Infer

10 models

Claude Haiku 4.5

Default Claude Haiku route for fast background work, summaries, and lightweight agent loops.

Anthropic·1M context·30 Credits / 1M in·150 Credits / 1M out·3 Credits / 1M cache read·37.5 Credits / 1M cache write

Claude Opus 4.6

Default Claude Opus route for complex planning and high-quality reasoning.

Anthropic·1M context·150 Credits / 1M in·750 Credits / 1M out·15 Credits / 1M cache read·187.5 Credits / 1M cache write

Claude Sonnet 4.6

Default Claude Sonnet route for balanced coding, analysis, and agent traffic.

Anthropic·1M context·90 Credits / 1M in·450 Credits / 1M out·9 Credits / 1M cache read·112.5 Credits / 1M cache write

DeepSeek V4 Pro

Infer DeepSeek Pro route for coding, math, and complex analysis workloads.

DeepSeek·1M context·174 Credits / 1M in·348 Credits / 1M out

Gemini 2.5 Flash

Discounted Gemini Flash route for fast multimodal-capable assistant traffic.

Google·1M context·7.5 Credits / 1M in·62.55 Credits / 1M out·1.875 Credits / 1M cache read

Gemini 2.5 Flash Image

Gemini image-capable route for visual prompts and image-token billing.

Google·1M context·7.5 Credits / 1M in·750 Credits / 1M out

GLM-5.2

Z.ai flagship route for long-context bilingual reasoning and agent workloads.

Zhipu·1M context·98 Credits / 1M in·308 Credits / 1M out·18.2 Credits / 1M cache read·98 Credits / 1M cache write

GPT-5.3 Codex

Default Codex-oriented GPT route for developer agents and code tasks.

OpenAI·400K context·140 Credits / 1M in·1,120 Credits / 1M out·14 Credits / 1M cache read·175 Credits / 1M cache write

GPT-5.4

Default GPT-5.4 route for cost-sensitive production agents.

OpenAI·1M context·200 Credits / 1M in·1,200 Credits / 1M out·20 Credits / 1M cache read·250 Credits / 1M cache write

Grok 4.1 Fast

Default Grok route for low-latency chat and production traffic.

xAI·2M context·13 Credits / 1M in·32.5 Credits / 1M out·3.25 Credits / 1M cache read