Baltor Get started

Endpoints

NovitaAI

A hosted service with its own key and prices. This page lists the addresses it answers, the facts its documentation states, and the setup of each harness.

Addresses and facts

  • OpenAI Chat Completions: https://api.novita.ai/openai models.dev, read
Authentication
Authorization: Bearer, with the key in NOVITA_API_KEY models.dev, read
Structured output
Unknown
Tool calling
72 of 107 listed models The share of this provider's models that models.dev records with tool calling. models.dev, read
Rate limits
Unknown
Prices
Unknown
Data retention
Unknown
Documentation
Read the page models.dev, read
Output limits Baltor recorded
Unknown

Harness setup

Replace baichuan/baichuan-m2-32b with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "novita-ai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "NovitaAI",
      "options": {
        "baseURL": "https://api.novita.ai/openai",
        "apiKey": "{env:NOVITA_API_KEY}"
      },
      "models": {
        "baichuan/baichuan-m2-32b": {
          "name": "baichuan/baichuan-m2-32b"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "novita-ai": {
      "baseUrl": "https://api.novita.ai/openai",
      "api": "openai-completions",
      "apiKey": "$NOVITA_API_KEY",
      "models": [
        {
          "id": "baichuan/baichuan-m2-32b"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and NovitaAI documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and NovitaAI documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Models it lists

Prices in US dollars per million tokens, input and output, as models.dev, read records them.

ModelInputOutputContextAs of
baichuan-m2-32b baichuan/baichuan-m2-32b0.070 USD0.070 USD131,072 older than 30 days
ERNIE 4.5 21B A3B baidu/ernie-4.5-21B-a3b0.070 USD0.280 USD120,000 older than 30 days
ERNIE-4.5-21B-A3B-Thinking baidu/ernie-4.5-21B-a3b-thinking0.070 USD0.280 USD131,072 older than 30 days
ERNIE 4.5 300B A47B baidu/ernie-4.5-300b-a47b-paddle0.280 USD1.10 USD123,000 older than 30 days
ERNIE 4.5 VL 28B A3B baidu/ernie-4.5-vl-28b-a3b0.140 USD0.560 USD30,000 older than 30 days
ERNIE-4.5-VL-28B-A3B-Thinking baidu/ernie-4.5-vl-28b-a3b-thinking0.390 USD0.390 USD131,072 older than 30 days
ERNIE 4.5 VL 424B A47B baidu/ernie-4.5-vl-424b-a47b0.420 USD1.25 USD123,000 older than 30 days
DeepSeek-OCR deepseek/deepseek-ocr0.030 USD0.030 USD8,192 older than 30 days
deepseek/deepseek-ocr-2 deepseek/deepseek-ocr-20.030 USD0.030 USD8,192 older than 30 days
Deepseek Prover V2 671B deepseek/deepseek-prover-v2-671b0.700 USD2.50 USD160,000 older than 30 days
DeepSeek R1 0528 deepseek/deepseek-r1-05280.700 USD2.50 USD163,840 older than 30 days
DeepSeek R1 0528 Qwen3 8B deepseek/deepseek-r1-0528-qwen3-8b0.060 USD0.090 USD128,000 older than 30 days
DeepSeek R1 Distill LLama 70B deepseek/deepseek-r1-distill-llama-70b0.800 USD0.800 USD8,192 older than 30 days
DeepSeek R1 Distill Qwen 14B deepseek/deepseek-r1-distill-qwen-14b0.150 USD0.150 USD32,768 older than 30 days
DeepSeek R1 Distill Qwen 32B deepseek/deepseek-r1-distill-qwen-32b0.300 USD0.300 USD64,000 older than 30 days
DeepSeek R1 (Turbo) deepseek/deepseek-r1-turbo0.700 USD2.50 USD64,000 older than 30 days
DeepSeek V3 0324 deepseek/deepseek-v3-03240.270 USD1.12 USD163,840 older than 30 days
DeepSeek V3 (Turbo) deepseek/deepseek-v3-turbo0.400 USD1.30 USD64,000 older than 30 days
DeepSeek V3.1 deepseek/deepseek-v3.10.270 USD1.00 USD131,072 older than 30 days
Deepseek V3.1 Terminus deepseek/deepseek-v3.1-terminus0.270 USD1.00 USD131,072 older than 30 days
Deepseek V3.2 deepseek/deepseek-v3.20.269 USD0.400 USD163,840 older than 30 days
Deepseek V3.2 Exp deepseek/deepseek-v3.2-exp0.270 USD0.410 USD163,840 older than 30 days
DeepSeek V4 Flash deepseek/deepseek-v4-flash0.140 USD0.280 USD1,048,576 older than 30 days
DeepSeek V4 Pro deepseek/deepseek-v4-pro1.60 USD3.20 USD1,048,576 older than 30 days
Gemma 3 12B google/gemma-3-12b-it0.050 USD0.100 USD131,072 older than 30 days
Gemma 3 27B google/gemma-3-27b-it0.119 USD0.200 USD98,304 older than 30 days
Gemma 4 26B A4B google/gemma-4-26b-a4b-it0.130 USD0.400 USD262,144 older than 30 days
Gemma 4 31B google/gemma-4-31b-it0.140 USD0.400 USD262,144 older than 30 days
Mythomax L2 13B gryphe/mythomax-l2-13b0.090 USD0.090 USD4,096 older than 30 days
Ling-2.6-1T inclusionai/ling-2.6-1t0.300 USD2.50 USD262,144 older than 30 days
Ling-2.6-flash inclusionai/ling-2.6-flash0.100 USD0.300 USD262,144 older than 30 days
Ring-2.6-1T inclusionai/ring-2.6-1t0.300 USD2.50 USD262,144 older than 30 days
Kat Coder Pro kwaipilot/kat-coder-pro0.300 USD1.20 USD256,000 older than 30 days
Llama3 70B Instruct meta-llama/llama-3-70b-instruct0.510 USD0.740 USD8,192 older than 30 days
Llama 3 8B Instruct meta-llama/llama-3-8b-instruct0.040 USD0.040 USD8,192 older than 30 days
Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct0.020 USD0.050 USD16,384 older than 30 days
Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct0.030 USD0.050 USD32,768 older than 30 days
Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct0.135 USD0.400 USD131,072 older than 30 days
Llama 4 Maverick Instruct meta-llama/llama-4-maverick-17b-128e-instruct-fp80.270 USD0.850 USD1,048,576 older than 30 days
Llama 4 Scout Instruct meta-llama/llama-4-scout-17b-16e-instruct0.180 USD0.590 USD131,072 older than 30 days
Wizardlm 2 8x22B microsoft/wizardlm-2-8x22b0.620 USD0.620 USD65,535 older than 30 days
MiniMax-M2 minimax/minimax-m20.300 USD1.20 USD204,800 older than 30 days
Minimax M2.1 minimax/minimax-m2.10.300 USD1.20 USD204,800 older than 30 days
MiniMax M2.5 minimax/minimax-m2.50.300 USD1.20 USD204,800 older than 30 days
MiniMax M2.5 Highspeed minimax/minimax-m2.5-highspeed0.600 USD2.40 USD204,800 older than 30 days
MiniMax M2.7 minimax/minimax-m2.70.300 USD1.20 USD204,800 older than 30 days
MiniMax-M2.7-highspeed minimax/minimax-m2.7-highspeed0.600 USD2.40 USD204,800 older than 30 days
MiniMax M1 minimaxai/minimax-m1-80k0.550 USD2.20 USD1,000,000 older than 30 days
Mistral Nemo mistralai/mistral-nemo0.040 USD0.170 USD60,288 older than 30 days
Kimi K2 0905 moonshotai/kimi-k2-09050.600 USD2.50 USD262,144 older than 30 days
Kimi K2 Instruct moonshotai/kimi-k2-instruct0.570 USD2.30 USD131,072 older than 30 days
Kimi K2 Thinking moonshotai/kimi-k2-thinking0.600 USD2.50 USD262,144 older than 30 days
Kimi K2.5 moonshotai/kimi-k2.50.600 USD3.00 USD262,144 older than 30 days
Kimi K2.6 moonshotai/kimi-k2.60.800 USD3.40 USD262,144 older than 30 days
Kimi K2.7 Code moonshotai/kimi-k2.7-code0.950 USD4.00 USD262,144 older than 30 days
Kimi K3 moonshotai/kimi-k33.00 USD15.00 USD1,048,576 older than 30 days
Hermes 2 Pro Llama 3 8B nousresearch/hermes-2-pro-llama-3-8b0.140 USD0.140 USD8,192 older than 30 days
OpenAI GPT OSS 120B openai/gpt-oss-120b0.050 USD0.250 USD131,072 older than 30 days
OpenAI: GPT OSS 20B openai/gpt-oss-20b0.040 USD0.150 USD131,072 older than 30 days
PaddleOCR-VL paddlepaddle/paddleocr-vl0.020 USD0.020 USD16,384 older than 30 days
Qwen 2.5 72B Instruct qwen/qwen-2.5-72b-instruct0.380 USD0.400 USD32,000 older than 30 days
Qwen MT Plus qwen/qwen-mt-plus0.250 USD0.750 USD16,384 older than 30 days
Qwen2.5 7B Instruct qwen/qwen2.5-7b-instruct0.070 USD0.070 USD32,000 older than 30 days
Qwen2.5 VL 72B Instruct qwen/qwen2.5-vl-72b-instruct0.800 USD0.800 USD32,768 older than 30 days
Qwen3 235B A22B qwen/qwen3-235b-a22b-fp80.200 USD0.800 USD40,960 older than 30 days
Qwen3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-instruct-25070.090 USD0.580 USD131,072 older than 30 days
Qwen3 235B A22b Thinking 2507 qwen/qwen3-235b-a22b-thinking-25070.300 USD3.00 USD131,072 older than 30 days
Qwen3 30B A3B qwen/qwen3-30b-a3b-fp80.090 USD0.450 USD40,960 older than 30 days
Qwen3 32B qwen/qwen3-32b-fp80.100 USD0.450 USD40,960 older than 30 days
Qwen3 4B qwen/qwen3-4b-fp80.030 USD0.030 USD128,000 older than 30 days
Qwen3 8B qwen/qwen3-8b-fp80.035 USD0.138 USD128,000 older than 30 days
Qwen3 Coder 30b A3B Instruct qwen/qwen3-coder-30b-a3b-instruct0.070 USD0.270 USD160,000 older than 30 days
Qwen3 Coder 480B A35B Instruct qwen/qwen3-coder-480b-a35b-instruct0.380 USD1.55 USD262,144 older than 30 days
Qwen3 Coder Next qwen/qwen3-coder-next0.200 USD1.50 USD262,144 older than 30 days
Qwen3 Max qwen/qwen3-max2.11 USD8.45 USD262,144 older than 30 days
Qwen3 Next 80B A3B Instruct qwen/qwen3-next-80b-a3b-instruct0.150 USD1.50 USD131,072 older than 30 days
Qwen3 Next 80B A3B Thinking qwen/qwen3-next-80b-a3b-thinking0.150 USD1.50 USD131,072 older than 30 days
Qwen3 Omni 30B A3B Instruct qwen/qwen3-omni-30b-a3b-instruct0.250 USD0.970 USD65,536 older than 30 days
Qwen3 Omni 30B A3B Thinking qwen/qwen3-omni-30b-a3b-thinking0.250 USD0.970 USD65,536 older than 30 days
Qwen3 VL 235B A22B Instruct qwen/qwen3-vl-235b-a22b-instruct0.300 USD1.50 USD131,072 older than 30 days
Qwen3 VL 235B A22B Thinking qwen/qwen3-vl-235b-a22b-thinking0.980 USD3.95 USD131,072 older than 30 days
qwen/qwen3-vl-30b-a3b-instruct qwen/qwen3-vl-30b-a3b-instruct0.200 USD0.700 USD131,072 older than 30 days
qwen/qwen3-vl-30b-a3b-thinking qwen/qwen3-vl-30b-a3b-thinking0.200 USD1.00 USD131,072 older than 30 days
qwen/qwen3-vl-8b-instruct qwen/qwen3-vl-8b-instruct0.080 USD0.500 USD131,072 older than 30 days
Qwen3.5-122B-A10B qwen/qwen3.5-122b-a10b0.400 USD3.20 USD262,144 older than 30 days
Qwen3.5-27B qwen/qwen3.5-27b0.300 USD2.40 USD262,144 older than 30 days
Qwen3.5-35B-A3B qwen/qwen3.5-35b-a3b0.250 USD2.00 USD262,144 older than 30 days
Qwen3.5-397B-A17B qwen/qwen3.5-397b-a17b0.600 USD3.60 USD262,144 older than 30 days
Qwen3.7-Max qwen/qwen3.7-max1.25 USD3.75 USD1,000,000 older than 30 days
L3 8B Stheno V3.2 sao10K/L3-8B-stheno-v3.20.050 USD0.050 USD8,192 older than 30 days
L3 70B Euryale V2.1 sao10K/l3-70b-euryale-v2.11.48 USD1.48 USD8,192 older than 30 days
Sao10k L3 8B Lunaris sao10K/l3-8b-lunaris0.050 USD0.050 USD8,192 older than 30 days
L31 70B Euryale V2.2 sao10K/l31-70b-euryale-v2.21.48 USD1.48 USD8,192 older than 30 days
XiaomiMiMo/MiMo-V2-Flash xiaomimimo/mimo-v2-flash0.100 USD0.300 USD262,144 older than 30 days
MiMo-V2-Pro xiaomimimo/mimo-v2-pro2.00 USD6.00 USD1,048,576 older than 30 days
MiMo-V2.5-Pro xiaomimimo/mimo-v2.5-pro0.522 USD1.04 USD1,048,576 older than 30 days
AutoGLM-Phone-9B-Multilingual zai-org/autoglm-phone-9b-multilingual0.035 USD0.138 USD65,536 older than 30 days
GLM-4.5 zai-org/glm-4.50.600 USD2.20 USD131,072 older than 30 days
GLM 4.5 Air zai-org/glm-4.5-air0.130 USD0.850 USD131,072 older than 30 days
GLM 4.5V zai-org/glm-4.5v0.600 USD1.80 USD65,536 older than 30 days
GLM 4.6 zai-org/glm-4.60.550 USD2.20 USD204,800 older than 30 days
GLM 4.6V zai-org/glm-4.6v0.300 USD0.900 USD131,072 older than 30 days
GLM-4.7 zai-org/glm-4.70.600 USD2.20 USD204,800 older than 30 days
GLM-4.7-Flash zai-org/glm-4.7-flash0.070 USD0.400 USD200,000 older than 30 days
GLM-5 zai-org/glm-51.00 USD3.20 USD202,800 older than 30 days
GLM-5.1 zai-org/glm-5.11.38 USD4.40 USD204,800 older than 30 days
GLM-5.2 zai-org/glm-5.21.40 USD4.40 USD1,048,576 older than 30 days

Sources of this page