Skip to main content

​
Synthetic

Synthetic exposes Anthropic-compatible endpoints. Fased registers it as the synthetic provider and uses the Anthropic Messages API. Synthetic also offers OpenAI-compatible endpoints, but this Fased provider route intentionally uses the Anthropic-compatible endpoint.

​
Quick setup

  1. Set SYNTHETIC_API_KEY (or run the wizard below).
  2. Run onboarding:
fased onboard --auth-choice synthetic-api-key
The default model is set to: 
synthetic/hf:MiniMaxAI/MiniMax-M2.5

​
Config example

{
  env: { SYNTHETIC_API_KEY: "sk-..." },
  agents: {
    defaults: {
      model: { primary: "synthetic/hf:MiniMaxAI/MiniMax-M2.5" },
      models: { "synthetic/hf:MiniMaxAI/MiniMax-M2.5": { alias: "MiniMax M2.5" } },
    },
  },
  models: {
    mode: "merge",
    providers: {
      synthetic: {
        baseUrl: "https://api.synthetic.new/anthropic",
        apiKey: "${SYNTHETIC_API_KEY}",
        api: "anthropic-messages",
        models: [
          {
            id: "hf:MiniMaxAI/MiniMax-M2.5",
            name: "MiniMax M2.5",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 191488,
            maxTokens: 65536,
          },
        ],
      },
    },
  },
}
Note: Fased’s Anthropic client appends /v1 to the base URL, so use https://api.synthetic.new/anthropic (not /anthropic/v1). If Synthetic changes its base URL, override models.providers.synthetic.baseUrl.

​
Model catalog

All models below use cost 0 (input/output/cache).
Model IDContext windowMax tokensReasoningInput
hf:zai-org/GLM-5.119660865536truetext
hf:moonshotai/Kimi-K2.626214465536truetext + image
hf:MiniMaxAI/MiniMax-M2.519148865536falsetext
hf:zai-org/GLM-4.7-Flash19660865536falsetext
hf:zai-org/GLM-519660865536truetext
hf:zai-org/GLM-4.720275265536falsetext
hf:deepseek-ai/DeepSeek-V3.21590008192falsetext
hf:Qwen/Qwen3-Coder-480B-A35B-Instruct2560008192falsetext
hf:Qwen/Qwen3-235B-A22B-Thinking-25072560008192truetext
hf:Qwen/Qwen3.5-397B-A17B2560008192falsetext
hf:nvidia/Kimi-K2.5-NVFP42560008192falsetext
hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP42560008192falsetext
hf:openai/gpt-oss-120b1280008192falsetext
hf:meta-llama/Llama-3.3-70B-Instruct1280008192falsetext
hf:deepseek-ai/DeepSeek-R1-05281280008192truetext
hf:moonshotai/Kimi-K2.52621448192truetext + image
hf:deepseek-ai/DeepSeek-V31280008192falsetext

​
Notes

  • Model refs use synthetic/<modelId>.
  • If you enable a model allowlist (agents.defaults.models), add every model you plan to use.
  • See Model providers for provider rules.