跳过主要内容
聚合网关

Vercel AI Gateway

Vercel AI Gateway 是一个聚合网关提供商,收录 138 个模型和 138 个接入项。

接入

SDK
@ai-sdk/gateway
环境变量
AI_GATEWAY_API_KEY

模型

列表视图 / 表格视图

显示 138 / 138 个模型版本

模型家族提供商模型 ID协议流式输出组织上下文最大输出输入输出推理工具调用结构化输出温度参数权重价格发布日期更新时间
DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
DEDeepSeekDeepSeek
deepseek/deepseek-v4-flash-0731
Openai chat
1M66K
开放
输入 $0.13/M · 输出 $0.26/M
缓存读取 $0.028/M
2026-07-312026-08-06
Inkling Small
thinkingmachines/inkling-small
TMThinking MachinesLing
thinkingmachines/inkling-small
Openai chat
1M1M
-开放
输入 $0.5/M · 输出 $1.2/M
缓存读取 $0.1/M
2026-07-302026-08-06
Claude Opus 5
anthropic/claude-opus-5
ANAnthropicClaude
anthropic/claude-opus-5
Openai chat
1M128K
--闭源
输入 $5/M · 输出 $25/M
缓存读取 $0.5/M · 缓存写入 $6.25/M
2026-07-242026-07-24
Claude Opus 5 (Fast)
anthropic/claude-opus-5-fast
ANAnthropicClaude
anthropic/claude-opus-5-fast
Openai chat
1M128K
-闭源
输入 $10/M · 输出 $50/M
缓存读取 $1/M · 缓存写入 $12.5/M
2026-07-242026-07-24
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-lite
GOGoogleGemini
google/gemini-3.5-flash-lite
Openai chat
1M66K
闭源
输入 $0.3/M · 输出 $2.5/M
缓存读取 $0.03/M
2026-07-212026-07-21
Gemini 3.6 Flash
google/gemini-3.6-flash
GOGoogleGemini
google/gemini-3.6-flash
Openai chat
1M66K
闭源
输入 $1.5/M · 输出 $7.5/M
缓存读取 $0.15/M
2026-07-212026-07-21
Laguna S 2.1
poolside/laguna-s-2.1
POPoolsideLaguna
poolside/laguna-s-2.1
Openai chat
1M33K
-开放
输入 $0.1/M · 输出 $0.2/M
缓存读取 $0.01/M
2026-07-212026-08-06
Kimi K3
moonshotai/kimi-k3
MAMoonshot AIKimi
moonshotai/kimi-k3
Openai chat
1M131K
-开放
输入 $3/M · 输出 $15/M
缓存读取 $0.3/M
2026-07-162026-07-30
Inkling
thinkingmachines/inkling
TMThinking MachinesLing
thinkingmachines/inkling
Openai chat
1M1M
-开放
输入 $1/M · 输出 $4.05/M
缓存读取 $0.17/M
2026-07-152026-08-06
KAT-Coder-Air V2.5
kwaipilot/kat-coder-air-v2.5
KWKwaipilotKat
kwaipilot/kat-coder-air-v2.5
Openai chat
256K80K
-闭源
输入 $0.15/M · 输出 $0.6/M
缓存读取 $0.03/M
2026-07-102026-07-14
KAT-Coder-Pro V2.5
kwaipilot/kat-coder-pro-v2.5
KWKwaipilotKat
kwaipilot/kat-coder-pro-v2.5
Openai chat
256K80K
-闭源
输入 $0.74/M · 输出 $2.96/M
缓存读取 $0.15/M
2026-07-102026-07-14
GPT-5.6 Luna
openai/gpt-5.6-luna
OPOpenAIGPT
openai/gpt-5.6-luna
Openai chat
1.1M128K
-闭源
输入 $0.2/M · 输出 $1.2/M
缓存读取 $0.02/M · 缓存写入 $0.25/M
2026-07-092026-08-06
GPT-5.6 Sol
openai/gpt-5.6-sol
OPOpenAIGPT
openai/gpt-5.6-sol
Openai chat
1.1M128K
-闭源
输入 $5/M · 输出 $30/M
缓存读取 $0.5/M · 缓存写入 $6.25/M
2026-07-092026-08-06
GPT-5.6 Terra
openai/gpt-5.6-terra
OPOpenAIGPT
openai/gpt-5.6-terra
Openai chat
1.1M128K
-闭源
输入 $2/M · 输出 $12/M
缓存读取 $0.2/M · 缓存写入 $2.5/M
2026-07-092026-08-06
Grok 4.5
xai/grok-4.5
XAxAIGrok
xai/grok-4.5
Openai chat
500K500K
闭源
输入 $2/M · 输出 $6/M
缓存读取 $0.3/M
2026-07-082026-08-06
GPT-Realtime-2.1
openai/gpt-realtime-2.1
OPOpenAIGPT
openai/gpt-realtime-2.1
Openai chat
128K32K
--闭源
输入 $4/M · 输出 $24/M
缓存读取 $0.4/M
2026-07-062026-07-06
Hy3
tencent/hy3
TETencentHy
tencent/hy3
Openai chat
256K64K
-开放
输入 $0.14/M · 输出 $0.58/M
缓存读取 $0.035/M
2026-07-062026-08-06
Claude Sonnet 5
anthropic/claude-sonnet-5
ANAnthropicClaude
anthropic/claude-sonnet-5
Openai chat
1M128K
--闭源
输入 $2/M · 输出 $10/M
缓存读取 $0.2/M · 缓存写入 $2.5/M
2026-06-302026-07-01
Gemini Omni Flash Preview
google/gemini-omni-flash-preview
GOGoogleGemini
google/gemini-omni-flash-preview
Openai chat
1M58K
---闭源
输入 $1.5/M · 输出 $9/M
2026-06-302026-06-30
Nano Banana 2 Lite
google/gemini-3.1-flash-lite-image
GOGoogleGemini
google/gemini-3.1-flash-lite-image
Openai chat
66K4.1K
-闭源
输入 $0.25/M · 输出 $1.5/M
缓存读取 $0.03/M
2026-06-302026-06-30
Fugu Ultra
sakana/fugu-ultra
SASakana AIFugu
sakana/fugu-ultra
Openai chat
1M128K
-闭源
输入 $5/M · 输出 $30/M
缓存读取 $0.5/M
2026-06-152026-06-22
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
MAMoonshot AIKimi
moonshotai/kimi-k2.7-code
Openai chat
262K262K
-开放
输入 $0.95/M · 输出 $4/M
缓存读取 $0.19/M
2026-06-122026-08-06
Kimi K2.7 Code Highspeed
moonshotai/kimi-k2.7-code-highspeed
MAMoonshot AIKimi
moonshotai/kimi-k2.7-code-highspeed
Openai chat
262K262K
-开放
输入 $1.9/M · 输出 $8/M
缓存读取 $0.38/M
2026-06-122026-06-12
Claude Fable 5
anthropic/claude-fable-5
ANAnthropicClaude
anthropic/claude-fable-5
Openai chat
1M128K
--闭源
输入 $10/M · 输出 $50/M
缓存读取 $1/M · 缓存写入 $12.5/M
2026-06-092026-06-11
Nemotron 3 Ultra 550B A55B
nvidia/nemotron-3-ultra-550b-a55b
NVNVIDIANemotron
nvidia/nemotron-3-ultra-550b-a55b
Openai chat
1M128K
-开放
输入 $0.6/M · 输出 $2.4/M
缓存读取 $0.12/M
2026-06-042026-06-04
Qwen3.7 Plus
alibaba/qwen3.7-plus
ALAlibabaQwen
alibaba/qwen3.7-plus
Openai chat
1M64K
闭源
输入 $0.4/M · 输出 $1.6/M
缓存读取 $0.08/M · 缓存写入 $0.5/M
2026-06-022026-07-22
MiniMax-M3
minimax/minimax-m3
MIMiniMaxMinimax
minimax/minimax-m3
Openai chat
512K128K
-开放
输入 $0.3/M · 输出 $1.2/M
缓存读取 $0.06/M
2026-06-012026-08-06
Grok Imagine Video 1.5
xai/grok-imagine-video-1.5
XAxAIGrok
xai/grok-imagine-video-1.5
Openai chat
1K-
----闭源
输入 $0.01/image · 输出 $0.08/video second
2026-05-302026-05-30
Step 3.7 Flash
stepfun/step-3.7-flash
STStepFunStep
stepfun/step-3.7-flash
Openai chat
256K256K
-开放
输入 $0.2/M · 输出 $1.15/M
缓存读取 $0.04/M
2026-05-292026-08-06
Claude Opus 4.8
anthropic/claude-opus-4-8
ANAnthropicClaude
anthropic/claude-opus-4.8
Openai chat
1M128K
--闭源
输入 $5/M · 输出 $25/M
缓存读取 $0.5/M · 缓存写入 $6.25/M
2026-05-282026-06-11
Nano Banana 2
google/gemini-3.1-flash-image
GOGoogleGemini
google/gemini-3.1-flash-image
Openai chat
131K33K
--闭源
输入 $0.5/M · 输出 $3/M
缓存读取 $0.05/M
2026-05-282026-05-28
Nano Banana Pro
google/gemini-3-pro-image
GOGoogleGemini
google/gemini-3-pro-image
Openai chat
66K33K
--闭源
输入 $2/M · 输出 $12/M
缓存读取 $0.2/M
2026-05-282026-05-28
Claude Opus 4.8 (Fast)
anthropic/claude-opus-4.8-fast
ANAnthropicClaude
anthropic/claude-opus-4.8-fast
Openai chat
1M128K
-闭源
输入 $10/M · 输出 $50/M
缓存读取 $1/M · 缓存写入 $12.5/M
2026-05-272026-05-28
Qwen3.7 Max
alibaba/qwen3.7-max
ALAlibabaQwen
alibaba/qwen3.7-max
Openai chat
1M66K
闭源
输入 $2.5/M · 输出 $7.5/M
缓存读取 $0.5/M · 缓存写入 $3.125/M
2026-05-212026-07-22
Gemini 3.5 Flash
google/gemini-3.5-flash
GOGoogleGemini
google/gemini-3.5-flash
Openai chat
1M66K
闭源
输入 $1.5/M · 输出 $9/M
缓存读取 $0.15/M
2026-05-192026-06-11
Gemini 3.1 Flash Lite
google/gemini-3.1-flash-lite
GOGoogleGemini
google/gemini-3.1-flash-lite
Openai chat
1M66K
闭源
输入 $0.25/M · 输出 $1.5/M
缓存读取 $0.03/M
2026-05-072026-05-07
GPT-Realtime-Whisper
openai/gpt-realtime-whisper
OPOpenAIWhisper
openai/gpt-realtime-whisper
Openai chat
16K2K
---闭源
输入 $0/audio second
2026-05-072026-08-06
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
DEDeepSeekDeepSeek
deepseek/deepseek-v4-flash
Openai chat
1M384K
开放
输入 $0.2/M · 输出 $0.4/M
缓存读取 $0.04/M
2026-04-242026-08-06
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
DEDeepSeekDeepSeek
deepseek/deepseek-v4-pro
Openai chat
1M384K
开放
输入 $0.435/M · 输出 $0.87/M
缓存读取 $0.004/M
2026-04-242026-08-06
GPT-5.5
openai/gpt-5.5
OPOpenAIGPT
openai/gpt-5.5
Openai chat
1.1M128K
-闭源
输入 $5/M · 输出 $30/M
缓存读取 $0.5/M
2026-04-232026-08-06
GPT-5.5 Pro
openai/gpt-5.5-pro
OPOpenAIGPT
openai/gpt-5.5-pro
Openai chat
1.1M128K
-闭源
输入 $30/M · 输出 $180/M
2026-04-232026-08-06
Gemini Embedding 2
google/gemini-embedding-2
GOGoogleGemini
google/gemini-embedding-2
Openai chat
8.2K3.1K
----闭源
输入 $0.2/M
2026-04-222026-04-22
MiMo-V2.5
xiaomi/mimo-v2.5
XIXiaomiMiMo
xiaomi/mimo-v2.5
Openai chat
1M131K
-开放
输入 $0.14/M · 输出 $0.28/M
缓存读取 $0.003/M
2026-04-222026-08-06
MiMo-V2.5-Pro
xiaomi/mimo-v2.5-pro
XIXiaomiMiMo
xiaomi/mimo-v2.5-pro
Openai chat
1M131K
-开放
输入 $0.435/M · 输出 $0.87/M
缓存读取 $0.004/M
2026-04-222026-08-06
Qwen3.6 27B
alibaba/qwen3.6-27b
ALAlibabaQwen
alibaba/qwen3.6-27b
Openai chat
262K66K
开放
输入 $0.6/M · 输出 $3.6/M
2026-04-222026-08-06
GPT Image 2
openai/gpt-image-2
OPOpenAIGPT
openai/gpt-image-2
Openai chat
--
----闭源
输入 $5/M · 输出 $30/M
缓存读取 $1.25/M
2026-04-212026-08-06
Kimi K2.6
moonshotai/kimi-k2.6
MAMoonshot AIKimi
moonshotai/kimi-k2.6
Openai chat
262K262K
开放
输入 $0.95/M · 输出 $4/M
缓存读取 $0.16/M
2026-04-212026-08-06
Grok 4.3
xai/grok-4.3
XAxAIGrok
xai/grok-4.3
Openai chat
1M30K
闭源
输入 $1.25/M · 输出 $2.5/M
缓存读取 $0.2/M
2026-04-172026-06-11
Claude Opus 4.7
anthropic/claude-opus-4-7
ANAnthropicClaude
anthropic/claude-opus-4.7
Openai chat
1M128K
--闭源
输入 $5/M · 输出 $25/M
缓存读取 $0.5/M · 缓存写入 $6.25/M
2026-04-162026-06-11
Grok Build 0.1
xai/grok-build-0.1
XAxAIGrok Build
xai/grok-build-0.1
Openai chat
256K256K
闭源
输入 $1/M · 输出 $2/M
缓存读取 $0.2/M
2026-04-162026-06-11
Muse Spark 1.1
meta/muse-spark-1.1
MEMetaMuse
meta/muse-spark-1.1
Openai chat
1M32K
闭源
输入 $1.25/M · 输出 $4.25/M
缓存读取 $0.15/M
2026-04-082026-07-09
Gemma 4 26B A4B IT
google/gemma-4-26b-a4b-it
GOGoogleGemma
google/gemma-4-26b-a4b-it
Openai chat
262K33K
开放
输入 $0.15/M · 输出 $0.6/M
缓存读取 $0.015/M
2026-04-022026-08-06
Gemma 4 31B IT
google/gemma-4-31b-it
GOGoogleGemma
google/gemma-4-31b-it
Openai chat
262K33K
开放
输入 $0.14/M · 输出 $0.4/M
2026-04-022026-08-06
Qwen3.6 Plus
alibaba/qwen3.6-plus
ALAlibabaQwen
alibaba/qwen3.6-plus
Openai chat
1M66K
闭源
输入 $0.5/M · 输出 $3/M
缓存读取 $0.1/M · 缓存写入 $0.625/M
2026-04-022026-07-22
Trinity Large Thinking
arcee-ai/trinity-large-thinking
AAArcee AiTrinity
arcee-ai/trinity-large-thinking
Openai chat
262K262K
开放
输入 $0.25/M · 输出 $0.9/M
2026-04-012026-08-06
KAT-Coder-Pro V2
kwaipilot/kat-coder-pro-v2
KWKwaipilotKat
kwaipilot/kat-coder-pro-v2
Openai chat
262K80K
-闭源
输入 $0.3/M · 输出 $1.2/M
缓存读取 $0.06/M
2026-03-272026-03-30
MiniMax-M2.7
minimax/minimax-m2.7
MIMiniMaxMinimax
minimax/minimax-m2.7
Openai chat
205K131K
-开放
输入 $0.3/M · 输出 $1.2/M
缓存读取 $0.06/M · 缓存写入 $0.375/M
2026-03-182026-08-06
MiniMax-M2.7-highspeed
minimax/minimax-m2.7-highspeed
MIMiniMaxMinimax
minimax/minimax-m2.7-highspeed
Openai chat
205K131K
-开放
输入 $0.6/M · 输出 $2.4/M
缓存读取 $0.06/M · 缓存写入 $0.375/M
2026-03-182026-05-27
GPT-5.4 mini
openai/gpt-5.4-mini
OPOpenAIGPT
openai/gpt-5.4-mini
Openai chat
400K128K
-闭源
输入 $0.75/M · 输出 $4.5/M
缓存读取 $0.075/M
2026-03-172026-03-20
GPT-5.4 nano
openai/gpt-5.4-nano
OPOpenAIGPT
openai/gpt-5.4-nano
Openai chat
400K128K
-闭源
输入 $0.2/M · 输出 $1.25/M
缓存读取 $0.02/M
2026-03-172026-03-20
Nemotron 3 Super 120B A12B
nvidia/nemotron-3-super-120b-a12b
NVNVIDIANemotron
nvidia/nemotron-3-super-120b-a12b
Openai chat
262K262K
-开放
输入 $0.15/M · 输出 $0.65/M
2026-03-112026-03-12
GPT-5.4
openai/gpt-5.4
OPOpenAIGPT
openai/gpt-5.4
Openai chat
1.1M128K
-闭源
输入 $2.5/M · 输出 $15/M
缓存读取 $0.25/M
2026-03-052026-08-06
GPT-5.4 Pro
openai/gpt-5.4-pro
OPOpenAIGPT
openai/gpt-5.4-pro
Openai chat
1.1M128K
--闭源
输入 $30/M · 输出 $180/M
2026-03-052026-03-20
Mercury 2
inception/mercury-2
INInceptionMercury
inception/mercury-2
Openai chat
128K50K
闭源
输入 $0.25/M · 输出 $0.75/M
缓存读取 $0.025/M
2026-03-042026-03-06
GPT-5.3 Chat
openai/gpt-5.3-chat
OPOpenAIGPT
openai/gpt-5.3-chat
Openai chat
128K16K
-闭源
输入 $1.75/M · 输出 $14/M
缓存读取 $0.175/M
2026-03-032026-03-20
Nano Banana 2
google/gemini-3.1-flash-image-preview
GOGoogleGemini
google/gemini-3.1-flash-image-preview
Openai chat
66K66K
--闭源
输入 $0.5/M · 输出 $3/M
缓存读取 $0.05/M
2026-02-262026-02-27
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview
GOGoogleGemini
google/gemini-3.1-pro-preview
Openai chat
1M66K
闭源
输入 $2/M · 输出 $12/M
缓存读取 $0.2/M
2026-02-192026-06-11
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6
ANAnthropicClaude
anthropic/claude-sonnet-4.6
Openai chat
1M64K
-闭源
输入 $3/M · 输出 $15/M
缓存读取 $0.3/M · 缓存写入 $3.75/M
2026-02-172026-06-11
Qwen3.5 Plus
alibaba/qwen3.5-plus
ALAlibabaQwen
alibaba/qwen3.5-plus
Openai chat
1M66K
-闭源
输入 $0.4/M · 输出 $2.4/M
缓存读取 $0.04/M · 缓存写入 $0.5/M
2026-02-162026-02-16
MiniMax-M2.5-highspeed
minimax/minimax-m2.5-highspeed
MIMiniMaxMinimax
minimax/minimax-m2.5-highspeed
Openai chat
205K131K
-开放
输入 $0.6/M · 输出 $2.4/M
缓存读取 $0.03/M · 缓存写入 $0.375/M
2026-02-132026-02-14
MiniMax-M2.5
minimax/minimax-m2.5
MIMiniMaxMinimax
minimax/minimax-m2.5
Openai chat
205K131K
-开放
输入 $0.3/M · 输出 $1.2/M
缓存读取 $0.03/M · 缓存写入 $0.375/M
2026-02-122026-08-06
Claude Opus 4.6
anthropic/claude-opus-4-6
ANAnthropicClaude
anthropic/claude-opus-4.6
Openai chat
1M128K
-闭源
输入 $5/M · 输出 $25/M
缓存读取 $0.5/M · 缓存写入 $6.25/M
2026-02-052026-07-17
GPT-5.3-Codex
openai/gpt-5.3-codex
OPOpenAIGPT
openai/gpt-5.3-codex
Openai chat
400K128K
-闭源
输入 $1.75/M · 输出 $14/M
缓存读取 $0.175/M
2026-02-052026-08-06
Step 3.5 Flash
stepfun/step-3.5-flash
STStepFunStep
stepfun/step-3.5-flash
Openai chat
256K256K
-开放
输入 $0.09/M · 输出 $0.3/M
缓存读取 $0.02/M
2026-01-292026-08-06
Kimi K2.5
moonshotai/kimi-k2.5
MAMoonshot AIKimi
moonshotai/kimi-k2.5
Openai chat
262K262K
-开放
输入 $0.6/M · 输出 $3/M
缓存读取 $0.1/M
2026-012026-08-06
MiniMax-M2.1
minimax/minimax-m2.1
MIMiniMaxMinimax
minimax/minimax-m2.1
Openai chat
205K131K
-开放
输入 $0.3/M · 输出 $1.2/M
缓存读取 $0.03/M · 缓存写入 $0.375/M
2025-12-232026-08-06
Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b
NVNVIDIANemotron
nvidia/nemotron-3-nano-30b-a3b
Openai chat
262K262K
-开放
输入 $0.05/M · 输出 $0.24/M
2025-12-152025-12-15
GPT-5.2
openai/gpt-5.2
OPOpenAIGPT
openai/gpt-5.2
Openai chat
400K128K
-闭源
输入 $1.75/M · 输出 $14/M
缓存读取 $0.175/M
2025-12-112026-01-01
GPT-5.2 Pro
openai/gpt-5.2-pro
OPOpenAIGPT
openai/gpt-5.2-pro
Openai chat
400K128K
--闭源
输入 $21/M · 输出 $168/M
2025-12-112026-01-01
GPT-5.2-Codex
openai/gpt-5.2-codex
OPOpenAIGPT
openai/gpt-5.2-codex
Openai chat
400K128K
-闭源
输入 $1.75/M · 输出 $14/M
缓存读取 $0.175/M
2025-12-112026-08-06
DeepSeek V3.2
deepseek/deepseek-v3.2
DEDeepSeekDeepSeek
deepseek/deepseek-v3.2
Openai chat
164K66K
开放
输入 $0.28/M · 输出 $0.42/M
缓存读取 $0.028/M
2025-12-012026-08-06
GPT Image 1.5
openai/gpt-image-1.5
OPOpenAIGPT
openai/gpt-image-1.5
Openai chat
--
----闭源
输入 $5/M · 输出 $32/M
缓存读取 $1.25/M
2025-11-252026-08-06
GPT-5.1-Codex
openai/gpt-5.1-codex
OPOpenAIGPT
openai/gpt-5.1-codex
Openai chat
400K128K
-闭源
输入 $1.25/M · 输出 $10/M
缓存读取 $0.13/M
2025-11-132026-08-06
GPT-5.1-Codex mini
openai/gpt-5.1-codex-mini
OPOpenAIGPT
openai/gpt-5.1-codex-mini
Openai chat
400K128K
-闭源
输入 $0.25/M · 输出 $2/M
缓存读取 $0.03/M
2025-11-132026-08-06
GPT-5.1-Codex-Max
openai/gpt-5.1-codex-max
OPOpenAIGPT
openai/gpt-5.1-codex-max
Openai chat
400K128K
-闭源
输入 $1.25/M · 输出 $10/M
缓存读取 $0.125/M
2025-11-132026-08-06
Kimi K2 Thinking
moonshotai/kimi-k2-thinking
MAMoonshot AIKimi
moonshotai/kimi-k2-thinking
Openai chat
262K262K
-开放
输入 $0.47/M · 输出 $2/M
缓存读取 $0.141/M
2025-11-062026-08-06
Claude Opus 4.5
anthropic/claude-opus-4-5-20251101
ANAnthropicClaude
anthropic/claude-opus-4.5
Openai chat
200K64K
-闭源
输入 $5/M · 输出 $25/M
缓存读取 $0.5/M · 缓存写入 $6.25/M
2025-11-012026-06-11
gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b
OPOpenAIGPT
openai/gpt-oss-safeguard-20b
Openai chat
131K66K
开放
输入 $0.075/M · 输出 $0.3/M
缓存读取 $0.037/M
2025-10-292026-08-06
Nemotron Nano 12B v2 VL
nvidia/nemotron-nano-12b-v2-vl
NVNVIDIANemotron
nvidia/nemotron-nano-12b-v2-vl
Openai chat
128K128K
-开放
输入 $0.2/M · 输出 $0.6/M
2025-10-282025-10-28
MiniMax-M2
minimax/minimax-m2
MIMiniMaxMinimax
minimax/minimax-m2
Openai chat
197K128K
-开放
输入 $0.3/M · 输出 $1.2/M
缓存读取 $0.03/M · 缓存写入 $0.375/M
2025-10-272026-08-06
Claude Haiku 4.5
anthropic/claude-haiku-4-5-20251001
ANAnthropicClaude
anthropic/claude-haiku-4.5
Openai chat
200K64K
-闭源
输入 $1/M · 输出 $5/M
缓存读取 $0.1/M · 缓存写入 $1.25/M
2025-10-152026-01-01
GPT-5 Pro
openai/gpt-5-pro
OPOpenAIGPT
openai/gpt-5-pro
Openai chat
400K272K
-闭源
输入 $15/M · 输出 $120/M
2025-10-062026-01-01
Claude Sonnet 4.5
anthropic/claude-sonnet-4-5-20250929
ANAnthropicClaude
anthropic/claude-sonnet-4.5
Openai chat
200K64K
-闭源
输入 $3/M · 输出 $15/M
缓存读取 $0.3/M · 缓存写入 $3.75/M
2025-09-292026-06-11
Qwen3 Max
alibaba/qwen3-max
ALAlibabaQwen
alibaba/qwen3-max
Openai chat
262K66K
-闭源
输入 $1.2/M · 输出 $6/M
缓存读取 $0.24/M
2025-09-232026-01-23
DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminus
DEDeepSeekDeepSeek
deepseek/deepseek-v3.1-terminus
Openai chat
164K33K
开放
输入 $0.27/M · 输出 $1/M
缓存读取 $0.135/M
2025-09-222026-08-06
GPT-5-Codex
openai/gpt-5-codex
OPOpenAIGPT
openai/gpt-5-codex
Openai chat
400K128K
-闭源
输入 $1.25/M · 输出 $10/M
缓存读取 $0.13/M
2025-09-152026-08-06
Qwen3-Next 80B-A3B (Thinking)
alibaba/qwen3-next-80b-a3b-thinking
ALAlibabaQwen
alibaba/qwen3-next-80b-a3b-thinking
Openai chat
131K33K
开放
输入 $0.15/M · 输出 $1.2/M
2025-092026-08-06
Qwen3-Next 80B-A3B Instruct
alibaba/qwen3-next-80b-a3b-instruct
ALAlibabaQwen
alibaba/qwen3-next-80b-a3b-instruct
Openai chat
131K33K
-开放
输入 $0.15/M · 输出 $1.2/M
2025-092026-08-06
Nano Banana
google/gemini-2.5-flash-image
GOGoogleGemini
google/gemini-2.5-flash-image
Openai chat
33K33K
--闭源
输入 $0.3/M · 输出 $2.5/M
缓存读取 $0.03/M
2025-08-262025-10-22
Nemotron Nano 9B v2
nvidia/nemotron-nano-9b-v2
NVNVIDIANemotron
nvidia/nemotron-nano-9b-v2
Openai chat
131K131K
-开放
输入 $0.06/M · 输出 $0.23/M
2025-08-182025-08-18
GPT-5
openai/gpt-5
OPOpenAIGPT
openai/gpt-5
Openai chat
400K128K
-闭源
输入 $1.25/M · 输出 $10/M
缓存读取 $0.125/M
2025-08-072025-09-19
GPT-5 mini
openai/gpt-5-mini
OPOpenAIGPT
openai/gpt-5-mini
Openai chat
400K128K
-闭源
输入 $0.25/M · 输出 $2/M
缓存读取 $0.025/M
2025-08-072026-08-06
GPT-5 nano
openai/gpt-5-nano
OPOpenAIGPT
openai/gpt-5-nano
Openai chat
400K128K
-闭源
输入 $0.05/M · 输出 $0.4/M
缓存读取 $0.005/M
2025-08-072026-08-06
Claude Opus 4.1
anthropic/claude-opus-4-1-20250805
ANAnthropicClaude
anthropic/claude-opus-4.1
Openai chat
200K32K
-闭源
输入 $15/M · 输出 $75/M
缓存读取 $1.5/M · 缓存写入 $18.75/M
2025-08-052026-08-06
gpt-oss-120b
openai/gpt-oss-120b
OPOpenAIGPT
openai/gpt-oss-120b
Openai chat
131K131K
开放
输入 $0.1/M · 输出 $0.5/M
2025-08-052026-08-06
gpt-oss-20b
openai/gpt-oss-20b
OPOpenAIGPT
openai/gpt-oss-20b
Openai chat
131K131K
开放
输入 $0.05/M · 输出 $0.2/M
2025-08-052026-08-06
Qwen3 Coder Plus
alibaba/qwen3-coder-plus
ALAlibabaQwen
alibaba/qwen3-coder-plus
Openai chat
1M66K
-开放
输入 $1/M · 输出 $5/M
缓存读取 $0.2/M
2025-07-232025-07-23
Kimi K2 0711
moonshotai/kimi-k2
MAMoonshot AIKimi
moonshotai/kimi-k2
Openai chat
131K100K
--开放
输入 $0.57/M · 输出 $2.3/M
2025-07-112026-08-06
Morph V3 Fast
morph/morph-v3-fast
MOMorphMorph
morph/morph-v3-fast
Openai chat
82K38K
---闭源
输入 $0.8/M · 输出 $1.2/M
2025-07-072025-07-07
Morph V3 Large
morph/morph-v3-large
MOMorphMorph
morph/morph-v3-large
Openai chat
262K131K
--闭源
输入 $0.9/M · 输出 $1.9/M
2025-07-072025-07-07
Gemini 2.5 Flash
google/gemini-2.5-flash
GOGoogleGemini
google/gemini-2.5-flash
Openai chat
1M66K
闭源
输入 $0.3/M · 输出 $2.5/M
缓存读取 $0.03/M
2025-06-172026-01-01
Gemini 2.5 Flash-Lite
google/gemini-2.5-flash-lite
GOGoogleGemini
google/gemini-2.5-flash-lite
Openai chat
1M66K
闭源
输入 $0.1/M · 输出 $0.4/M
缓存读取 $0.01/M
2025-06-172026-01-01
Gemini 2.5 Pro
google/gemini-2.5-pro
GOGoogleGemini
google/gemini-2.5-pro
Openai chat
1M66K
闭源
输入 $1.25/M · 输出 $10/M
缓存读取 $0.125/M
2025-06-172026-01-01
o3-pro
openai/o3-pro
OPOpenAIo-series
openai/o3-pro
Openai chat
200K100K
-闭源
输入 $20/M · 输出 $80/M
2025-06-102026-08-06
Claude Opus 4
anthropic/claude-opus-4
ANAnthropicClaude
anthropic/claude-opus-4
Openai chat
200K32K
-闭源
输入 $15/M · 输出 $75/M
缓存读取 $1.5/M · 缓存写入 $18.75/M
2025-05-222026-08-06
Claude Sonnet 4
anthropic/claude-sonnet-4
ANAnthropicClaude
anthropic/claude-sonnet-4
Openai chat
1M64K
-闭源
输入 $3/M · 输出 $15/M
缓存读取 $0.3/M · 缓存写入 $3.75/M
2025-05-222026-08-06
Gemini Embedding 001
google/gemini-embedding-001
GOGoogleGemini
google/gemini-embedding-001
Openai chat
2K1
----闭源
输入 $0.15/M
2025-05-202025-05-20
GPT Image 1
openai/gpt-image-1
OPOpenAIGPT
openai/gpt-image-1
Openai chat
--
----闭源
输入 $5/M · 输出 $40/M
缓存读取 $1.25/M
2025-04-242026-08-06
o3
openai/o3
OPOpenAIo-series
openai/o3
Openai chat
200K100K
-闭源
输入 $2/M · 输出 $8/M
缓存读取 $0.5/M
2025-04-162026-08-06
o4-mini
openai/o4-mini
OPOpenAIo-series
openai/o4-mini
Openai chat
200K100K
-闭源
输入 $1.1/M · 输出 $4.4/M
缓存读取 $0.275/M
2025-04-162026-08-06
GPT-4.1
openai/gpt-4.1
OPOpenAIGPT
openai/gpt-4.1
Openai chat
1M33K
-闭源
输入 $2/M · 输出 $8/M
缓存读取 $0.5/M
2025-04-142026-08-06
GPT-4.1 mini
openai/gpt-4.1-mini
OPOpenAIGPT
openai/gpt-4.1-mini
Openai chat
1M33K
-闭源
输入 $0.4/M · 输出 $1.6/M
缓存读取 $0.1/M
2025-04-142026-08-06
GPT-4.1 nano
openai/gpt-4.1-nano
OPOpenAIGPT
openai/gpt-4.1-nano
Openai chat
1M33K
-闭源
输入 $0.1/M · 输出 $0.4/M
缓存读取 $0.025/M
2025-04-142026-08-06
Command A
cohere/command-a
COCohereCommand
cohere/command-a
Openai chat
256K8.2K
--开放
输入 $2.5/M · 输出 $10/M
2025-03-132025-03-13
DeepSeek-R1
deepseek/deepseek-r1
DEDeepSeekDeepSeek
deepseek/deepseek-r1
Openai chat
128K33K
-开放
输入 $1.35/M · 输出 $5.4/M
2025-01-202026-08-06
o3-mini
openai/o3-mini
OPOpenAIo-series
openai/o3-mini
Openai chat
200K100K
-闭源
输入 $1.1/M · 输出 $4.4/M
缓存读取 $0.55/M
2024-12-202026-08-06
o1
openai/o1
OPOpenAIo-series
openai/o1
Openai chat
200K100K
-闭源
输入 $15/M · 输出 $60/M
缓存读取 $7.5/M
2024-12-052026-08-06
Pixtral 12B
mistral/pixtral-12b-24-09
MAMistral AIPixtral
mistral/pixtral-12b
Openai chat
128K128K
--开放
输入 $0.15/M · 输出 $0.15/M
2024-09-012026-08-06
GPT-4o mini
openai/gpt-4o-mini
OPOpenAIGPT
openai/gpt-4o-mini
Openai chat
128K16K
-闭源
输入 $0.15/M · 输出 $0.6/M
缓存读取 $0.075/M
2024-07-182026-08-06
Mistral Nemo
mistral/mistral-nemo-12b-24-07
MAMistral AIMistral
mistral/mistral-nemo
Openai chat
128K128K
-开放
输入 $0.15/M · 输出 $0.15/M
2024-07-012026-08-06
o3-deep-research
openai/o3-deep-research
OPOpenAIo-series
openai/o3-deep-research
Openai chat
200K100K
--闭源
输入 $10/M · 输出 $40/M
缓存读取 $2.5/M
2024-06-262026-08-06
GPT-4o
openai/gpt-4o
OPOpenAIGPT
openai/gpt-4o
Openai chat
128K16K
-闭源
输入 $2.5/M · 输出 $10/M
缓存读取 $1.25/M
2024-05-132026-08-06
Claude 3 Haiku
anthropic/claude-3-haiku
ANAnthropicClaude
anthropic/claude-3-haiku
Openai chat
200K4.1K
--闭源
输入 $0.25/M · 输出 $1.25/M
缓存读取 $0.03/M · 缓存写入 $0.3/M
2024-03-132026-08-06
Sonar
perplexity/sonar
PEPerplexitySonar
perplexity/sonar
Openai chat
128K4.1K
---闭源
输入 $1/M · 输出 $1/M
2024-01-012025-09-01
Sonar Pro
perplexity/sonar-pro
PEPerplexitySonar
perplexity/sonar-pro
Openai chat
200K8.2K
---闭源
输入 $3/M · 输出 $15/M
2024-01-012025-09-01
Sonar Reasoning Pro
perplexity/sonar-reasoning-pro
PEPerplexitySonar
perplexity/sonar-reasoning-pro
Openai chat
128K4.1K
--闭源
输入 $2/M · 输出 $8/M
2024-01-012025-09-01
GPT-4 Turbo
openai/gpt-4-turbo
OPOpenAIGPT
openai/gpt-4-turbo
Openai chat
128K4.1K
--闭源
输入 $10/M · 输出 $30/M
2023-11-062026-08-06
GPT-3.5 Turbo
openai/gpt-3.5-turbo
OPOpenAIGPT
openai/gpt-3.5-turbo
Openai chat
16K4.1K
---闭源
输入 $0.5/M · 输出 $1.5/M
2023-03-012026-08-06

常见问题