TOKENBISON / PRICING

Clear prices. Better decisions.

View model prices, cache rates and billing conditions.

Price table

USD · unit shown per model

21 models

USD · unit shown per model
Model	TokenBisonUSD · unit shown per model	Billing conditions / ReferencePlatform pricing
deepseek-v4-proDeepSeek	TokenBison Input$0.70 Output$2.10 Cached: $0.025 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
deepseek-v4.1-flashDeepSeek	TokenBison Input$0.30 Output$1.20 Cached: $0.006 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
doubao-seed-2.0-liteByteDance	TokenBison Input$0.071642 Output$0.429851 Cached: $0.014328 / 1M Base rates · tiered pricing	Billing conditions ≤ 32,000 Input tokens Input $0.071642 / 1M Output $0.429851 / 1M Cached $0.014328 / 1M ≤ 128,000 Input tokens Input $0.107463 / 1M Output $0.644776 / 1M Cached $0.021493 / 1M > 128,000 Input tokens Input $0.214925 / 1M Output $1.289552 / 1M Cached $0.042985 / 1M Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
doubao-seed-2.1-turboByteDance	TokenBison Input$0.358209 Output$1.791045 Cached: $0.071642 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
doubao-seed-evolvingByteDance	TokenBison Input$0.716418 Output$3.58209 Cached: $0.143284 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
glm-5.2Zhipu AI1M context	TokenBison Input$1.12 Output$3.52 Cached: $0.28 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
glm-5.3Zhipu AI1M context	TokenBison Input$1.12 Output$3.52 Cached: $0.28 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
glm-5.3-flashZhipu AI	TokenBison Input$0.06 Output$0.20 Cached: $0.02 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
hy4-previewTencent	TokenBison Input$0.66 Output$2.00 Cached: $0.033 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
kimi-k2.7-codeMoonshot AI	TokenBison Input$0.58 Output$2.80 Cached: $0.116 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
kimi-k3Moonshot AI	TokenBison Input$2.55 Output$12.75 Cached: $0.255 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
minimax-m2.7MiniMax	TokenBison Input$0.21 Output$0.84 Cached: $0.042 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
minimax-m3MiniMax	TokenBison Input$0.23 Output$0.96 Cached: $0.046 / 1M Base rates · tiered pricing	Billing conditions ≤ 512,000 Input tokens Input $0.23 / 1M Output $0.96 / 1M Cached $0.046 / 1M > 512,000 Input tokens Input $0.46 / 1M Output $1.92 / 1M Cached $0.092 / 1M Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
qwen-audio-3.0-tts-plusAlibaba	TokenBison $0.20Per 10000 characters	Billing conditions $0.20／万字符，按实际字符比例计费；每Unicode字符计1（含空格/标点）；文本与音频输出均免费。
qwen3.6-flashAlibaba1M context	TokenBison Input$0.112 Output$0.80 Cached: $0.0224 / 1M Base rates · tiered pricing	Billing conditions ≤ 256,000 Input tokens Input $0.112 / 1M Output $0.80 / 1M Cached $0.0224 / 1M > 256,000 Input tokens Input $0.336 / 1M Output $2.40 / 1M Cached $0.0672 / 1M Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
qwen3.7-maxAlibaba1M context	TokenBison Input$1.25 Output$3.75 Cached: $0.25 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
qwen3.7-plusAlibaba1M context	TokenBison Input$0.256 Output$1.024 Cached: $0.0512 / 1M Base rates · tiered pricing	Billing conditions ≤ 256,000 Input tokens Input $0.256 / 1M Output $1.024 / 1M Cached $0.0512 / 1M > 256,000 Input tokens Input $0.768 / 1M Output $3.072 / 1M Cached $0.1536 / 1M Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
qwen3.8-flashAlibaba1M context	TokenBison Input$0.12 Output$0.376 Cached: $0.024 / 1M Base rates · tiered pricing	Billing conditions ≤ 256,000 Input tokens Input $0.12 / 1M Output $0.376 / 1M Cached $0.024 / 1M > 256,000 Input tokens Input $0.36 / 1M Output $1.128 / 1M Cached $0.072 / 1M Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
qwen3.8-maxAlibaba1M context	TokenBison Input$2.00 Output$6.00 Cached: $0.40 / 1M	Billing conditions Cached input counts toward the tier. One tier applies to the entire request; cached tokens are not charged twice.
wan2.7-imageAlibaba	TokenBison $0.027504Per image	Billing conditions $0.027504／张；按图片张数收费，不叠加尺寸倍率；结算待核对。
wan2.7-image-proAlibaba	TokenBison $0.068761Per image	Billing conditions $0.068761／张；按图片张数收费，不叠加尺寸倍率；结算待核对。

How are these prices compared?

TokenBison catalog prices are configured retail prices. Provider price changes do not automatically change your billing rates. Missing reference prices may be supplemented from verified manufacturer international pricing pages. Token prices are per million tokens. Images are billed per returned image and speech synthesis per input character. Tier thresholds include cached input; one tier applies to the whole request.