Models

Every model available through the gateway, with one key and one bill. This list mirrors GET /v1/models — swap in a live fetch against that endpoint to replace this mock shelf.

7 of 7 models

ByteHorizon Chat Pro

bh-chat-proByteHorizon

Flagship general-purpose chat model. Strong reasoning and instruction-following for everyday production traffic.

32K

context

$2 / $8

per 1M tok (in/out)

Try it

ByteHorizon Reasoner

bh-reasonerByteHorizon

Deep multi-step reasoning model for complex analysis, planning, and agentic workflows.

32K

context

$4 / $16

per 1M tok (in/out)

Try it

ByteHorizon Chat Lite

bh-chat-liteByteHorizon

Lightweight and fast — built for high-volume, latency-sensitive chat and classification tasks.

32K

context

$0.6 / $2.4

per 1M tok (in/out)

Try it

GPT-4o

gpt-4oOpenAImultimodal

OpenAI's natively multimodal flagship model, routed through the gateway with one unified key.

128K

context

$5 / $15

per 1M tok (in/out)

Try it

GPT-4o Mini

gpt-4o-miniOpenAImultimodal

Smaller, cheaper GPT-4o variant for high-throughput everyday tasks.

128K

context

$0.15 / $0.6

per 1M tok (in/out)

Try it

Claude 3.5 Sonnet

claude-3-5-sonnetAnthropic

Anthropic's balanced model for coding, writing, and analysis — strong instruction-following at mid-tier cost.

200K

context

$3 / $15

per 1M tok (in/out)

Try it

Llama 3.3 70B

byte-horizon-llama-70bByteHorizon

Open-weight 70B model on dedicated infrastructure — a self-hosted, cost-efficient alternative to closed models.

128K

context

$0.9 / $0.9

per 1M tok (in/out)

Try it