8.2K | ReasoningOpen |
| Kimi K2.6kimi-k2 | moonshotai/kimi-k2.6 | $0.80/MTok | $3.40/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.7 Codekimi-k2 | moonshotai/kimi-k2.7-code | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| Qwen3 VL 235B A22B Thinking | qwen/qwen3-vl-235b-a22b-thinking | $0.98/MTok | $3.95/MTok | 131.1K | ReasoningOpen |
| GLM 5glm | zai-org/glm-5 | $1/MTok | $3.20/MTok | 202.8K | ReasoningToolsOpen |
| Qwen 3.7 Maxqwen | qwen/qwen3.7-max | $1.25/MTok | $3.75/MTok | 1M | ReasoningTools |
| GLM 5.1glm | zai-org/glm-5.1 | $1.38/MTok | $4.40/MTok | 204.8K | ReasoningToolsOpen |
| GLM 5.2glm | zai-org/glm-5.2 | $1.40/MTok | $4.40/MTok | 1.0M | ReasoningToolsOpen |
| L3 70B Euryale V2.1 | sao10K/l3-70b-euryale-v2.1 | $1.48/MTok | $1.48/MTok | 8.2K | ToolsOpen |
| L31 70B Euryale V2.2 | sao10K/l31-70b-euryale-v2.2 | $1.48/MTok | $1.48/MTok | 8.2K | ToolsOpen |
| DeepSeek V4 Prodeepseek-thinking | deepseek/deepseek-v4-pro | $1.60/MTok | $3.20/MTok | 1.0M | ReasoningToolsOpen |
| MiMo V2 Promimo | xiaomimimo/mimo-v2-pro | $2/MTok | $6/MTok | 1.0M | ReasoningTools |
| Qwen3 Maxqwen | qwen/qwen3-max | $2.11/MTok | $8.45/MTok | 262.1K | Tools |
| Kimi K3kimi-k3 | moonshotai/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |