Baltor Get started

Endpoints

SiliconFlow

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.siliconflow.com/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in SILICONFLOW_API_KEY models.dev, read
Structured output
Unknown
Tool calling
57 of 57 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 ByteDance-Seed/Seed-OSS-36B-Instruct with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "siliconflow": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "SiliconFlow",
      "options": {
        "baseURL": "https://api.siliconflow.com/v1",
        "apiKey": "{env:SILICONFLOW_API_KEY}"
      },
      "models": {
        "ByteDance-Seed/Seed-OSS-36B-Instruct": {
          "name": "ByteDance-Seed/Seed-OSS-36B-Instruct"
        }
      }
    }
  }
}
  • 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": {
    "siliconflow": {
      "baseUrl": "https://api.siliconflow.com/v1",
      "api": "openai-completions",
      "apiKey": "$SILICONFLOW_API_KEY",
      "models": [
        {
          "id": "ByteDance-Seed/Seed-OSS-36B-Instruct"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and SiliconFlow 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 SiliconFlow 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
ByteDance-Seed/Seed-OSS-36B-Instruct ByteDance-Seed/Seed-OSS-36B-Instruct0.210 USD0.570 USD262,000 older than 30 days
MiniMaxAI/MiniMax-M2.5 MiniMaxAI/MiniMax-M2.50.300 USD1.20 USD197,000 older than 30 days
MiniMax-M3 MiniMaxAI/MiniMax-M30.300 USD1.20 USD1,048,576 older than 30 days
Qwen/Qwen2.5-72B-Instruct Qwen/Qwen2.5-72B-Instruct0.590 USD0.590 USD33,000 older than 30 days
Qwen/Qwen2.5-7B-Instruct Qwen/Qwen2.5-7B-Instruct0.050 USD0.050 USD33,000 older than 30 days
Qwen/Qwen3-14B Qwen/Qwen3-14B0.070 USD0.280 USD131,000 older than 30 days
Qwen/Qwen3-30B-A3B-Instruct-2507 Qwen/Qwen3-30B-A3B-Instruct-25070.090 USD0.300 USD262,000 older than 30 days
Qwen/Qwen3-32B Qwen/Qwen3-32B0.140 USD0.570 USD131,000 older than 30 days
Qwen/Qwen3-8B Qwen/Qwen3-8B0.060 USD0.060 USD131,000 older than 30 days
Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen/Qwen3-Coder-30B-A3B-Instruct0.070 USD0.280 USD262,000 older than 30 days
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen/Qwen3-Coder-480B-A35B-Instruct0.250 USD1.00 USD262,000 older than 30 days
Qwen/Qwen3-VL-30B-A3B-Instruct Qwen/Qwen3-VL-30B-A3B-Instruct0.290 USD1.00 USD262,000 older than 30 days
Qwen/Qwen3-VL-30B-A3B-Thinking Qwen/Qwen3-VL-30B-A3B-Thinking0.290 USD1.00 USD262,000 older than 30 days
Qwen/Qwen3-VL-32B-Instruct Qwen/Qwen3-VL-32B-Instruct0.200 USD0.600 USD262,000 older than 30 days
Qwen/Qwen3-VL-32B-Thinking Qwen/Qwen3-VL-32B-Thinking0.200 USD1.50 USD262,000 older than 30 days
Qwen/Qwen3-VL-8B-Instruct Qwen/Qwen3-VL-8B-Instruct0.180 USD0.680 USD262,000 older than 30 days
Qwen3.5 122B-A10B Qwen/Qwen3.5-122B-A10B0.260 USD2.08 USD262,144 older than 30 days
Qwen3.5 27B Qwen/Qwen3.5-27B0.250 USD2.00 USD262,144 older than 30 days
Qwen3.5 35B-A3B Qwen/Qwen3.5-35B-A3B0.240 USD1.80 USD262,144 older than 30 days
Qwen3.5 397B-A17B Qwen/Qwen3.5-397B-A17B0.390 USD2.34 USD262,144 older than 30 days
Qwen/Qwen3.5-9B Qwen/Qwen3.5-9B0.100 USD0.150 USD262,144 older than 30 days
Qwen3.6 27B Qwen/Qwen3.6-27B0.300 USD3.20 USD262,144 older than 30 days
Qwen3.6 35B-A3B Qwen/Qwen3.6-35B-A3B0.200 USD1.60 USD262,144 older than 30 days
Qwen3.8 2.4T A95B Qwen/Qwen3.8-2.4T-A95B2.00 USD6.00 USD1,049,000 older than 30 days
deepseek-ai/DeepSeek-R1 deepseek-ai/DeepSeek-R10.500 USD2.18 USD164,000 older than 30 days
deepseek-ai/DeepSeek-V3 deepseek-ai/DeepSeek-V30.250 USD1.00 USD164,000 older than 30 days
deepseek-ai/DeepSeek-V3.1 deepseek-ai/DeepSeek-V3.10.270 USD1.00 USD164,000 older than 30 days
deepseek-ai/DeepSeek-V3.1-Terminus deepseek-ai/DeepSeek-V3.1-Terminus0.270 USD1.00 USD164,000 older than 30 days
deepseek-ai/DeepSeek-V3.2 deepseek-ai/DeepSeek-V3.20.270 USD0.420 USD164,000 older than 30 days
deepseek-ai/DeepSeek-V3.2-Exp deepseek-ai/DeepSeek-V3.2-Exp0.270 USD0.410 USD164,000 older than 30 days
DeepSeek V4 Flash deepseek-ai/DeepSeek-V4-Flash0.130 USD0.280 USD1,000,000 older than 30 days
DeepSeek V4 Flash 0731 deepseek-ai/DeepSeek-V4-Flash-07310.220 USD0.660 USD1,000,000 older than 30 days
DeepSeek V4 Flash Vision Exp deepseek-ai/DeepSeek-V4-Flash-Vision-Exp0.440 USD1.32 USD1,000,000
DeepSeek V4 Pro deepseek-ai/DeepSeek-V4-Pro1.50 USD3.13 USD1,000,000 older than 30 days
DeepSeek V4 Pro 0813 deepseek-ai/DeepSeek-V4-Pro-08131.32 USD3.96 USD1,000,000 older than 30 days
Gemma 4 12B IT google/gemma-4-12B-it0.100 USD0.300 USD262,144 older than 30 days
Gemma 4 26B A4B IT google/gemma-4-26B-A4B-it0.120 USD0.400 USD262,144 older than 30 days
Gemma 4 31B IT google/gemma-4-31B-it0.130 USD0.400 USD262,144 older than 30 days
inclusionAI/Ling-flash-2.0 inclusionAI/Ling-flash-2.00.140 USD0.570 USD131,000 older than 30 days
LongCat-2.0 meituan-longcat/LongCat-2.00.750 USD2.95 USD1,049,000 older than 30 days
moonshotai/Kimi-K2.5 moonshotai/Kimi-K2.50.450 USD2.25 USD262,000 older than 30 days
moonshotai/Kimi-K2.6 moonshotai/Kimi-K2.60.770 USD3.40 USD262,000 older than 30 days
Kimi K2.7 Code moonshotai/Kimi-K2.7-Code0.859 USD3.80 USD262,144 older than 30 days
Kimi K3 moonshotai/Kimi-K32.70 USD13.50 USD1,048,576 older than 30 days
Nex-N2-Pro nex-agi/Nex-N2-Pro0.500 USD2.50 USD262,144 older than 30 days
openai/gpt-oss-120b openai/gpt-oss-120b0.050 USD0.450 USD131,000 older than 30 days
openai/gpt-oss-20b openai/gpt-oss-20b0.040 USD0.180 USD131,000 older than 30 days
stepfun-ai/Step-3.5-Flash stepfun-ai/Step-3.5-Flash0.100 USD0.300 USD262,000 older than 30 days
tencent/Hunyuan-A13B-Instruct tencent/Hunyuan-A13B-Instruct0.140 USD0.570 USD131,000 older than 30 days
Hy3 tencent/Hy30.132 USD0.528 USD262,144 older than 30 days
zai-org/GLM-4.5-Air zai-org/GLM-4.5-Air0.140 USD0.860 USD131,000 older than 30 days
zai-org/GLM-5 zai-org/GLM-50.950 USD2.55 USD205,000 older than 30 days
zai-org/GLM-5.1 zai-org/GLM-5.11.19 USD3.74 USD205,000 older than 30 days
GLM-5.2 zai-org/GLM-5.21.30 USD4.09 USD1,049,000 older than 30 days
GLM-5.3 zai-org/GLM-5.31.40 USD4.40 USD1,049,000 older than 30 days
GLM-5.3-Flash zai-org/GLM-5.3-Flash0.150 USD0.500 USD1,049,000
zai-org/GLM-5V-Turbo zai-org/GLM-5V-Turbo1.20 USD4.00 USD200,000 older than 30 days

Sources of this page