Skip to content

Qwen3.5 397B A17B

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

Best price · blended / 1M

$0.87

at DeepInfra

Input / output
$0.36 / $2.40
Providers
8
Spread
1.93×
7 days
−0.9%
30 days
−0.9%
Context
256K
Prices per 1M tokens, blended: DeepInfra (fp8/flex) $0.87, Alibaba $0.878, DeepInfra $1.09, Parasail $1.275, AtlasCloud $1.29, GMICloud $1.35, Novita $1.35, StreamLake $1.35, DeepInfra (fp8/priority) $1.63, Venice $1.69.

Providers

  • DeepInfraCheapest
    fp8/flex
    $0.87
    $0.36 in · $2.40 out
    ref vs ref
    256K ctx100% uptimefp8
  • $0.878
    $0.39 in · $2.34 out
    ref vs ref
    256K ctx100% uptime
  • $1.09
    $0.45 in · $3.00 out
    +24% vs ref
    256K ctx97.8% uptimefp8
  • $1.275
    $0.50 in · $3.60 out
    +46% vs ref
    256K ctx99.0% uptimefp8
  • $1.29
    $0.55 in · $3.50 out
    +47% vs ref
    256K ctx100% uptimefp8
  • $1.35
    $0.60 in · $3.60 out
    +55% vs ref
    256K ctx100% uptimefp8
  • $1.35
    $0.60 in · $3.60 out
    +55% vs ref
    256K ctx100% uptime
  • $1.35
    $0.60 in · $3.60 out
    +55% vs ref
    250K ctx97.8% uptime
  • fp8/priority
    $1.63
    $0.675 in · $4.50 out
    +87% vs ref
    256K ctx92.5% uptimefp8
  • $1.69
    $0.75 in · $4.50 out
    +93% vs ref
    125K ctx98.3% uptime
Blended = (3 × input + output) / 4. Ref $0.874 = median of cheapest 20%.

Price history

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

Prices in USD / 1M tokens.

No provider has changed its price since tracking began on Oct 3, 2026.

Other pricing

Offered byCache read
DeepInfra (fp8/flex)$0.176
DeepInfra$0.22
Parasail$0.30
AtlasCloud$0.55
StreamLake$0.12
DeepInfra (fp8/priority)$0.33

Changes

  • Now served,
    Listed
  • Now served,
    Listed
  • No longer served,
    Delisted
  • No longer served,
    Delisted

About

The cheapest provider for Qwen3.5 397B A17B is DeepInfra at $0.87 per 1M tokens (blended), charging $0.36 per 1M input and $2.40 per 1M output tokens. 8 providers serve it; the most expensive charges 1.93× the typical price. Its best price fell 0.9% over the last 30 days. Context window: 256K tokens. Prices tracked since Oct 3, 2026.

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
Released
Feb 16, 2026
First tracked
Oct 3, 2026
Canonical slug
qwen/qwen3.5-397b-a17b-20260216
Weights
Qwen/Qwen3.5-397B-A17B