Skip to content

Kimi K3.1 Pro

text + image + video → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$2.28

at Relace

Input / output
$0.24 / $8.40
Providers
20
Spread
3.2×
7 days
−3.9%
30 days
—
Context
1M
Prices per 1M tokens, blended: Relace $2.28, Wafer (us) $2.39, Decart $2.40, Sail Research (fp4/us) $3.12, Sail Research $3.39, InferenceNet $3.60, InferenceNet (mxfp4/us) $3.60, Wafer $3.60, DeepInfra $3.80, AkashML $3.81, Makora $3.87, Alibaba $4.00, DigitalOcean $4.00, Fireworks $4.00, Modal $4.00, Moonshot AI $4.00, Nebius $4.00, Parasail $4.00, PrimaLabs $4.00, River $4.00, Together $4.00, Morph $4.387, InferenceNet (fast) $5.40, InferenceNet (us/fast) $5.40, Amazon Bedrock (us-east-2) $8.00, Moonshot AI (highspeed) $8.00, Amazon Bedrock (us-east-1) $8.80.

Providers

  • RelaceCheapest
    $2.28
    $0.24 in · $8.40 out
    −17% vs ref
    1M ctx100% uptimefp4
  • $2.39
    $0.253 in · $8.80 out
    −13% vs ref
    1M ctx100% uptimemxfp4
  • $2.40
    $1.20 in · $6.00 out
    −13% vs ref
    1M ctx100% uptimemxfp4·−40% discount
  • $3.12
    $1.04 in · $9.35 out
    +13% vs ref
    1M ctx100% uptimefp4
  • $3.39
    $1.40 in · $9.35 out
    +23% vs ref
    1M ctx100% uptimefp4
  • $3.60
    $1.80 in · $9.00 out
    +30% vs ref
    1M ctx100% uptimemxfp4
  • mxfp4/us
    $3.60
    $1.80 in · $9.00 out
    +30% vs ref
    1M ctx100% uptimemxfp4
  • $3.60
    $1.80 in · $9.00 out
    +30% vs ref
    1M ctx100% uptimemxfp4
  • $3.80
    $1.90 in · $9.50 out
    +38% vs ref
    1M ctx99.9% uptimebf16·−5% discount
  • $3.81
    $1.75 in · $10 out
    +38% vs ref
    1M ctx100% uptimefp4
  • $3.87
    $2.00 in · $9.49 out
    +40% vs ref
    1M ctx97.2% uptime
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx100% uptime
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx100% uptime
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx97.5% uptime
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx100% uptimemxfp4
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx99.9% uptimemxfp4
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx100% uptimefp4
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx99.9% uptimefp4
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx100% uptimemxfp4
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx99.9% uptime
  • $4.00
    $2.00 in · $10 out
    +45% vs ref
    1M ctx99.8% uptime
  • $4.387
    $0.975 in · $14.62 out
    +59% vs ref
    1M ctx98.7% uptimefp8
  • $5.40
    $2.70 in · $13.50 out
    +96% vs ref
    1M ctx100% uptimemxfp4
  • $5.40
    $2.70 in · $13.50 out
    +96% vs ref
    1M ctx100% uptimemxfp4
  • $8.00
    $4.00 in · $20 out
    +190% vs ref
    1M ctx100% uptime
  • highspeed
    $8.00
    $4.00 in · $20 out
    +190% vs ref
    1M ctx98.4% uptimemxfp4
  • $8.80
    $4.40 in · $22 out
    +219% vs ref
    1M ctx100% uptime
Blended = (3 × input + output) / 4. Ref $2.76 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

Other pricing

Offered byCache readCache write
Relace, Makora +11$0.20—
Wafer (us), Wafer +1$0.18—
Decart$0.12—
Sail Research (fp4/us), Sail Research$0.187—
InferenceNet, InferenceNet (mxfp4/us)$0.189—
DeepInfra$0.19—
Morph$0.309—
InferenceNet (fast), InferenceNet (us/fast)$0.27—
Amazon Bedrock (us-east-2)$0.20$5.00
Amazon Bedrock (us-east-1)$0.22$5.50

Changes

  • Cache read price,
    $0.353→$0.309−12.5%
  • Output price,
    $16.67→$14.62−12.3%
  • Input price,
    $1.111→$0.975−12.2%
  • Cache read price,
    $0.286→$0.353+23.4%
  • Output price,
    $13.51→$16.67+23.3%
  • Input price,
    $0.901→$1.111+23.3%
  • Cache read price,
    $0.353→$0.286−19.0%
  • Output price,
    $16.66→$13.51−18.9%
  • Input price,
    $1.111→$0.901−18.9%
  • Cache read price,
    $0.18→$0.189+5.0%
  • Cache read price,
    $0.18→$0.189+5.0%
  • Cache read price,
    $0.393→$0.353−10.2%
  • Output price,
    $18.55→$16.66−10.2%
  • Input price,
    $1.236→$1.111−10.1%
  • Cache read price,
    $0.202→$0.393+94.6%

About

The cheapest provider for Kimi K3.1 Pro is Relace at $2.28 per 1M tokens (blended), charging $0.24 per 1M input and $8.40 per 1M output tokens. 20 providers serve it; the most expensive charges 3.2× the typical price. Context window: 1M tokens. Prices tracked since Oct 24, 2026.

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
Released
Oct 23, 2026
First tracked
Oct 24, 2026
Canonical slug
moonshotai/kimi-k3.1-pro-20261023
Weights
moonshotai/Kimi-K3.1-Pro