LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
de

Ornith 1.5 35B A3B

deepreinforce·deepreinforce/ornith-1.5-35b-a3b·GA·Open weights·ornith series·NEW
Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·RunInfraGateway
$0.10 / $0.40
Blended $0.18 · 1× spread
Context
262,144
Output limit
32,768
Knowledge cutoff
—
Released / updated
2026-08-18 / 2026-08-23
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImage
License
MIT
Weights
Hugging Face
References
Model card

Available at 2 providers2 with public prices

  • ProviderInput / Output
  • RunInfraGateway
    ornith-ai/Ornith-1.5-35B-A3B
    $0.10 / $0.40
    Cache read $0.01Context 262,144Output limit 32,768
  • NanoGPTGateway
    $0.10 / $0.40
    Cache read $0.05Context 262,144Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
RunInfra
ornith-ai/Ornith-1.5-35B-A3B
Gateway$0.10$0.40$0.01—262,14432,768
NanoGPTGateway$0.10$0.40$0.05—262,14432,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)

Interleaved thinking (reasoning between tool calls) is declared by 1 of 2 providers.

1 / 2 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1RunInfra$29.20
2NanoGPT$34.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.18

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-21). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

deOrnith 1.5 122Bsame series—deOrnith 1.5 35B Thinkingsame series—deOrnith 1.0 35Bsame series—
Data partly from models.dev (MIT)