Baltor Get started

Endpoints

Ollama 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://ollama.com/v1 provider documentation, read
  • OpenAI Responses: https://ollama.com/v1 The cloud address answers stateless Responses requests only. provider documentation, read
  • Anthropic Messages: https://ollama.com The cloud address needs Authorization: Bearer and does not accept x-api-key alone. provider documentation, read
  • Native API: https://ollama.com/api provider documentation, read
Authentication
Authorization: Bearer, with the key in OLLAMA_API_KEY provider documentation, read
Structured output
provider documentation, read
Tool calling
provider documentation, read
Rate limits
Usage is limited by the plan; the account's usage page shows it. Read the page provider documentation, read
Prices
Read the page provider documentation, read
Data retention
Content sent to cloud models is processed to answer the request and is not stored beyond it. Read the page provider documentation, read
Documentation
Unknown
Output limits Baltor recorded
Baltor's own provider client declares an output limit for deepseek-v4-flash:0731 (65,536 tokens, 2026-08-25), deepseek-v4-pro:0813 (65,536 tokens, 2026-08-31), deepseek-v4.1-flash (393,216 tokens, 2026-09-14), gemma4:31b (262,144 tokens, 2026-09-06), glm-5.1 (131,072 tokens, 2026-09-14), glm-5.2 (131,072 tokens, 2026-09-14), glm-5.3 (1,048,576 tokens, 2026-09-14), glm-5.3-flash (1,048,576 tokens, 2026-08-31), gpt-oss:120b (131,072 tokens, 2026-09-14), gpt-oss:20b (131,072 tokens, 2026-09-06), kimi-k2.6 (262,144 tokens, 2026-09-14), kimi-k2.7-code (262,144 tokens, 2026-09-14) and more. Baltor records, read

Harness setup

Replace deepseek-v4-flash with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama-cloud": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama Cloud",
      "options": {
        "baseURL": "https://ollama.com/v1",
        "apiKey": "{env:OLLAMA_API_KEY}"
      },
      "models": {
        "deepseek-v4-flash": {
          "name": "deepseek-v4-flash"
        }
      }
    }
  }
}
  • 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": {
    "ollama-cloud": {
      "baseUrl": "https://ollama.com/v1",
      "api": "openai-completions",
      "apiKey": "$OLLAMA_API_KEY",
      "models": [
        {
          "id": "deepseek-v4-flash"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Put this in ~/.codex/config.toml:

model = "deepseek-v4-flash"
model_provider = "ollama-cloud"

[model_providers.ollama-cloud]
name = "Ollama Cloud"
base_url = "https://ollama.com/v1"
env_key = "OLLAMA_API_KEY"
  • 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

Put this in ~/.claude/settings.json, or variables in your shell:

export ANTHROPIC_BASE_URL="https://ollama.com"
export ANTHROPIC_AUTH_TOKEN="$OLLAMA_API_KEY"
export ANTHROPIC_MODEL="deepseek-v4-flash"
claude
  • 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.
  • The cloud address needs Authorization: Bearer and does not accept x-api-key alone.

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
deepseek-v4-flash deepseek-v4-flash0.220 USD0.660 USD1,048,576 older than 30 days
DeepSeek V4 Flash 0731 deepseek-v4-flash:07310.220 USD0.660 USD1,048,576 older than 30 days
deepseek-v4-pro deepseek-v4-pro0.660 USD1.98 USD1,048,576 older than 30 days
DeepSeek V4 Pro 0813 deepseek-v4-pro:08130.660 USD1.98 USD1,048,576 older than 30 days
DeepSeek V4.1 Flash deepseek-v4.1-flash0.150 USD0.600 USD1,048,576
gemma4:31b gemma4:31b0.140 USD0.400 USD262,144 older than 30 days
glm-5.1 glm-5.11.00 USD3.20 USD202,752 older than 30 days
GLM-5.2 glm-5.21.40 USD4.40 USD976,000 older than 30 days
GLM-5.3 glm-5.31.40 USD4.40 USD1,048,576 older than 30 days
GLM-5.3-Flash glm-5.3-flash0.150 USD0.500 USD1,000,000
gpt-oss:120b gpt-oss:120b0.150 USD0.600 USD131,072 older than 30 days
gpt-oss:20b gpt-oss:20b0.070 USD0.300 USD131,072 older than 30 days
kimi-k2.5 kimi-k2.5UnknownUnknown262,144
kimi-k2.6 kimi-k2.60.950 USD4.00 USD262,144 older than 30 days
kimi-k2.7-code kimi-k2.7-code0.950 USD4.00 USD262,144 older than 30 days
kimi-k3 kimi-k33.00 USD15.00 USD1,048,576 older than 30 days
minimax-m2.5 minimax-m2.5UnknownUnknown204,800
minimax-m2.7 minimax-m2.70.300 USD1.20 USD196,608 older than 30 days
minimax-m3 minimax-m30.600 USD2.40 USD512,000 older than 30 days
mistral-large-3:675b mistral-large-3:675b0.500 USD1.50 USD262,144 older than 30 days
nemotron-3-nano:30b nemotron-3-nano:30b0.060 USD0.240 USD1,048,576 older than 30 days
nemotron-3-super nemotron-3-super0.015 USD0.600 USD262,144 older than 30 days
nemotron-3-ultra nemotron-3-ultra0.100 USD3.00 USD262,144 older than 30 days
qwen3.5:397b qwen3.5:397b0.600 USD3.60 USD262,144 older than 30 days