Site descriptions, notices, and reviews are shown in the language in which they were submitted.
稳定接入 SOTA 模型。 更优的模型价格。 Modelflare 为 AI 工具、应用和 Agent 提供稳定的模型请求服务，聚合多类前沿 SOTA 模型，并提供清晰的价格、用量与请求状态。
Price listing
GPT 5.6 Sol
3 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.5
3 public records are listed; open the full page to review details as needed.
Price listing
Opus 5
3 public records are listed; open the full page to review details as needed.
Price listing
Claude Fable 5
2 public records are listed; open the full page to review details as needed.
Price listing
Claude Opus 4.8
3 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.6 Terra
3 public records are listed; open the full page to review details as needed.
Price listing
DeepSeek V4 Flash
2 public records are listed; open the full page to review details as needed.
Price listing
Kimi K3
1 public records are listed; open the full page to review details as needed.
Price listing
Grok 4.5
2 public records are listed; open the full page to review details as needed.
Price listing
Claude Sonnet 5
3 public records are listed; open the full page to review details as needed.
Price listing
DeepSeek V4 Pro
1 public records are listed; open the full page to review details as needed.
Price listing
Gemini 3.1 Pro
1 public records are listed; open the full page to review details as needed.
Price listing
Gemini 3.5 Flash
1 public records are listed; open the full page to review details as needed.
Price listing
Gemini 3.6 Flash
1 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.4
3 public records are listed; open the full page to review details as needed.
Price listing
GPT-5.4 Mini
3 public records are listed; open the full page to review details as needed.
Price listing
GPT-5.6 Luna
3 public records are listed; open the full page to review details as needed.
Price listing
Kimi K2.7 Code
1 public records are listed; open the full page to review details as needed.
Current public prices are shown by model and channel. Token prices use CNY per 1M tokens unless another billing unit is shown.
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| openai-first-topup | gpt-5.6-sol | 输入 ¥0.075 / 输出 ¥0.45 / 缓存 ¥0.0075 / 写入 ¥0.0938 | 0% | — | — | — |
| openai-award | gpt-5.6-sol | 输入 ¥0.15 / 输出 ¥0.9 / 缓存 ¥0.015 / 写入 ¥0.1875 | 0% | — | — | — |
| openai-stable | gpt-5.6-sol | 输入 ¥0.3 / 输出 ¥1.8 / 缓存 ¥0.03 / 写入 ¥0.375 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| openai-first-topup | gpt-5.5 | 输入 ¥0.075 / 输出 ¥0.45 / 缓存 ¥0.0075 / 写入 ¥0 | 0% | — | — | — |
| openai-award | gpt-5.5 | 输入 ¥0.15 / 输出 ¥0.9 / 缓存 ¥0.015 / 写入 ¥0 | 0% | — | — | — |
| openai-stable | gpt-5.5 | 输入 ¥0.3 / 输出 ¥1.8 / 缓存 ¥0.03 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-tmp | claude-opus-5 | 输入 ¥0.3 / 输出 ¥1.5 / 缓存 ¥0.03 / 写入 ¥0.6 | 0% | — | — | — |
| claude-award | claude-opus-5 | 输入 ¥1.07 / 输出 ¥5.38 / 缓存 ¥0.1075 / 写入 ¥2.15 | 0% | — | — | — |
| claude-stable | claude-opus-5 | 输入 ¥1.57 / 输出 ¥7.88 / 缓存 ¥0.1575 / 写入 ¥3.15 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-award | claude-fable-5 | 输入 ¥2.15 / 输出 ¥10.75 / 缓存 ¥0.215 / 写入 ¥4.3 | 0% | — | — | — |
| claude-stable | claude-fable-5 | 输入 ¥3.15 / 输出 ¥15.75 / 缓存 ¥0.315 / 写入 ¥6.3 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-tmp | claude-opus-4-8 | 输入 ¥0.3 / 输出 ¥1.5 / 缓存 ¥0.03 / 写入 ¥0.6 | 0% | — | — | — |
| claude-award | claude-opus-4-8 | 输入 ¥1.07 / 输出 ¥5.38 / 缓存 ¥0.1075 / 写入 ¥2.15 | 0% | — | — | — |
| claude-stable | claude-opus-4-8 | 输入 ¥1.57 / 输出 ¥7.88 / 缓存 ¥0.1575 / 写入 ¥3.15 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| openai-first-topup | gpt-5.6-terra | 输入 ¥0.03 / 输出 ¥0.18 / 缓存 ¥0.003 / 写入 ¥0.0375 | -20% | — | — | — |
| openai-award | gpt-5.6-terra | 输入 ¥0.06 / 输出 ¥0.36 / 缓存 ¥0.006 / 写入 ¥0.075 | -20% | — | — | — |
| openai-stable | gpt-5.6-terra | 输入 ¥0.12 / 输出 ¥0.72 / 缓存 ¥0.012 / 写入 ¥0.15 | -20% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| deepseek-award | deepseek-v4-flash | 输入 ¥0.105 / 输出 ¥0.21 / 缓存 ¥0.0021 / 写入 ¥0 | +50% | — | — | — |
| deepseek-stable | deepseek-v4-flash | 输入 ¥0.15 / 输出 ¥0.3 / 缓存 ¥0.003 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kimi | kimi-k3 | 输入 ¥3 / 输出 ¥15 / 缓存 ¥0.3 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| grok-award | grok-4.5 | 输入 ¥0.06 / 输出 ¥0.18 / 缓存 ¥0.015 / 写入 ¥0 | 0% | — | — | — |
| grok | grok-4.5 | 输入 ¥0.12 / 输出 ¥0.36 / 缓存 ¥0.03 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-tmp | claude-sonnet-5 | 输入 ¥0.12 / 输出 ¥0.6 / 缓存 ¥0.012 / 写入 ¥0.24 | 0% | — | — | — |
| claude-award | claude-sonnet-5 | 输入 ¥0.43 / 输出 ¥2.15 / 缓存 ¥0.043 / 写入 ¥0.86 | 0% | — | — | — |
| claude-stable | claude-sonnet-5 | 输入 ¥0.63 / 输出 ¥3.15 / 缓存 ¥0.063 / 写入 ¥1.26 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| deepseek-stable | deepseek-v4-pro | 输入 ¥0.45 / 输出 ¥0.9 / 缓存 ¥0.0037 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gemini-stable | gemini-3.1-pro-preview | 输入 ¥0.3 / 输出 ¥1.8 / 缓存 ¥0.03 / 写入 ¥0.675 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gemini-stable | gemini-3.5-flash | 输入 ¥0.225 / 输出 ¥1.35 / 缓存 ¥0.0225 / 写入 ¥0.15 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gemini-stable | gemini-3.6-flash | 输入 ¥0.225 / 输出 ¥1.13 / 缓存 ¥0.0225 / 写入 ¥0.15 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| openai-first-topup | gpt-5.4 | 输入 ¥0.0375 / 输出 ¥0.225 / 缓存 ¥0.0037 / 写入 ¥0 | 0% | — | — | — |
| openai-award | gpt-5.4 | 输入 ¥0.075 / 输出 ¥0.45 / 缓存 ¥0.0075 / 写入 ¥0 | 0% | — | — | — |
| openai-stable | gpt-5.4 | 输入 ¥0.15 / 输出 ¥0.9 / 缓存 ¥0.015 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| openai-first-topup | gpt-5.4-mini | 输入 ¥0.0112 / 输出 ¥0.0675 / 缓存 ¥0.0011 / 写入 ¥0 | 0% | — | — | — |
| openai-award | gpt-5.4-mini | 输入 ¥0.0225 / 输出 ¥0.135 / 缓存 ¥0.0022 / 写入 ¥0 | 0% | — | — | — |
| openai-stable | gpt-5.4-mini | 输入 ¥0.045 / 输出 ¥0.27 / 缓存 ¥0.0045 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| openai-first-topup | gpt-5.6-luna | 输入 ¥0.0075 / 输出 ¥0.045 / 缓存 ¥0.0008 / 写入 ¥0.0094 | -50% | — | — | — |
| openai-award | gpt-5.6-luna | 输入 ¥0.015 / 输出 ¥0.09 / 缓存 ¥0.0015 / 写入 ¥0.0187 | -50% | — | — | — |
| openai-stable | gpt-5.6-luna | 输入 ¥0.03 / 输出 ¥0.18 / 缓存 ¥0.003 / 写入 ¥0.0375 | -50% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kimi | kimi-k2.7-code | 输入 ¥6.5 / 输出 ¥27 / 缓存 ¥1.3 / 写入 ¥0 | 0% | — | — | — |
Welcome to Modelflare Modelflare’s first priority is stability. We help more users access global SOTA AI models reliably and at lower cost. Credits are denominated in US dollars: top up US$1 and US$1 is added to your credit balance. New users receive US$0.50 automatically after signup. If you run into request failures, slow responses, unavailable models, top-up issues, or billing questions, please contact us through support tickets, our after-sales QQ group, or Telegram.
🎉 The grok-award group is now available! Demand for Grok has been growing, so we’ve added the new grok-award group. Its multiplier is just 0.03, with pricing as low as 3% of official list prices. The group is now available for selection. Choose grok-award when creating or updating an API Key to get started.
Kimi K3 special-pricing availability update Kimi K3 special pricing is temporarily unavailable because of upstream compute constraints. Availability and stability are not guaranteed and may change without notice. Check the pricing page for the currently available groups before use. Do not use Kimi K3 for production or critical workloads.
ModelFlare API Key Fallback Groups Are Now Available Configure ordered fallback groups under API Keys. Requests try channels in the primary group first, then switch through fallback groups. Billing follows the group that serves the request.
ModelFlare Top-up Special is now available. Any single top-up reaching US$20 unlocks the openai-first-topup group. The current rate is 0.015x. Create or update an API key and select openai-first-topup to use it.
5.0 / 5 from 2 approved reviews
还可以，物美价廉，体验挺好
送了6$ 不错 codex可以使用还不错
Uptime is the share of recent probes where the service was available; a higher value generally indicates better stability.
Model consistency uses model pass results to show whether the endpoint behaves like the target model.
Pricing and latency come from public monitoring data and are intended for side-by-side gateway comparison.
Data is provided for reference. Third-party gateways may experience outages or balance loss, so test first and add only a small balance when needed.