Model catalog & pricing

Browse public list prices and capability tags without signing in.

Amounts are in USD; token models are per 1M tokens.

Virtual route entries omit dollar amounts on the card; look up physical models in the catalog.

• someim-auto-flash

  Upstream brand: deepseek

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-auto-pro

  Upstream brand: deepseek

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-code-high

  Upstream brand: zhipu

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-code-low

  Upstream brand: deepseek

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-code-premium

  Upstream brand: openai

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-coding-plan-high

  Upstream brand: zhipu

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-coding-plan-low

  Upstream brand: deepseek

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-coding-plan-premium

  Upstream brand: openai

  Virtual routeBilling follows the physical model your routing actually hits.

• someim-judge

  Upstream brand: deepseek

  Virtual routeBilling follows the physical model your routing actually hits.

• bytedance/seedance-2.0

  Upstream brand: bytedance

  Per second

  .1 / s

• claude-haiku-4-5

  Upstream brand: anthropic

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• claude-opus-4-7

  Upstream brand: anthropic

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• claude-sonnet-4-6

  Upstream brand: anthropic

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• deepseek-v4-flash

  Upstream brand: deepseek

  Input

  .00 / 1M tokens

  Output

  .00 / 1M tokens

• deepseek-v4-pro

  Upstream brand: deepseek

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• gemini-2.0-flash

  Upstream brand: google

  Input

  .15 / 1M tokens

  Output .00 / 1M tokens

• gemini-2.5-flash

  Upstream brand: google

  Input

  .30 / 1M tokens

  Output .50 / 1M tokens

• gemini-3-flash

  Upstream brand: google

  Input

  .00 / 1M tokens

  Output

  .00 / 1M tokens

• gemini-3.1-pro-preview

  Upstream brand: google

  Input .50 / 1M tokens

  Output .00 / 1M tokens

• gemini-3.5-flash

  Upstream brand: google

  Input .52 / 1M tokens

  Output .09 / 1M tokens

• glm-5

  Upstream brand: zhipu

  Input

  .86 / 1M tokens

  Output .14 / 1M tokens

• glm-5.1

  Upstream brand: alibaba

  Input

  .86 / 1M tokens

  Output .43 / 1M tokens

• glm-5.2

  Upstream brand: zhipu

  Input .18 / 1M tokens

  Output .12 / 1M tokens

• gpt-5.6-luna

  Upstream brand: openai

  Input

  .10 / 1M tokens

  Output

  .70 / 1M tokens

• gpt-5.6-sol

  Upstream brand: openai

  Input

  .20 / 1M tokens

  Output .20 / 1M tokens

• gpt-5.6-terra

  Upstream brand: openai

  Input

  .12 / 1M tokens

  Output

  .91 / 1M tokens

• gpt-image-2

  Upstream brand: openai

  Per image

  .02

• grok-4.5

  Upstream brand: xai

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• kimi-k2.5

  Upstream brand: moonshot

  Input

  .35 / 1M tokens

  Output .80 / 1M tokens

• kimi-k2.6

  Upstream brand: moonshot

  Input

  .93 / 1M tokens

  Output .00 / 1M tokens

• kimi-k3

  Upstream brand: moonshot

  Input .86 / 1M tokens

  Output .30 / 1M tokens

• kimi/kimi-k3

  Upstream brand: moonshot

  Input .86 / 1M tokens

  Output .30 / 1M tokens

• klaude-opus-4-7

  Upstream brand: anthropic

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• klaude-sonnet-4-6

  Upstream brand: anthropic

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• MiniMax-M2.5

  Upstream brand: minimax

  Input

  .18 / 1M tokens

  Output

  .72 / 1M tokens

• nano_banana_2

  Upstream brand: google

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• nano-banana-2

  Upstream brand: google

  Per image

  .055

• qwen-flash

  Upstream brand: alibaba

  Input

  .00 / 1M tokens

  Output

  .09 / 1M tokens

• qwen-max

  Upstream brand: alibaba

  Input

  .14 / 1M tokens

  Output

  .55 / 1M tokens

• qwen-plus

  Upstream brand: alibaba

  Input

  .05 / 1M tokens

  Output

  .46 / 1M tokens

• qwen3-vl-plus

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• qwen3.6-max-preview

  Upstream brand: alibaba

  Input .30 / 1M tokens

  Output .80 / 1M tokens

• qwen3.6-plus

  Upstream brand: alibaba

  Input

  .37 / 1M tokens

  Output .77 / 1M tokens

• qwen3.7-max

  Upstream brand: alibaba

  Input .76 / 1M tokens

  Output .26 / 1M tokens

• seedance-2.0

  Upstream brand: bytedance

  Per second

  .1 / s

• someim-free

  Input

  .00 / 1M tokens

  Output

  .00 / 1M tokens

• spt-5.3-codex

  Upstream brand: anthropic

  Input .75 / 1M tokens

  Output .00 / 1M tokens

• spt-5.3-codex-official

  Input .75 / 1M tokens

  Output .00 / 1M tokens

• spt-5.4

  Upstream brand: anthropic

  Input

  .65 / 1M tokens

  Output .00 / 1M tokens

• spt-5.5

  Upstream brand: anthropic

  Input .00 / 1M tokens

  Output .00 / 1M tokens

• veo3.1-lite

  Per request

  .3

• xiaomi/mimo-v2.5

  Upstream brand: xiaomi

  Input

  .80 / 1M tokens

  Output .00 / 1M tokens

Prices in USD; token models per 1M tokens.