找模型算成本选型卡变动模型

大模型 API 价格与 token 成本计算器

找模型

→ 1043 条报价符合

真实成本

请看下方比较

这是估算，不是账单：只含 token 与请求费用，按报价自身币种计。不含工具、存储、搜索、税费和平台费。不同模型对同一任务的分词数不同。

选型卡 0/3

在结果里点「+ 选型卡」加入，或让我们挑 3 个。

今日

1043 条匹配 · 每百万 token

已追踪模型在各服务商端点的成对输入/输出费率，经 OpenRouter 购买；端点报价超过 24 小时需复核。

  • 1.Mistral: Mistral Nemo

    DekaLLM 经 OpenRouter · dekallm/fp8

    fp8
    输入 / 1M
    US$0.018
    输出 / 1M
    US$0.03
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.24
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DekaLLM through OpenRouter, not a direct-provider contract. Published rates for route dekallm/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    dekallm/fp8 · fp8

    声明支持的参数： frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: mistralai/mistral-nemo
Protocol: openai
Provider routing: DekaLLM
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "mistralai/mistral-nemo",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DekaLLM"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "mistralai/mistral-nemo". Route requests to provider "DekaLLM" by setting the `provider.order` field to ["DekaLLM"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.018 / 1M input tokens, $0.03 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/mistralai/mistral-nemo/endpoints.
    Price facts
    Input: $0.018 / 1M tokens
Output: $0.03 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:28.816Z
Source: https://openrouter.ai/api/v1/models/mistralai/mistral-nemo/endpoints
    价格自 OpenRouter 端点

  • 2.Mistral: Mistral Nemo

    DeepInfra 经 OpenRouter · deepinfra/fp8

    fp8
    输入 / 1M
    US$0.019
    输出 / 1M
    US$0.03
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.25
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    deepinfra/fp8 · fp8

    声明支持的参数： frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: mistralai/mistral-nemo
Protocol: openai
Provider routing: DeepInfra
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "mistralai/mistral-nemo",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DeepInfra"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "mistralai/mistral-nemo". Route requests to provider "DeepInfra" by setting the `provider.order` field to ["DeepInfra"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.019 / 1M input tokens, $0.03 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/mistralai/mistral-nemo/endpoints.
    Price facts
    Input: $0.019 / 1M tokens
Output: $0.03 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:28.816Z
Source: https://openrouter.ai/api/v1/models/mistralai/mistral-nemo/endpoints
    价格自 OpenRouter 端点

  • 3.Meta: Llama 3.1 8B Instruct

    DeepInfra 经 OpenRouter · deepinfra/fp8

    fp8
    输入 / 1M
    US$0.02
    输出 / 1M
    US$0.04
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.28
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    deepinfra/fp8 · fp8

    声明支持的参数： frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: meta-llama/llama-3.1-8b-instruct
Protocol: openai
Provider routing: DeepInfra
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "meta-llama/llama-3.1-8b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DeepInfra"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "meta-llama/llama-3.1-8b-instruct". Route requests to provider "DeepInfra" by setting the `provider.order` field to ["DeepInfra"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.02 / 1M input tokens, $0.04 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints.
    Price facts
    Input: $0.02 / 1M tokens
Output: $0.04 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:26.014Z
Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints
    价格自 OpenRouter 端点

  • 4.Meta: Llama 3.1 8B Instruct

    Novita 经 OpenRouter · novita/fp8

    fp8
    输入 / 1M
    US$0.02
    输出 / 1M
    US$0.05
    缓存读 / 1M
    —
    上下文
    16K
    你的月成本
    US$0.30
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Novita through OpenRouter, not a direct-provider contract. Published rates for route novita/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    novita/fp8 · fp8

    声明支持的参数： frequency_penalty, logprobs, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, temperature, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: meta-llama/llama-3.1-8b-instruct
Protocol: openai
Provider routing: Novita
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "meta-llama/llama-3.1-8b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Novita"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "meta-llama/llama-3.1-8b-instruct". Route requests to provider "Novita" by setting the `provider.order` field to ["Novita"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.02 / 1M input tokens, $0.05 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints.
    Price facts
    Input: $0.02 / 1M tokens
Output: $0.05 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:26.014Z
Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints
    价格自 OpenRouter 端点

  • 5.Mistral: Mistral Nemo

    Parasail 经 OpenRouter · parasail/fp8

    fp8
    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.03
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.36
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Parasail through OpenRouter, not a direct-provider contract. Published rates for route parasail/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    parasail/fp8 · fp8

    声明支持的参数： frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: mistralai/mistral-nemo
Protocol: openai
Provider routing: Parasail
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "mistralai/mistral-nemo",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Parasail"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "mistralai/mistral-nemo". Route requests to provider "Parasail" by setting the `provider.order` field to ["Parasail"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.03 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/mistralai/mistral-nemo/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.03 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:28.816Z
Source: https://openrouter.ai/api/v1/models/mistralai/mistral-nemo/endpoints
    价格自 OpenRouter 端点

  • 6.OpenAI: gpt-oss-20b

    Darkbloom 经 OpenRouter · darkbloom/fp8

    fp8
    输入 / 1M
    US$0.018
    输出 / 1M
    US$0.09
    缓存读 / 1M
    US$0.009
    上下文
    131K
    你的月成本
    US$0.36
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Darkbloom through OpenRouter, not a direct-provider contract. Published rates for route darkbloom/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.009
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    darkbloom/fp8 · fp8

    声明支持的参数： frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-20b
Protocol: openai
Provider routing: Darkbloom
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Darkbloom"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-20b". Route requests to provider "Darkbloom" by setting the `provider.order` field to ["Darkbloom"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.018 / 1M input tokens, $0.09 / 1M output tokens, $0.009 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints.
    Price facts
    Input: $0.018 / 1M tokens
Output: $0.09 / 1M tokens
Cache read: $0.009 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.420Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints
    价格自 OpenRouter 端点

  • 7.IBM: Granite 4.0 Micro

    Cloudflare 经 OpenRouter · cloudflare

    输入 / 1M
    US$0.017
    输出 / 1M
    US$0.112
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.394
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Cloudflare through OpenRouter, not a direct-provider contract. Published rates for route cloudflare; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    cloudflare · unknown

    声明支持的参数： frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, temperature, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: ibm-granite/granite-4.0-h-micro
Protocol: openai
Provider routing: Cloudflare
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "ibm-granite/granite-4.0-h-micro",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Cloudflare"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "ibm-granite/granite-4.0-h-micro". Route requests to provider "Cloudflare" by setting the `provider.order` field to ["Cloudflare"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.017 / 1M input tokens, $0.112 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints.
    Price facts
    Input: $0.017 / 1M tokens
Output: $0.112 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:24.978Z
Source: https://openrouter.ai/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints
    价格自 OpenRouter 端点

  • 8.OpenAI: gpt-oss-20b

    AkashML 经 OpenRouter · akashml/fp4

    fp4
    输入 / 1M
    US$0.02
    输出 / 1M
    US$0.10
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.40
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by AkashML through OpenRouter, not a direct-provider contract. Published rates for route akashml/fp4; fp4 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    akashml/fp4 · fp4

    声明支持的参数： frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-20b
Protocol: openai
Provider routing: AkashML
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "AkashML"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-20b". Route requests to provider "AkashML" by setting the `provider.order` field to ["AkashML"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.02 / 1M input tokens, $0.10 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints.
    Price facts
    Input: $0.02 / 1M tokens
Output: $0.10 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.420Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints
    价格自 OpenRouter 端点

  • 9.Nex AGI: Nex-N2.5-Mini

    Nex AGI 经 OpenRouter · nex-agi/bf16

    bf16
    输入 / 1M
    US$0.025
    输出 / 1M
    US$0.10
    缓存读 / 1M
    US$0.0025
    上下文
    262K
    你的月成本
    US$0.45
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Nex AGI through OpenRouter, not a direct-provider contract. Published rates for route nex-agi/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.0025
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    nex-agi/bf16 · bf16

    声明支持的参数： include_reasoning, logprobs, max_tokens, reasoning, reasoning_effort, structured_outputs, temperature, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: nex-agi/nex-n2.5-mini
Protocol: openai
Provider routing: Nex AGI
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "nex-agi/nex-n2.5-mini",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Nex AGI"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "nex-agi/nex-n2.5-mini". Route requests to provider "Nex AGI" by setting the `provider.order` field to ["Nex AGI"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.025 / 1M input tokens, $0.10 / 1M output tokens, $0.0025 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/nex-agi/nex-n2.5-mini/endpoints.
    Price facts
    Input: $0.025 / 1M tokens
Output: $0.10 / 1M tokens
Cache read: $0.0025 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:30.211Z
Source: https://openrouter.ai/api/v1/models/nex-agi/nex-n2.5-mini/endpoints
    价格自 OpenRouter 端点

  • 10.Sao10K: Llama 3 8B Lunaris

    DeepInfra 经 OpenRouter · deepinfra/turbo

    fp8
    输入 / 1M
    US$0.04
    输出 / 1M
    US$0.05
    缓存读 / 1M
    —
    上下文
    8K
    你的月成本
    US$0.50
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/turbo; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    deepinfra/turbo · fp8

    声明支持的参数： frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, seed, stop, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: sao10k/l3-lunaris-8b
Protocol: openai
Provider routing: DeepInfra
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "sao10k/l3-lunaris-8b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DeepInfra"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "sao10k/l3-lunaris-8b". Route requests to provider "DeepInfra" by setting the `provider.order` field to ["DeepInfra"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.04 / 1M input tokens, $0.05 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/sao10k/l3-lunaris-8b/endpoints.
    Price facts
    Input: $0.04 / 1M tokens
Output: $0.05 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:44.773Z
Source: https://openrouter.ai/api/v1/models/sao10k/l3-lunaris-8b/endpoints
    价格自 OpenRouter 端点

  • 11.Sao10K: Llama 3 8B Lunaris

    Parasail 经 OpenRouter · parasail/bf16

    bf16
    输入 / 1M
    US$0.04
    输出 / 1M
    US$0.05
    缓存读 / 1M
    —
    上下文
    8K
    你的月成本
    US$0.50
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Parasail through OpenRouter, not a direct-provider contract. Published rates for route parasail/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    parasail/bf16 · bf16

    声明支持的参数： frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: sao10k/l3-lunaris-8b
Protocol: openai
Provider routing: Parasail
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "sao10k/l3-lunaris-8b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Parasail"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "sao10k/l3-lunaris-8b". Route requests to provider "Parasail" by setting the `provider.order` field to ["Parasail"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.04 / 1M input tokens, $0.05 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/sao10k/l3-lunaris-8b/endpoints.
    Price facts
    Input: $0.04 / 1M tokens
Output: $0.05 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:44.773Z
Source: https://openrouter.ai/api/v1/models/sao10k/l3-lunaris-8b/endpoints
    价格自 OpenRouter 端点

  • 12.OpenAI: gpt-oss-20b

    CoreWeave 经 OpenRouter · coreweave/fp4

    fp4
    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.13
    缓存读 / 1M
    US$0.03
    上下文
    131K
    你的月成本
    US$0.56
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by CoreWeave through OpenRouter, not a direct-provider contract. Published rates for route coreweave/fp4; fp4 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.03
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    coreweave/fp4 · fp4

    声明支持的参数： frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-20b
Protocol: openai
Provider routing: CoreWeave
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "CoreWeave"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-20b". Route requests to provider "CoreWeave" by setting the `provider.order` field to ["CoreWeave"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.13 / 1M output tokens, $0.03 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.13 / 1M tokens
Cache read: $0.03 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.420Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints
    价格自 OpenRouter 端点

  • 13.Qwen: Qwen3.7 Flash

    Alibaba 经 OpenRouter · alibaba

    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.13
    缓存读 / 1M
    US$0.006
    上下文
    1M
    你的月成本
    US$0.56
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Alibaba through OpenRouter, not a direct-provider contract. Published rates for route alibaba; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.006
    缓存写 / 1M
    US$0.038
    每请求
    未公布
    路由
    alibaba · unknown

    声明支持的参数： include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, temperature, tool_choice, tools, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: qwen/qwen3.7-flash
Protocol: openai
Provider routing: Alibaba
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "qwen/qwen3.7-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Alibaba"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "qwen/qwen3.7-flash". Route requests to provider "Alibaba" by setting the `provider.order` field to ["Alibaba"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.13 / 1M output tokens, $0.006 / 1M cache read tokens, $0.038 / 1M cache write tokens. Source: https://openrouter.ai/api/v1/models/qwen/qwen3.7-flash/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.13 / 1M tokens
Cache read: $0.006 / 1M tokens
Cache write: $0.038 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:43.500Z
Source: https://openrouter.ai/api/v1/models/qwen/qwen3.7-flash/endpoints
    价格自 OpenRouter 端点

  • 14.OpenAI: gpt-oss-20b

    DekaLLM 经 OpenRouter · dekallm/bf16

    bf16
    输入 / 1M
    US$0.029
    输出 / 1M
    US$0.14
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.57
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DekaLLM through OpenRouter, not a direct-provider contract. Published rates for route dekallm/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    dekallm/bf16 · bf16

    声明支持的参数： frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-20b
Protocol: openai
Provider routing: DekaLLM
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DekaLLM"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-20b". Route requests to provider "DekaLLM" by setting the `provider.order` field to ["DekaLLM"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.029 / 1M input tokens, $0.14 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints.
    Price facts
    Input: $0.029 / 1M tokens
Output: $0.14 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.420Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints
    价格自 OpenRouter 端点

  • 15.OpenAI: gpt-oss-20b

    DeepInfra 经 OpenRouter · deepinfra/bf16

    bf16
    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.14
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.58
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    deepinfra/bf16 · bf16

    声明支持的参数： frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-20b
Protocol: openai
Provider routing: DeepInfra
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DeepInfra"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-20b". Route requests to provider "DeepInfra" by setting the `provider.order` field to ["DeepInfra"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.14 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.14 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.420Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints
    价格自 OpenRouter 端点

  • 16.Inference.net: Schematron V2 Turbo

    InferenceNet 经 OpenRouter · inference-net

    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.15
    缓存读 / 1M
    US$0.03
    上下文
    128K
    你的月成本
    US$0.60
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by InferenceNet through OpenRouter, not a direct-provider contract. Published rates for route inference-net; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.03
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    inference-net · unknown

    声明支持的参数： frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: inference-net/schematron-v2-turbo
Protocol: openai
Provider routing: InferenceNet
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "inference-net/schematron-v2-turbo",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "InferenceNet"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "inference-net/schematron-v2-turbo". Route requests to provider "InferenceNet" by setting the `provider.order` field to ["InferenceNet"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.15 / 1M output tokens, $0.03 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/inference-net/schematron-v2-turbo/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.15 / 1M tokens
Cache read: $0.03 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:25.607Z
Source: https://openrouter.ai/api/v1/models/inference-net/schematron-v2-turbo/endpoints
    价格自 OpenRouter 端点

  • 17.OpenAI: gpt-oss-20b

    Parasail 经 OpenRouter · parasail/fp4

    fp4
    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.15
    缓存读 / 1M
    US$0.02
    上下文
    131K
    你的月成本
    US$0.60
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Parasail through OpenRouter, not a direct-provider contract. Published rates for route parasail/fp4; fp4 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.02
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    parasail/fp4 · fp4

    声明支持的参数： frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-20b
Protocol: openai
Provider routing: Parasail
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Parasail"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-20b". Route requests to provider "Parasail" by setting the `provider.order` field to ["Parasail"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.15 / 1M output tokens, $0.02 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.15 / 1M tokens
Cache read: $0.02 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.420Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints
    价格自 OpenRouter 端点

  • 18.Sao10K: Llama 3 8B Lunaris

    Novita 经 OpenRouter · novita/bf16

    bf16
    输入 / 1M
    US$0.05
    输出 / 1M
    US$0.05
    缓存读 / 1M
    —
    上下文
    8K
    你的月成本
    US$0.60
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Novita through OpenRouter, not a direct-provider contract. Published rates for route novita/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    novita/bf16 · bf16

    声明支持的参数： frequency_penalty, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: sao10k/l3-lunaris-8b
Protocol: openai
Provider routing: Novita
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "sao10k/l3-lunaris-8b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Novita"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "sao10k/l3-lunaris-8b". Route requests to provider "Novita" by setting the `provider.order` field to ["Novita"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.05 / 1M input tokens, $0.05 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/sao10k/l3-lunaris-8b/endpoints.
    Price facts
    Input: $0.05 / 1M tokens
Output: $0.05 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:44.773Z
Source: https://openrouter.ai/api/v1/models/sao10k/l3-lunaris-8b/endpoints
    价格自 OpenRouter 端点

  • 19.Amazon: Nova Micro 1.0

    Amazon Bedrock 经 OpenRouter · amazon-bedrock

    输入 / 1M
    US$0.035
    输出 / 1M
    US$0.14
    缓存读 / 1M
    —
    上下文
    128K
    你的月成本
    US$0.63
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Amazon Bedrock through OpenRouter, not a direct-provider contract. Published rates for route amazon-bedrock; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    amazon-bedrock · unknown

    声明支持的参数： max_tokens, stop, temperature, tools, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: amazon/nova-micro-v1
Protocol: openai
Provider routing: Amazon Bedrock
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "amazon/nova-micro-v1",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Amazon Bedrock"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "amazon/nova-micro-v1". Route requests to provider "Amazon Bedrock" by setting the `provider.order` field to ["Amazon Bedrock"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.035 / 1M input tokens, $0.14 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/amazon/nova-micro-v1/endpoints.
    Price facts
    Input: $0.035 / 1M tokens
Output: $0.14 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:17.502Z
Source: https://openrouter.ai/api/v1/models/amazon/nova-micro-v1/endpoints
    价格自 OpenRouter 端点

  • 20.Amazon: Nova Micro 1.0

    Amazon Bedrock 经 OpenRouter · amazon-bedrock/eu-west-1

    输入 / 1M
    US$0.035
    输出 / 1M
    US$0.14
    缓存读 / 1M
    —
    上下文
    128K
    你的月成本
    US$0.63
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Amazon Bedrock through OpenRouter, not a direct-provider contract. Published rates for route amazon-bedrock/eu-west-1; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    amazon-bedrock/eu-west-1 · unknown

    声明支持的参数： max_tokens, stop, temperature, tools, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: amazon/nova-micro-v1
Protocol: openai
Provider routing: Amazon Bedrock
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "amazon/nova-micro-v1",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Amazon Bedrock"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "amazon/nova-micro-v1". Route requests to provider "Amazon Bedrock" by setting the `provider.order` field to ["Amazon Bedrock"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.035 / 1M input tokens, $0.14 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/amazon/nova-micro-v1/endpoints.
    Price facts
    Input: $0.035 / 1M tokens
Output: $0.14 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:17.502Z
Source: https://openrouter.ai/api/v1/models/amazon/nova-micro-v1/endpoints
    价格自 OpenRouter 端点

  • 21.OpenAI: gpt-oss-120b

    CoreWeave 经 OpenRouter · coreweave/fp4

    fp4
    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.17
    缓存读 / 1M
    US$0.03
    上下文
    131K
    你的月成本
    US$0.64
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by CoreWeave through OpenRouter, not a direct-provider contract. Published rates for route coreweave/fp4; fp4 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.03
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    coreweave/fp4 · fp4

    声明支持的参数： frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-120b
Protocol: openai
Provider routing: CoreWeave
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "CoreWeave"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-120b". Route requests to provider "CoreWeave" by setting the `provider.order` field to ["CoreWeave"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.17 / 1M output tokens, $0.03 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.17 / 1M tokens
Cache read: $0.03 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.695Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints
    价格自 OpenRouter 端点

  • 22.OpenAI: GPT-5 Nano

    OpenAI 经 OpenRouter · openai/flex

    输入 / 1M
    US$0.025
    输出 / 1M
    US$0.20
    缓存读 / 1M
    US$0.0025
    上下文
    400K
    你的月成本
    US$0.65
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by OpenAI through OpenRouter, not a direct-provider contract. Published rates for route openai/flex; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.0025
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    openai/flex · unknown

    声明支持的参数： include_reasoning, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-5-nano
Protocol: openai
Provider routing: OpenAI
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-5-nano",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "OpenAI"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-5-nano". Route requests to provider "OpenAI" by setting the `provider.order` field to ["OpenAI"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.025 / 1M input tokens, $0.20 / 1M output tokens, $0.0025 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-5-nano/endpoints.
    Price facts
    Input: $0.025 / 1M tokens
Output: $0.20 / 1M tokens
Cache read: $0.0025 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:33.354Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-5-nano/endpoints
    价格自 OpenRouter 端点

  • 23.Meta: Llama 3.1 8B Instruct

    Groq 经 OpenRouter · groq

    输入 / 1M
    US$0.05
    输出 / 1M
    US$0.08
    缓存读 / 1M
    US$0.025
    上下文
    131K
    你的月成本
    US$0.66
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Groq through OpenRouter, not a direct-provider contract. Published rates for route groq; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.025
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    groq · unknown

    声明支持的参数： max_tokens, response_format, seed, stop, temperature, tool_choice, tools, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: meta-llama/llama-3.1-8b-instruct
Protocol: openai
Provider routing: Groq
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "meta-llama/llama-3.1-8b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Groq"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "meta-llama/llama-3.1-8b-instruct". Route requests to provider "Groq" by setting the `provider.order` field to ["Groq"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.05 / 1M input tokens, $0.08 / 1M output tokens, $0.025 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints.
    Price facts
    Input: $0.05 / 1M tokens
Output: $0.08 / 1M tokens
Cache read: $0.025 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:26.014Z
Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints
    价格自 OpenRouter 端点

  • 24.Mistral: Mistral Small 3

    DeepInfra 经 OpenRouter · deepinfra/fp8

    fp8
    输入 / 1M
    US$0.05
    输出 / 1M
    US$0.08
    缓存读 / 1M
    —
    上下文
    33K
    你的月成本
    US$0.66
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    deepinfra/fp8 · fp8

    声明支持的参数： frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: mistralai/mistral-small-24b-instruct-2501
Protocol: openai
Provider routing: DeepInfra
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "mistralai/mistral-small-24b-instruct-2501",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DeepInfra"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "mistralai/mistral-small-24b-instruct-2501". Route requests to provider "DeepInfra" by setting the `provider.order` field to ["DeepInfra"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.05 / 1M input tokens, $0.08 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints.
    Price facts
    Input: $0.05 / 1M tokens
Output: $0.08 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:28.946Z
Source: https://openrouter.ai/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints
    价格自 OpenRouter 端点

  • 25.OpenAI: gpt-oss-120b

    DekaLLM 经 OpenRouter · dekallm/bf16

    bf16
    输入 / 1M
    US$0.03
    输出 / 1M
    US$0.18
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.66
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DekaLLM through OpenRouter, not a direct-provider contract. Published rates for route dekallm/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    dekallm/bf16 · bf16

    声明支持的参数： frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-120b
Protocol: openai
Provider routing: DekaLLM
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DekaLLM"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-120b". Route requests to provider "DekaLLM" by setting the `provider.order` field to ["DekaLLM"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.03 / 1M input tokens, $0.18 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints.
    Price facts
    Input: $0.03 / 1M tokens
Output: $0.18 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.695Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints
    价格自 OpenRouter 端点

  • 26.Meta: Llama 3.2 1B Instruct

    Cloudflare 经 OpenRouter · cloudflare

    输入 / 1M
    US$0.027
    输出 / 1M
    US$0.201
    缓存读 / 1M
    —
    上下文
    60K
    你的月成本
    US$0.672
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Cloudflare through OpenRouter, not a direct-provider contract. Published rates for route cloudflare; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    cloudflare · unknown

    声明支持的参数： frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, seed, stop, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: meta-llama/llama-3.2-1b-instruct
Protocol: openai
Provider routing: Cloudflare
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "meta-llama/llama-3.2-1b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Cloudflare"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "meta-llama/llama-3.2-1b-instruct". Route requests to provider "Cloudflare" by setting the `provider.order` field to ["Cloudflare"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.027 / 1M input tokens, $0.201 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints.
    Price facts
    Input: $0.027 / 1M tokens
Output: $0.201 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:26.127Z
Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints
    价格自 OpenRouter 端点

  • 27.Cohere: Command R7B (12-2024)

    Cohere 经 OpenRouter · cohere

    输入 / 1M
    US$0.0375
    输出 / 1M
    US$0.15
    缓存读 / 1M
    —
    上下文
    128K
    你的月成本
    US$0.675
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Cohere through OpenRouter, not a direct-provider contract. Published rates for route cohere; unknown quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    cohere · unknown

    声明支持的参数： frequency_penalty, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: cohere/command-r7b-12-2024
Protocol: openai
Provider routing: Cohere
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "cohere/command-r7b-12-2024",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Cohere"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "cohere/command-r7b-12-2024". Route requests to provider "Cohere" by setting the `provider.order` field to ["Cohere"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.0375 / 1M input tokens, $0.15 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/cohere/command-r7b-12-2024/endpoints.
    Price facts
    Input: $0.0375 / 1M tokens
Output: $0.15 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:21.103Z
Source: https://openrouter.ai/api/v1/models/cohere/command-r7b-12-2024/endpoints
    价格自 OpenRouter 端点

  • 28.Google: Gemma 3 4B

    DeepInfra 经 OpenRouter · deepinfra/bf16

    bf16
    输入 / 1M
    US$0.05
    输出 / 1M
    US$0.10
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.70
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    deepinfra/bf16 · bf16

    声明支持的参数： frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: google/gemma-3-4b-it
Protocol: openai
Provider routing: DeepInfra
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "google/gemma-3-4b-it",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "DeepInfra"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "google/gemma-3-4b-it". Route requests to provider "DeepInfra" by setting the `provider.order` field to ["DeepInfra"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.05 / 1M input tokens, $0.10 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/google/gemma-3-4b-it/endpoints.
    Price facts
    Input: $0.05 / 1M tokens
Output: $0.10 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:24.464Z
Source: https://openrouter.ai/api/v1/models/google/gemma-3-4b-it/endpoints
    价格自 OpenRouter 端点

  • 29.OpenAI: gpt-oss-20b

    Novita 经 OpenRouter · novita/fp4

    fp4
    输入 / 1M
    US$0.04
    输出 / 1M
    US$0.15
    缓存读 / 1M
    —
    上下文
    131K
    你的月成本
    US$0.70
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by Novita through OpenRouter, not a direct-provider contract. Published rates for route novita/fp4; fp4 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    未公布
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    novita/fp4 · fp4

    声明支持的参数： frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-20b
Protocol: openai
Provider routing: Novita
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "Novita"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-20b". Route requests to provider "Novita" by setting the `provider.order` field to ["Novita"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.04 / 1M input tokens, $0.15 / 1M output tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints.
    Price facts
    Input: $0.04 / 1M tokens
Output: $0.15 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.420Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-20b/endpoints
    价格自 OpenRouter 端点

  • 30.OpenAI: gpt-oss-120b

    AkashML 经 OpenRouter · akashml/bf16

    bf16
    输入 / 1M
    US$0.033
    输出 / 1M
    US$0.187
    缓存读 / 1M
    US$0.033
    上下文
    131K
    你的月成本
    US$0.704
    比最低
    —
    1 天可用率
    无
    计费条件

    Served by AkashML through OpenRouter, not a direct-provider contract. Published rates for route akashml/bf16; bf16 quantization. Other fees, tier conditions and regional access must be checked before use.

    缓存读 / 1M
    US$0.033
    缓存写 / 1M
    未公布
    每请求
    未公布
    路由
    akashml/bf16 · bf16

    声明支持的参数： frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

    Use this endpoint
    Endpoint
    Base URL: https://openrouter.ai/api/v1
Model: openai/gpt-oss-120b
Protocol: openai
Provider routing: AkashML
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
    curl
    curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "provider": {
    "order": [
      "AkashML"
    ],
    "allow_fallbacks": false
  }
}'
    Prompt for your coding agent
    Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "openai/gpt-oss-120b". Route requests to provider "AkashML" by setting the `provider.order` field to ["AkashML"] with `allow_fallbacks: false`. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-09-29: $0.033 / 1M input tokens, $0.187 / 1M output tokens, $0.033 / 1M cache read tokens. Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints.
    Price facts
    Input: $0.033 / 1M tokens
Output: $0.187 / 1M tokens
Cache read: $0.033 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-09-29T18:01:16.695Z
Source: https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints
    价格自 OpenRouter 端点

区间 = 假设的低端与高端；重试按 1 天可用率计算。

价格截至 2026-09-29 · 自 2026-09-29 起追踪 · 共 8 次检查。 4 个模型检查失败；此前价格保留原时间。 历史与数据源状态

追踪模型
521
准确模型 ID，逐服务商比较
推理服务商
83
+ 159 条人工核验的直连报价
有效端点报价
1348
54 条不可用报价保留供参考
最近价格变化
2026-09-29
4 个模型检查失败

我们怎么比

这里的「最便宜」指什么

在当前列出的、同一币种的报价中，按你设定的用量和计费档位估算出的最低值。标准、批处理、谷时、免费和促销价格从不混排，币种之间也不做换算。模型质量、限速和地区可用性是另外的问题。

每个价格都带来源和币种

服务商端点保留成对的输入/输出费率、路由标签和量化精度。直连报价保留服务商实际计费的币种和地区。快照记录的是我们观察到变化的时间，不是服务商的生效时间。

尚未覆盖

大多数官方直连价格页、区域和上下文阶梯定价、embedding、语音、图像和视频计费、免费额度和实测延迟。未知值显示为未知，绝不按零计算。

按服务商看模型服务商覆盖价格历史与数据源状态快照 JSON