Baltor Get started

Endpoints

Jiekou.AI

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.jiekou.ai/openai models.dev, read
Authentication
Authorization: Bearer, with the key in JIEKOU_API_KEY models.dev, read
Structured output
Unknown
Tool calling
58 of 61 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 baidu/ernie-4.5-300b-a47b-paddle with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "jiekou": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Jiekou.AI",
      "options": {
        "baseURL": "https://api.jiekou.ai/openai",
        "apiKey": "{env:JIEKOU_API_KEY}"
      },
      "models": {
        "baidu/ernie-4.5-300b-a47b-paddle": {
          "name": "baidu/ernie-4.5-300b-a47b-paddle"
        }
      }
    }
  }
}
  • 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": {
    "jiekou": {
      "baseUrl": "https://api.jiekou.ai/openai",
      "api": "openai-completions",
      "apiKey": "$JIEKOU_API_KEY",
      "models": [
        {
          "id": "baidu/ernie-4.5-300b-a47b-paddle"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Jiekou.AI 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 Jiekou.AI 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
ERNIE 4.5 300B A47B baidu/ernie-4.5-300b-a47b-paddle0.280 USD1.10 USD123,000
ERNIE 4.5 VL 424B A47B baidu/ernie-4.5-vl-424b-a47b0.420 USD1.25 USD123,000
claude-haiku-4-5-20251001 claude-haiku-4-5-202510010.900 USD4.50 USD20,000
claude-opus-4-1-20250805 claude-opus-4-1-2025080513.50 USD67.50 USD200,000
claude-opus-4-20250514 claude-opus-4-2025051413.50 USD67.50 USD200,000
claude-opus-4-5-20251101 claude-opus-4-5-202511014.50 USD22.50 USD200,000
claude-opus-4-6 claude-opus-4-65.00 USD25.00 USD1,000,000
claude-sonnet-4-20250514 claude-sonnet-4-202505142.70 USD13.50 USD200,000
claude-sonnet-4-5-20250929 claude-sonnet-4-5-202509292.70 USD13.50 USD200,000
DeepSeek R1 0528 deepseek/deepseek-r1-05280.700 USD2.50 USD163,840
DeepSeek V3 0324 deepseek/deepseek-v3-03240.280 USD1.14 USD163,840
DeepSeek V3.1 deepseek/deepseek-v3.10.270 USD1.00 USD163,840
gemini-2.5-flash gemini-2.5-flash0.270 USD2.25 USD1,048,576
gemini-2.5-flash-lite gemini-2.5-flash-lite0.090 USD0.360 USD1,048,576
gemini-2.5-flash-lite-preview-06-17 gemini-2.5-flash-lite-preview-06-170.090 USD0.360 USD1,048,576
gemini-2.5-flash-lite-preview-09-2025 gemini-2.5-flash-lite-preview-09-20250.090 USD0.360 USD1,048,576
gemini-2.5-flash-preview-05-20 gemini-2.5-flash-preview-05-200.135 USD3.15 USD1,048,576
gemini-2.5-pro gemini-2.5-pro1.12 USD9.00 USD1,048,576
gemini-2.5-pro-preview-06-05 gemini-2.5-pro-preview-06-051.12 USD9.00 USD1,048,576
gemini-3-flash-preview gemini-3-flash-preview0.500 USD3.00 USD1,048,576
gemini-3-pro-preview gemini-3-pro-preview1.80 USD10.80 USD1,048,576
gpt-5-chat-latest gpt-5-chat-latest1.12 USD9.00 USD400,000
gpt-5-codex gpt-5-codex1.12 USD9.00 USD400,000
gpt-5-mini gpt-5-mini0.225 USD1.80 USD400,000
gpt-5-nano gpt-5-nano0.045 USD0.360 USD400,000
gpt-5-pro gpt-5-pro13.50 USD108.00 USD400,000
gpt-5.1 gpt-5.11.12 USD9.00 USD400,000
gpt-5.1-codex gpt-5.1-codex1.12 USD9.00 USD400,000
gpt-5.1-codex-max gpt-5.1-codex-max1.12 USD9.00 USD400,000
gpt-5.1-codex-mini gpt-5.1-codex-mini0.225 USD1.80 USD400,000
gpt-5.2 gpt-5.21.57 USD12.60 USD400,000
gpt-5.2-codex gpt-5.2-codex1.75 USD14.00 USD400,000
gpt-5.2-pro gpt-5.2-pro18.90 USD151.20 USD400,000
grok-4-0709 grok-4-07092.70 USD13.50 USD256,000
grok-4-1-fast-non-reasoning grok-4-1-fast-non-reasoning0.180 USD0.450 USD2,000,000
grok-4-1-fast-reasoning grok-4-1-fast-reasoning0.180 USD0.450 USD2,000,000
grok-4-fast-non-reasoning grok-4-fast-non-reasoning0.180 USD0.450 USD2,000,000
grok-4-fast-reasoning grok-4-fast-reasoning0.180 USD0.450 USD2,000,000
grok-code-fast-1 grok-code-fast-10.180 USD1.35 USD256,000
Minimax M2.1 minimax/minimax-m2.10.300 USD1.20 USD204,800
MiniMax M1 minimaxai/minimax-m1-80k0.550 USD2.20 USD1,000,000
Kimi K2 0905 moonshotai/kimi-k2-09050.600 USD2.50 USD262,144
Kimi K2 Instruct moonshotai/kimi-k2-instruct0.570 USD2.30 USD131,072
Kimi K2.5 moonshotai/kimi-k2.50.600 USD3.00 USD262,144
o3 o310.00 USD40.00 USD131,072
o3-mini o3-mini1.10 USD4.40 USD131,072
o4-mini o4-mini1.10 USD4.40 USD200,000
Qwen3 235B A22B qwen/qwen3-235b-a22b-fp80.200 USD0.800 USD40,960
Qwen3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-instruct-25070.150 USD0.800 USD131,072
Qwen3 235B A22b Thinking 2507 qwen/qwen3-235b-a22b-thinking-25070.300 USD3.00 USD131,072
Qwen3 30B A3B qwen/qwen3-30b-a3b-fp80.090 USD0.450 USD40,960
Qwen3 32B qwen/qwen3-32b-fp80.100 USD0.450 USD40,960
Qwen3 Coder 480B A35B Instruct qwen/qwen3-coder-480b-a35b-instruct0.290 USD1.20 USD262,144
qwen/qwen3-coder-next qwen/qwen3-coder-next0.200 USD1.50 USD262,144
Qwen3 Next 80B A3B Instruct qwen/qwen3-next-80b-a3b-instruct0.150 USD1.50 USD65,536
Qwen3 Next 80B A3B Thinking qwen/qwen3-next-80b-a3b-thinking0.150 USD1.50 USD65,536
XiaomiMiMo/MiMo-V2-Flash xiaomimimo/mimo-v2-flash0 USD0 USD262,144
GLM-4.5 zai-org/glm-4.50.600 USD2.20 USD131,072
GLM 4.5V zai-org/glm-4.5v0.600 USD1.80 USD65,536
GLM-4.7 zai-org/glm-4.70.600 USD2.20 USD204,800
GLM-4.7-Flash zai-org/glm-4.7-flash0.070 USD0.400 USD200,000

Sources of this page