Baltor Get started

Endpoints

NEAR AI Cloud

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://cloud-api.near.ai/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in NEARAI_API_KEY models.dev, read
Structured output
Unknown
Tool calling
28 of 32 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 Qwen/Qwen3-Embedding-0.6B with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "nearai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "NEAR AI Cloud",
      "options": {
        "baseURL": "https://cloud-api.near.ai/v1",
        "apiKey": "{env:NEARAI_API_KEY}"
      },
      "models": {
        "Qwen/Qwen3-Embedding-0.6B": {
          "name": "Qwen/Qwen3-Embedding-0.6B"
        }
      }
    }
  }
}
  • 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": {
    "nearai": {
      "baseUrl": "https://cloud-api.near.ai/v1",
      "api": "openai-completions",
      "apiKey": "$NEARAI_API_KEY",
      "models": [
        {
          "id": "Qwen/Qwen3-Embedding-0.6B"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and NEAR AI Cloud 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 NEAR AI Cloud 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
Qwen3 Embedding 0.6B Qwen/Qwen3-Embedding-0.6B0.010 USD0.010 USD32,768 older than 30 days
Qwen3 Reranker 0.6B Qwen/Qwen3-Reranker-0.6B0.010 USD0.010 USD40,960 older than 30 days
Qwen3-VL 30B-A3B Instruct Qwen/Qwen3-VL-30B-A3B-Instruct0.150 USD0.550 USD16,384 older than 30 days
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B-FP80.170 USD1.10 USD262,144 older than 30 days
Claude Haiku 4.5 (latest) anthropic/claude-haiku-4-51.00 USD5.00 USD200,000 older than 30 days
Claude Opus 4.6 anthropic/claude-opus-4-65.00 USD25.00 USD200,000 older than 30 days
Claude Opus 4.7 anthropic/claude-opus-4-75.00 USD25.00 USD1,000,000 older than 30 days
Claude Sonnet 4.5 (latest) anthropic/claude-sonnet-4-53.00 USD15.00 USD200,000 older than 30 days
Claude Sonnet 4.6 anthropic/claude-sonnet-4-63.00 USD15.00 USD1,000,000 older than 30 days
FLUX.2 Klein 4B black-forest-labs/FLUX.2-klein-4B1.00 USD1.00 USD128,000 older than 30 days
Gemini 2.5 Flash google/gemini-2.5-flash0.300 USD2.50 USD1,048,576 older than 30 days
Gemini 2.5 Flash-Lite google/gemini-2.5-flash-lite0.100 USD0.400 USD1,048,576 older than 30 days
Gemini 2.5 Pro google/gemini-2.5-pro1.25 USD10.00 USD1,048,576 older than 30 days
Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite0.250 USD1.50 USD1,048,576 older than 30 days
Gemini 3.5 Flash google/gemini-3.5-flash1.50 USD9.00 USD1,048,576 older than 30 days
GPT-4.1 openai/gpt-4.12.00 USD8.00 USD1,047,576 older than 30 days
GPT-4.1 mini openai/gpt-4.1-mini0.400 USD1.60 USD1,047,576 older than 30 days
GPT-4.1 nano openai/gpt-4.1-nano0.100 USD0.400 USD1,047,576 older than 30 days
GPT-5 openai/gpt-51.25 USD10.00 USD400,000 older than 30 days
GPT-5 Mini openai/gpt-5-mini0.250 USD2.00 USD400,000 older than 30 days
GPT-5 Nano openai/gpt-5-nano0.050 USD0.400 USD400,000 older than 30 days
GPT-5.1 openai/gpt-5.11.25 USD10.00 USD400,000 older than 30 days
GPT-5.2 openai/gpt-5.21.75 USD14.00 USD400,000 older than 30 days
GPT-5.4 openai/gpt-5.42.50 USD15.00 USD1,050,000 older than 30 days
GPT-5.4 mini openai/gpt-5.4-mini0.750 USD4.50 USD400,000 older than 30 days
GPT-5.4 nano openai/gpt-5.4-nano0.200 USD1.25 USD400,000 older than 30 days
GPT-5.5 openai/gpt-5.55.00 USD30.00 USD1,050,000 older than 30 days
o3 openai/o32.00 USD8.00 USD200,000 older than 30 days
o3-mini openai/o3-mini1.10 USD4.40 USD200,000 older than 30 days
o4-mini openai/o4-mini1.10 USD4.40 USD200,000 older than 30 days
Whisper Large v3 openai/whisper-large-v30.010 USD0.010 USD448 older than 30 days
GLM-5.1 FP8 zai-org/GLM-5.1-FP81.40 USD4.40 USD202,752 older than 30 days

Sources of this page