Provides API access to AI models including Claude, GPT, and Gemini, with support for chat, image generation, and coding tools.
https://newapi.aiopus.org/Supports longer wait times, suitable for non-streaming Gemini
https://newapi.aisonnet.org/Supports longer wait times, suitable for non-streaming Gemini
https://cfnewapi.aisonnet.org/Optimized for domestic access
https://newapi.aisonnet.orghttps://newapi.aiopus.orghttps://cfnewapi.aisonnet.orgCompare 54 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
| Model | Input ($/M) | Output ($/M) | Audit | Speed | Latency | Tests |
|---|---|---|---|---|---|---|
gpt-5.5 | — | — | — | 44.5 t/s | 3.89 s | 5 |
gemini-3.1-pro-preview-thinking-high-count | — | — | — | 109.9 t/s | 17.03 s | 5 |
minimax-m2.1default | $0.010 | $0.010 | — | 27.5 t/s | 9.56 s | 5 |
deepseek-v3.2default | $0.010 | $0.010 | — | 53.1 t/s | 3.36 s | 5 |
| — | — | — | 203.8 t/s | 7.20 s | 5 | |
| — | — | — | 345.4 t/s | 2.47 s | 5 | |
claude-fable-5default | $10.00 | $10.00 | — | — | — | — |
claude-opus-4-5-20251101default | $5.00 | $25.00 | — | — | — | — |
claude-opus-4-6default | $5.00 | $25.00 | — | — | — | — |
claude-opus-4-6-thinkingdefault | $5.00 | $25.00 | — | — | — | — |
claude-opus-4-7default | $5.00 | $25.00 | — | — | — | — |
claude-opus-4-8default | $5.00 | $25.00 | — | — | — | — |
claude-sonnet-4-6default | $3.00 | $15.00 | — | — | — | — |
deepseek-v3.2-expdefault | $0.010 | $0.010 | — | — | — | — |
deepseek-v4-flashdefault | $1.00 | $2.00 | — | — | — | — |
deepseek-v4-prodefault | $3.00 | $6.00 | — | — | — | — |
gemini-3-flash-previewdefault | $0.500 | $3.50 | — | — | — | — |
gemini-3-pro-image-previewdefault | $0.400 | $0.400 | — | — | — | — |
| $0.600 | $0.600 | — | — | — | — | |
| $0.800 | $0.800 | — | — | — | — | |
| $0.160 | $0.160 | — | — | — | — | |
| $0.180 | $0.180 | — | — | — | — | |
| $0.200 | $0.200 | — | — | — | — | |
gemini-3.1-flash-litedefault | $0.010 | $0.010 | — | — | — | — |
| $0.250 | $1.75 | — | — | — | — | |
gemini-3.1-pro-previewdefault | $2.00 | $12.00 | — | — | — | — |
gemini-3.5-flashdefault | $1.50 | $9.00 | — | — | — | — |
glm-4.6vdefault | $0.010 | $0.010 | — | — | — | — |
glm-4.7default | $0.010 | $0.010 | — | — | — | — |
glm-4.7-flashdefault | $0.010 | $0.010 | — | — | — | — |
glm-5default | $0.010 | $0.010 | — | — | — | — |
glm-5.2default | $2.00 | $8.00 | — | — | — | — |
gpt-5.1default | $0.050 | $0.050 | — | — | — | — |
gpt-5.1-chat-2025-11-13default | $0.050 | $0.050 | — | — | — | — |
gpt-5.1-codexdefault | $0.050 | $0.050 | — | — | — | — |
gpt-5.1-codex-minidefault | $0.050 | $0.050 | — | — | — | — |
| $0.025 | $0.025 | — | — | — | — | |
gpt-5.1-highdefault | $0.050 | $0.050 | — | — | — | — |
gpt-5.2default | $0.050 | $0.050 | — | — | — | — |
gpt-5.2-chat-latestdefault | $75.00 | $600.00 | — | — | — | — |
gpt-5.2-codexdefault | $0.050 | $0.050 | — | — | — | — |
gpt-5.2-highdefault | $0.050 | $0.050 | — | — | — | — |
gpt-5.3-codexdefault | $0.050 | $0.050 | — | — | — | — |
gpt-5.4default | $0.050 | $0.050 | — | — | — | — |
gpt-5.4-highdefault | $0.050 | $0.050 | — | — | — | — |
kimi-k2-thinkingdefault | $0.010 | $0.010 | — | — | — | — |
kimi-k2.5default | $0.010 | $0.010 | — | — | — | — |
MiMo-V2-Flashdefault | $0.010 | $0.010 | — | — | — | — |
minimax-m2default | $0.010 | $0.010 | — | — | — | — |
minimax-m2.5default | $0.010 | $0.010 | — | — | — | — |
minimax-m2.7default | $0.030 | $0.030 | — | — | — | — |
mistral-large-latestdefault | $3.00 | $9.00 | — | — | — | — |
qwen3-coder-nextdefault | $0.010 | $0.010 | — | — | — | — |
Qwen3.5-397Bdefault | $0.010 | $0.010 | — | — | — | — |
Showing 54 of 54 model rows
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jun 8, 11:59 AM | gpt-5.5 | 44.46 tok/s | 3.89s |
| Jun 8, 03:39 AM | gemini-3.1-pro-preview-thinking-high-count | 109.87 tok/s | 17.03s |
| Mar 10, 06:33 AM | minimax-m2.1 | 27.49 tok/s | 9.56s |
| Mar 10, 06:29 AM | deepseek-v3.2 | 53.05 tok/s | 3.36s |
| Mar 10, 06:25 AM | gemini-2.5-flash-lite-preview-09-2025-thinking | 203.81 tok/s | 7.20s |
| Mar 10, 06:22 AM | gemini-2.5-flash-lite-preview-09-2025 | 345.45 tok/s | 2.47s |
Now supports glm-5.1, 0.01 per call.
gpt-5.5 is now supported, with official original input/output.
gpt-image-2, a new image generation model, supports 2K and 4K.
Due to upstream supplier changes, prices for gpt-5.4 and 5.3 series have been adjusted.
Token billing for Claude now supports 1 million context.
New models added: gpt-5.4, gpt-5.4-high.
Due to the Middle East war, currently opus is only stable in the claudecode group.
Due to Google's risk control today, the price of small banana has been temporarily adjusted to 0.07.
Compare 紫脑喵 alternatives against 6 nearby API providers using 592 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| 紫脑喵 newapi-aisonnet-org Provides API access to AI models including Claude, GPT, and Gemini, with support for chat, image generation, and coding tools. | Current provider baseline | 125 | 0 | $6.90/M | 131 tok/s | 99.9% |
| MapleLeaf API ai-071129-xyz MapleLeaf API runs a New API-powered gateway on ai.071129.xyz for aggregated access to multiple AI models. |
| 260 | 21 | $55.27/M | 38 tok/s | 100% |
api-futureppo-top Future Hub is a large-scale OpenAI-compatible API gateway at api.futureppo.top with extensive model coverage and pricing data. |
| 94 | 1 | $5.50/M | 67 tok/s | 100% |
catclaw-moetu-vip CatClaw API is an OpenAI-compatible LLM gateway at catclaw.moetu.vip, offering multi-model API access with transparent pricing. |
| 21 | 2 | $0.571/M | 69 tok/s | 100% |
api-kr777-top CaMeL AI provides an OpenAI-compatible API gateway with extensive model coverage and pricing options. |
| 172 | 4 | $24.16/M | 119 tok/s | 98.8% |
naapi-cc Na API (naapi.cc) is an OpenAI-compatible LLM API gateway with competitive pricing and stable access to 100+ models from OpenAI, Anthropic, Google, and more. |
| 65 | 0 | $545.00/M | 649 tok/s | 100% |
cpatp7eu3nc8-tokenclub-top An OpenAI-compatible API relay service on TokenClub, providing access to multiple AI models. |
| 14 | 0 | $11.59/M | 186 tok/s | 100% |
