▣ 1 video models×✦ 2 image models18 chat models
×

One subscription for every InferenceSaver model capability.

Choose a plan based on dashboard model details: capabilities, model IDs, context windows, output limits, and token pricing.

Compare plans

Find the capability mix that works best

Free
$0/month
Explore model details
$0 trialplan usage
  • Core chat model discovery
  • Model pricing visibility
  • Upgrade to unlock multimodal usage
Starter
$4050% OFF
$20/month
$200 billed yearly
For lightweight builds
$200 included usageplan usage
  • For lightweight builds$200 included usage
  • Chat + reasoning: Haiku 4.5.20251001, Opus 4.6CHAT
  • Image generation: Gpt Image 2, Agnes Image 2.1 FlashIMAGE
  • Dashboard model details includedDetails
Builder
$29850% OFF
$149/month
$1,490 billed yearly
For daily model work
$298 included usageplan usage
  • For daily model work$298 included usage
  • Chat + reasoning: Haiku 4.5.20251001, Opus 4.6CHAT
  • Image generation: Gpt Image 2, Agnes Image 2.1 FlashIMAGE
  • Audio + speech: Mimo V2.5 Tts, Music 2.6AUDIO
  • Dashboard model details includedDetails
Frontier
$59850% OFF
$299/month
$2,990 billed yearly
For multi-modal teams
$598 included usageplan usage
  • For multi-modal teams$598 included usage
  • Chat + reasoning: Haiku 4.5.20251001, Opus 4.6CHAT
  • Image generation: Gpt Image 2, Agnes Image 2.1 FlashIMAGE
  • Audio + speech: Mimo V2.5 Tts, Music 2.6AUDIO
  • Video generation: Agnes Video V2.0VIDEO
  • Dashboard model details includedDetails
Max
$99850% OFF
$499/month
annual scale plan
For production volume
Custom scale usageplan usage
  • For production volumeCustom scale usage
  • Chat + reasoning: Haiku 4.5.20251001, Opus 4.6, Opus 4.7CHAT
  • Image generation: Gpt Image 2, Agnes Image 2.1 FlashIMAGE
  • Audio + speech: Mimo V2.5 Tts, Music 2.6, Music 2.6 FreeAUDIO
  • Video generation: Agnes Video V2.0VIDEO
  • Dashboard model details includedDetails
  • Priority access to every capability groupAll models
Compare capabilitiesFreeStarterBuilderFrontierMax
MODEL COVERAGE
Chat + reasoning
Image generation
Video generation
Audio + transcription
REAL MODEL EXAMPLES
Top chat modelsHaiku 4.5.20251001 Opus 4.6 Opus 4.7Haiku 4.5.20251001 Opus 4.6 Opus 4.7Haiku 4.5.20251001 Opus 4.6 Opus 4.7Haiku 4.5.20251001 Opus 4.6 Opus 4.7Haiku 4.5.20251001 Opus 4.6 Opus 4.7
Top image modelsGpt Image 2 Agnes Image 2.1 FlashGpt Image 2 Agnes Image 2.1 FlashGpt Image 2 Agnes Image 2.1 FlashGpt Image 2 Agnes Image 2.1 Flash
Top video modelsAgnes Video V2.0Agnes Video V2.0
Top audio modelsMimo V2.5 Tts Music 2.6 Music 2.6 FreeMimo V2.5 Tts Music 2.6 Music 2.6 FreeMimo V2.5 Tts Music 2.6 Music 2.6 Free
MODEL DETAIL DATA
Maximum context window1M tokens1M tokens1M tokens1M tokens1M tokens
Maximum output tokens128K tokens128K tokens128K tokens128K tokens128K tokens
Input cost visibilityView model pages$0.300 – $5.00 / 1M$0.300 – $5.00 / 1M$0.300 – $5.00 / 1M$0.300 – $5.00 / 1M
Output cost visibilityView model pages$0.300 – $40.00 / 1M$0.300 – $40.00 / 1M$0.300 – $40.00 / 1M$0.300 – $40.00 / 1M
OpenAI-compatible API
Custom credit top-ups

Frequently Asked Questions about InferenceSaver model access

The same capability language used by dashboard model detail pages

For payment or model-access issues, contact us at [email protected]