src/shared/constants/pricing/inference-hosts.ts

/**
 * Pricing data — inference-hosts family (serverless GPU / OSS-model hosts + aggregator gateways).
 * Pure data; merged by default-pricing.ts via spread (god-file decomposition; semantic split).
 */
export const DEFAULT_PRICING_INFERENCE = {
  agentrouter: {
    auto: { input: 2.0, output: 8.0 },
  },
  openrouter: {
    auto: {
      input: 2.0,
      output: 8.0,
      cached: 1.0,
      reasoning: 12.0,
      cache_creation: 2.0,
    },
  },
  groq: {
    "openai/gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "llama-3.3-70b-versatile": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "meta-llama/llama-4-maverick-17b-128e-instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "qwen/qwen3-32b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
  },
  fireworks: {
    "accounts/fireworks/models/gpt-oss-120b": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "accounts/fireworks/models/deepseek-v3p1": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "accounts/fireworks/models/llama-v3p3-70b-instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "accounts/fireworks/models/qwen3-235b-a22b": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
  },
  cerebras: {
    "gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "zai-glm-4.7": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "llama-3.3-70b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "llama-4-scout-17b-16e-instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "qwen-3-235b-a22b-instruct-2507": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "qwen-3-32b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
  },
  nvidia: {
    "nvidia/gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "openai/gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "moonshotai/kimi-k2.5": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "z-ai/glm4.7": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "deepseek-ai/deepseek-v3.2": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "nvidia/llama-3.3-70b-instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "meta/llama-4-maverick-17b-128e-instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "deepseek/deepseek-r1": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
  },
  nebius: {
    "openai/gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "meta-llama/Llama-3.3-70B-Instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
  },
  siliconflow: {
    "openai/gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "deepseek-ai/DeepSeek-V3.2": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "deepseek-ai/DeepSeek-V3.1": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "deepseek-ai/DeepSeek-R1": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "Qwen/Qwen3-235B-A22B-Instruct-2507": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "Qwen/Qwen3-Coder-480B-A35B-Instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "Qwen/Qwen3-32B": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "moonshotai/Kimi-K2.5": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "zai-org/GLM-4.7": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "baidu/ERNIE-4.5-300B-A47B": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
  },
  hyperbolic: {
    "openai/gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "gpt-oss-120b": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "Qwen/QwQ-32B": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "deepseek-ai/DeepSeek-R1": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "deepseek-ai/DeepSeek-V3": { input: 0, output: 0, cached: 0, reasoning: 0, cache_creation: 0 },
    "meta-llama/Llama-3.3-70B-Instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "meta-llama/Llama-3.2-3B-Instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "Qwen/Qwen2.5-72B-Instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "Qwen/Qwen2.5-Coder-32B-Instruct": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
    "NousResearch/Hermes-3-Llama-3.1-70B": {
      input: 0,
      output: 0,
      cached: 0,
      reasoning: 0,
      cache_creation: 0,
    },
  },
};