价格

简单的按量计费。

从免费额度开始,之后按使用量付费。默认按上游模型成本计价。

Starter
$0

适合测试 API 和早期原型开发。

  • $1 注册额度
  • 访问已配置模型
  • 控制台用量追踪
  • API Key 管理
免费开始
Enterprise
定制

适合需要 SLA、私有路由、合规评估或独立部署的团队。

  • 私有中转选项
  • 直连服务商路由
  • 自定义额度和限制
  • 发票和采购支持
联系销售

常见模型费率

费率以每 100 万 Token 的美元价格展示,并已包含当前全局加价比例。

价格更新时间: 2026-05-18T11:35:13Z

模型输入输出
DeepSeek-V4-Flash$0.15$0.3
DeepSeek-V4-PRO$0.45$0.9
GLM-4-Flash-250414$0.01$0.01
GLM-4-FlashX-250414$0.1$0.2
GLM-4-Long$0.1$0.5
GLM-4.5-Air$0.15$0.8
GLM-4.5-AirX$0.25$1
GLM-4.6$0.3$1.3
GLM-4.7$0.35$1.4
GLM-4.7-Flash$0.01$0.01
GLM-4.7-FlashX$0.25$0.3
GLM-5$0.5$1.8
GLM-5-Turbo$1.3$3.5
GLM-5.1$0.9$3
ai21/jamba-large-1.7$2$8
aion-labs/aion-1.0$4$8
aion-labs/aion-1.0-mini$0.7$1.4
aion-labs/aion-2.0$0.8$1.6
aion-labs/aion-rp-llama-3.1-8b$0.8$1.6
alfredpros/codellama-7b-instruct-solidity$0.8$1.2
alibaba/tongyi-deepresearch-30b-a3b$0.09$0.45
allenai/olmo-3-32b-think$0.15$0.5
amazon/nova-2-lite-v1$0.3$2.5
amazon/nova-lite-v1$0.06$0.24
amazon/nova-micro-v1$0.035$0.14
amazon/nova-premier-v1$2.5$12.5
amazon/nova-pro-v1$0.8$3.2
anthracite-org/magnum-v4-72b$3$5
anthropic/claude-3-haiku$0.25$1.25
anthropic/claude-3.5-haiku$0.8$4
anthropic/claude-haiku-4.5$1$5
anthropic/claude-opus-4$15$75
anthropic/claude-opus-4.1$15$75
anthropic/claude-opus-4.5$5$25
anthropic/claude-opus-4.6$5$25
anthropic/claude-opus-4.6-fast$30$150
anthropic/claude-opus-4.7$5$25
anthropic/claude-opus-4.7-fast$30$150
anthropic/claude-sonnet-4$3$15
anthropic/claude-sonnet-4.5$3$15
anthropic/claude-sonnet-4.6$3$15
arcee-ai/coder-large$0.5$0.8
arcee-ai/maestro-reasoning$0.9$3.3
arcee-ai/spotlight$0.18$0.18
arcee-ai/trinity-large-preview$0.15$0.45
arcee-ai/trinity-large-thinking$0.22$0.85
arcee-ai/trinity-mini$0.045$0.15
arcee-ai/virtuoso-large$0.75$1.2
baai/bge-base-en-v1.5$0.005$0
baai/bge-large-en-v1.5$0.01$0
baai/bge-m3$0.01$0
baidu/ernie-4.5-21b-a3b$0.07$0.28
baidu/ernie-4.5-21b-a3b-thinking$0.07$0.28
baidu/ernie-4.5-300b-a47b$0.28$1.1
baidu/ernie-4.5-vl-28b-a3b$0.14$0.56
baidu/ernie-4.5-vl-424b-a47b$0.42$1.25
baidu/qianfan-ocr-fast$0.68$2.81
bytedance-seed/seed-1.6$0.25$2
bytedance-seed/seed-1.6-flash$0.075$0.3
bytedance-seed/seed-2.0-lite$0.25$2
bytedance-seed/seed-2.0-mini$0.1$0.4
bytedance/ui-tars-1.5-7b$0.1$0.2
canopylabs/orpheus-3b-0.1-ft$7$0
cohere/command-a$2.5$10
cohere/command-r-08-2024$0.15$0.6
cohere/command-r-plus-08-2024$2.5$10
cohere/command-r7b-12-2024$0.0375$0.15
deepcogito/cogito-v2.1-671b$1.25$1.25
deepseek-chat$0.14$0.28
deepseek-reasoner$0.55$2.19
deepseek/deepseek-chat$0.32$0.89
deepseek/deepseek-chat-v3-0324$0.2$0.77
deepseek/deepseek-chat-v3.1$0.21$0.79
deepseek/deepseek-r1$0.7$2.5
deepseek/deepseek-r1-0528$0.5$2.15
deepseek/deepseek-r1-distill-llama-70b$0.7$0.8
deepseek/deepseek-r1-distill-qwen-32b$0.29$0.29
deepseek/deepseek-v3.1-terminus$0.27$0.95
deepseek/deepseek-v3.2$0.252$0.378
deepseek/deepseek-v3.2-exp$0.27$0.41
deepseek/deepseek-v3.2-speciale$0.287$0.431
deepseek/deepseek-v4-flash$0.112$0.224
deepseek/deepseek-v4-pro$0.435$0.87
essentialai/rnj-1-instruct$0.15$0.15
google/chirp-3$16000$0
google/gemini-2.0-flash-001$0.1$0.4
google/gemini-2.0-flash-lite-001$0.075$0.3
google/gemini-2.5-flash$0.3$2.5
google/gemini-2.5-flash-image$0.3$2.5
google/gemini-2.5-flash-lite$0.1$0.4
google/gemini-2.5-flash-lite-preview-09-2025$0.1$0.4
google/gemini-2.5-pro$1.25$10
google/gemini-2.5-pro-preview$1.25$10
google/gemini-2.5-pro-preview-05-06$1.25$10
google/gemini-3-flash-preview$0.5$3
google/gemini-3-pro-image-preview$2$12
google/gemini-3.1-flash-image-preview$0.5$3
google/gemini-3.1-flash-lite$0.25$1.5
google/gemini-3.1-flash-lite-preview$0.25$1.5
google/gemini-3.1-flash-tts-preview$1$20
google/gemini-3.1-pro-preview$2$12
google/gemini-3.1-pro-preview-customtools$2$12
google/gemini-embedding-001$0.15$0
google/gemini-embedding-2-preview$0.2$0
google/gemma-2-27b-it$0.65$0.65
google/gemma-3-12b-it$0.04$0.13
google/gemma-3-27b-it$0.08$0.16
google/gemma-3-4b-it$0.04$0.08
google/gemma-3n-e4b-it$0.06$0.12
google/gemma-4-26b-a4b-it$0.06$0.33
google/gemma-4-31b-it$0.12$0.37
gryphe/mythomax-l2-13b$0.06$0.06
hexgrad/kokoro-82m$0.62$0
ibm-granite/granite-4.0-h-micro$0.017$0.112
ibm-granite/granite-4.1-8b$0.05$0.1
inception/mercury-2$0.25$0.75
inclusionai/ling-2.6-1t$0.3$2.5
inclusionai/ling-2.6-flash$0.01$0.03
inclusionai/ring-2.6-1t$0.075$0.625
inflection/inflection-3-pi$2.5$10
inflection/inflection-3-productivity$2.5$10
intfloat/e5-base-v2$0.005$0
intfloat/e5-large-v2$0.01$0
intfloat/multilingual-e5-large$0.01$0
kimi-k2.5$0.6$3
kimi-k2.6$1$4
kwaipilot/kat-coder-pro-v2$0.3$1.2
liquid/lfm-2-24b-a2b$0.03$0.12
mancer/weaver$0.75$1
meta-llama/llama-3-70b-instruct$0.51$0.74
meta-llama/llama-3-8b-instruct$0.04$0.04
meta-llama/llama-3.1-70b-instruct$0.4$0.4
meta-llama/llama-3.1-8b-instruct$0.02$0.05
meta-llama/llama-3.2-11b-vision-instruct$0.245$0.245
meta-llama/llama-3.2-1b-instruct$0.027$0.201
meta-llama/llama-3.2-3b-instruct$0.0509$0.335
meta-llama/llama-3.3-70b-instruct$0.1$0.32
meta-llama/llama-4-maverick$0.15$0.6
meta-llama/llama-4-scout$0.08$0.3
meta-llama/llama-guard-3-8b$0.484$0.03
meta-llama/llama-guard-4-12b$0.18$0.18
microsoft/phi-4$0.065$0.14
microsoft/phi-4-mini-instruct$0.08$0.35
microsoft/wizardlm-2-8x22b$0.62$0.62
minimax/minimax-01$0.2$1.1
minimax/minimax-m1$0.4$2.2
minimax/minimax-m2$0.255$1
minimax/minimax-m2-her$0.3$1.2
minimax/minimax-m2.1$0.29$0.95
minimax/minimax-m2.5$0.15$1.15
minimax/minimax-m2.7$0.279$1.2
mistralai/codestral-2508$0.3$0.9
mistralai/codestral-embed-2505$0.15$0
mistralai/devstral-2512$0.4$2
mistralai/devstral-medium$0.4$2
mistralai/devstral-small$0.1$0.3
mistralai/ministral-14b-2512$0.2$0.2
mistralai/ministral-3b-2512$0.1$0.1
mistralai/ministral-8b-2512$0.15$0.15
mistralai/mistral-7b-instruct-v0.1$0.11$0.19
mistralai/mistral-embed-2312$0.1$0
mistralai/mistral-large$2$6
mistralai/mistral-large-2407$2$6
mistralai/mistral-large-2411$2$6
mistralai/mistral-large-2512$0.5$1.5
mistralai/mistral-medium-3$0.4$2
mistralai/mistral-medium-3-5$1.5$7.5
mistralai/mistral-medium-3.1$0.4$2
mistralai/mistral-nemo$0.02$0.03
mistralai/mistral-saba$0.2$0.6
mistralai/mistral-small-24b-instruct-2501$0.05$0.08
mistralai/mistral-small-2603$0.15$0.6
mistralai/mistral-small-3.1-24b-instruct$0.351$0.555
mistralai/mistral-small-3.2-24b-instruct$0.075$0.2
mistralai/mixtral-8x22b-instruct$2$6
mistralai/pixtral-large-2411$2$6
mistralai/voxtral-mini-transcribe$3000$0
mistralai/voxtral-mini-tts-2603$16$0
mistralai/voxtral-small-24b-2507$0.1$0.3
moonshot-v1-128k$1.5$4.3
moonshot-v1-128k-vision-preview$1.5$4.3
moonshot-v1-32k$0.8$3.2
moonshot-v1-32k-vision-preview$0.8$3.2
moonshot-v1-8k$0.3$1.5
moonshot-v1-8k-vision-preview$0.3$1.5
moonshotai/kimi-k2$0.57$2.3
moonshotai/kimi-k2-0905$0.6$2.5
moonshotai/kimi-k2-thinking$0.6$2.5
moonshotai/kimi-k2.5$0.4$1.9
moonshotai/kimi-k2.6$0.73$3.49
morph/morph-v3-fast$0.8$1.2
morph/morph-v3-large$0.9$1.9
nex-agi/deepseek-v3.1-nex-n1$0.135$0.5
nousresearch/hermes-2-pro-llama-3-8b$0.14$0.14
nousresearch/hermes-3-llama-3.1-405b$1$1
nousresearch/hermes-3-llama-3.1-70b$0.3$0.3
nousresearch/hermes-4-405b$1$3
nousresearch/hermes-4-70b$0.13$0.4
nvidia/llama-3.3-nemotron-super-49b-v1.5$0.1$0.4
nvidia/nemotron-3-nano-30b-a3b$0.05$0.2
nvidia/nemotron-3-super-120b-a12b$0.09$0.45
nvidia/nemotron-nano-9b-v2$0.04$0.16
openai/gpt-3.5-turbo$0.5$1.5
openai/gpt-3.5-turbo-0613$1$2
openai/gpt-3.5-turbo-16k$3$4
openai/gpt-3.5-turbo-instruct$1.5$2
openai/gpt-4$30$60
openai/gpt-4-0314$30$60
openai/gpt-4-1106-preview$10$30
openai/gpt-4-turbo$10$30
openai/gpt-4-turbo-preview$10$30
openai/gpt-4.1$2$8
openai/gpt-4.1-mini$0.4$1.6
openai/gpt-4.1-nano$0.1$0.4
openai/gpt-4o$2.5$10
openai/gpt-4o-2024-05-13$5$15
openai/gpt-4o-2024-08-06$2.5$10
openai/gpt-4o-2024-11-20$2.5$10
openai/gpt-4o-audio-preview$2.5$10
openai/gpt-4o-mini$0.15$0.6
openai/gpt-4o-mini-2024-07-18$0.15$0.6
openai/gpt-4o-mini-search-preview$0.15$0.6
openai/gpt-4o-mini-transcribe$1.25$5
openai/gpt-4o-mini-tts-2025-12-15$0.6$0
openai/gpt-4o-search-preview$2.5$10
openai/gpt-4o-transcribe$2.5$10
openai/gpt-5$1.25$10
openai/gpt-5-chat$1.25$10
openai/gpt-5-codex$1.25$10
openai/gpt-5-image$10$10
openai/gpt-5-image-mini$2.5$2
openai/gpt-5-mini$0.25$2
openai/gpt-5-nano$0.05$0.4
openai/gpt-5-pro$15$120
openai/gpt-5.1$1.25$10
openai/gpt-5.1-chat$1.25$10
openai/gpt-5.1-codex$1.25$10
openai/gpt-5.1-codex-max$1.25$10
openai/gpt-5.1-codex-mini$0.25$2
openai/gpt-5.2$1.75$14
openai/gpt-5.2-chat$1.75$14
openai/gpt-5.2-codex$1.75$14
openai/gpt-5.2-pro$21$168
openai/gpt-5.3-chat$1.75$14
openai/gpt-5.3-codex$1.75$14
openai/gpt-5.4$2.5$15
openai/gpt-5.4-image-2$8$15
openai/gpt-5.4-mini$0.75$4.5
openai/gpt-5.4-nano$0.2$1.25
openai/gpt-5.4-pro$30$180
openai/gpt-5.5$5$30
openai/gpt-5.5-pro$30$180
openai/gpt-audio$2.5$10
openai/gpt-audio-mini$0.6$2.4
openai/gpt-chat-latest$5$30
openai/gpt-oss-120b$0.039$0.18
openai/gpt-oss-20b$0.03$0.14
openai/gpt-oss-safeguard-20b$0.075$0.3
openai/o1$15$60
openai/o1-pro$150$600
openai/o3$2$8
openai/o3-deep-research$10$40
openai/o3-mini$1.1$4.4
openai/o3-mini-high$1.1$4.4
openai/o3-pro$20$80
openai/o4-mini$1.1$4.4
openai/o4-mini-deep-research$2$8
openai/o4-mini-high$1.1$4.4
openai/text-embedding-3-large$0.13$0
openai/text-embedding-3-small$0.02$0
openai/text-embedding-ada-002$0.1$0
openai/whisper-1$6000$0
openai/whisper-large-v3$111000$0
openai/whisper-large-v3-turbo$40000$0
perceptron/perceptron-mk1$0.15$1.5
perplexity/pplx-embed-v1-0.6b$0.004$0
perplexity/pplx-embed-v1-4b$0.03$0
perplexity/sonar$1$1
perplexity/sonar-deep-research$2$8
perplexity/sonar-pro$3$15
perplexity/sonar-pro-search$3$15
perplexity/sonar-reasoning-pro$2$8
prime-intellect/intellect-3$0.2$1.1
qwen-plus$0.25$0.76
qwen-turbo$0.28$0.84
qwen/qwen-2.5-72b-instruct$0.36$0.4
qwen/qwen-2.5-7b-instruct$0.04$0.1
qwen/qwen-2.5-coder-32b-instruct$0.66$1
qwen/qwen-plus$0.26$0.78
qwen/qwen-plus-2025-07-28$0.26$0.78
qwen/qwen-plus-2025-07-28:thinking$0.26$0.78
qwen/qwen2.5-vl-72b-instruct$0.25$0.75
qwen/qwen3-14b$0.1$0.24
qwen/qwen3-235b-a22b$0.455$1.82
qwen/qwen3-235b-a22b-2507$0.071$0.1
qwen/qwen3-235b-a22b-thinking-2507$0.1495$1.495
qwen/qwen3-30b-a3b$0.09$0.45
qwen/qwen3-30b-a3b-instruct-2507$0.09$0.3
qwen/qwen3-30b-a3b-thinking-2507$0.08$0.4
qwen/qwen3-32b$0.08$0.28
qwen/qwen3-8b$0.05$0.4
qwen/qwen3-asr-flash-2026-02-10$35$0
qwen/qwen3-coder$0.22$1.8
qwen/qwen3-coder-30b-a3b-instruct$0.07$0.27
qwen/qwen3-coder-flash$0.195$0.975
qwen/qwen3-coder-next$0.11$0.8
qwen/qwen3-coder-plus$0.65$3.25
qwen/qwen3-embedding-4b$0.02$0
qwen/qwen3-embedding-8b$0.01$0
qwen/qwen3-max$0.78$3.9
qwen/qwen3-max-thinking$0.78$3.9
qwen/qwen3-next-80b-a3b-instruct$0.09$1.1
qwen/qwen3-next-80b-a3b-thinking$0.0975$0.78
qwen/qwen3-vl-235b-a22b-instruct$0.2$0.88
qwen/qwen3-vl-235b-a22b-thinking$0.26$2.6
qwen/qwen3-vl-30b-a3b-instruct$0.13$0.52
qwen/qwen3-vl-30b-a3b-thinking$0.13$1.56
qwen/qwen3-vl-32b-instruct$0.104$0.416
qwen/qwen3-vl-8b-instruct$0.08$0.5
qwen/qwen3-vl-8b-thinking$0.117$1.365
qwen/qwen3.5-122b-a10b$0.26$2.08
qwen/qwen3.5-27b$0.195$1.56
qwen/qwen3.5-35b-a3b$0.14$1
qwen/qwen3.5-397b-a17b$0.39$2.34
qwen/qwen3.5-9b$0.04$0.15
qwen/qwen3.5-flash-02-23$0.065$0.26
qwen/qwen3.5-plus-02-15$0.26$1.56
qwen/qwen3.5-plus-20260420$0.3$1.8
qwen/qwen3.6-27b$0.32$3.2
qwen/qwen3.6-35b-a3b$0.15$1
qwen/qwen3.6-flash$0.1875$1.125
qwen/qwen3.6-max-preview$1.04$6.24
qwen/qwen3.6-plus$0.325$1.95
qwen3.5-plus$0.4$2.4
qwen3.5-plus-2026-02-15$0.4$2.4
qwen3.5-plus-2026-04-20$0.4$2.4
rekaai/reka-edge$0.1$0.1
rekaai/reka-flash-3$0.1$0.2
relace/relace-apply-3$0.85$1.25
relace/relace-search$1$3
sao10k/l3-euryale-70b$1.48$1.48
sao10k/l3-lunaris-8b$0.04$0.05
sao10k/l3.1-70b-hanami-x1$3$3
sao10k/l3.1-euryale-70b$0.85$0.85
sao10k/l3.3-euryale-70b$0.65$0.75
sentence-transformers/all-minilm-l12-v2$0.005$0
sentence-transformers/all-minilm-l6-v2$0.005$0
sentence-transformers/all-mpnet-base-v2$0.005$0
sentence-transformers/multi-qa-mpnet-base-dot-v1$0.005$0
sentence-transformers/paraphrase-minilm-l6-v2$0.005$0
sesame/csm-1b$7$0
stepfun/step-3.5-flash$0.1$0.3
switchpoint/router$0.85$3.4
tencent/hunyuan-a13b-instruct$0.14$0.57
tencent/hy3-preview$0.066$0.26
thedrummer/cydonia-24b-v4.1$0.3$0.5
thedrummer/rocinante-12b$0.17$0.43
thedrummer/skyfall-36b-v2$0.55$0.8
thedrummer/unslopnemo-12b$0.4$0.4
thenlper/gte-base$0.005$0
thenlper/gte-large$0.01$0
undi95/remm-slerp-l2-13b$0.45$0.65
upstage/solar-pro-3$0.15$0.6
writer/palmyra-x5$0.6$6
x-ai/grok-4.20$1.25$2.5
x-ai/grok-4.20-multi-agent$2$6
x-ai/grok-4.3$1.25$2.5
x-ai/grok-voice-tts-1.0$15$0
xiaomi/mimo-v2-flash$0.1$0.3
xiaomi/mimo-v2-omni$0.4$2
xiaomi/mimo-v2-pro$1$3
xiaomi/mimo-v2.5$0.4$2
xiaomi/mimo-v2.5-pro$1$3
z-ai/glm-4-32b$0.1$0.1
z-ai/glm-4.5$0.6$2.2
z-ai/glm-4.5-air$0.13$0.85
z-ai/glm-4.5v$0.6$1.8
z-ai/glm-4.6$0.43$1.74
z-ai/glm-4.6v$0.3$0.9
z-ai/glm-4.7$0.4$1.75
z-ai/glm-4.7-flash$0.06$0.4
z-ai/glm-5$0.6$1.92
z-ai/glm-5-turbo$1.2$4
z-ai/glm-5.1$0.98$3.08
z-ai/glm-5v-turbo$1.2$4
zyphra/zonos-v0.1-hybrid$7$0
zyphra/zonos-v0.1-transformer$7$0
~anthropic/claude-haiku-latest$1$5
~anthropic/claude-opus-latest$5$25
~anthropic/claude-sonnet-latest$3$15
~google/gemini-flash-latest$0.5$3
~google/gemini-pro-latest$2$12
~moonshotai/kimi-latest$0.73$3.49
~openai/gpt-latest$5$30
~openai/gpt-mini-latest$0.75$4.5