Top open models,in the agent you already use.
One key and one endpoint for the strongest open coding models. Works with Claude Code, Codex, OpenCode, Cline and Cursor, and switching models never touches your setup.
- No charge at signup
- Cancel anytime
- Prompt bodies are never stored
# ~/.zshrc
export ANTHROPIC_BASE_URL=https://inferaft.com
export ANTHROPIC_API_KEY=$INFERAFT_API_KEY
export ANTHROPIC_MODEL=custom/kimi-k3
$ claude
› Refactor the billing webhook and add tests.
✓ 3 files changed · 12 tests passed
$ ANTHROPIC_MODEL=custom/glm-5.3 claude
› Same repo, lighter model for the follow-up.Requests
4 · $0.0341
- kimi-k3$0.0218↑148,212 ↓1,904 · cache 91%
- glm-5.3$0.0061↑96,440 ↓1,212 · cache 88%
- deepseek-v4-flash$0.0015↑52,118 ↓806 · cache 94%
- qwen-3.8-27b$0.0047↑61,020 ↓1,450 · cache 85%
Keep your agent, or use ours.
Both run on the same key, the same catalog and the same plan.
Inferaft API
Your agent, our models.
Point the agent you already run, or any OpenAI-compatible client, at one base URL. Your prompts, tools and habits stay as they are.
Claude Code
Codex
Cline
Cursor
Inferaft Code
Our agent, made for them.
A terminal agent with sub-agents, a macOS sandbox, rewind and memory. Included in every plan.
brew install inferaft/tap/inferaft-codeA gateway shaped around agent work.
Long contexts, heavy caching and many small turns. Inferaft is built for that traffic, and shows you what each turn cost.
Switch models without rewiring
Keep the same endpoint and client configuration when you move between models. Plan with a flagship, iterate with a fast one.
- kimi-k3
- glm-5.3
- deepseek-v4-pro
- qwen-3.8-27b
- deepseek-v4-flash
- gemma-4-31b
- Every model, rate and limit
Three wire formats
Whatever your agent speaks, it reaches the same catalog.
- POST/v1/chat/completions
- POST/v1/messages
- POST/v1/responses
No surprise charges
One shared allowance, paced by rolling windows. At the limit you get a clear plan_usage_limit error, never an overage bill.
Your prompts stay yours
Request history stores metadata and token counts. Prompt and response bodies are not retained.
Images included
Z-Image Turbo comes with every plan, with five free images a day before it draws on the same allowance.
Connected in a minute.
No SDK to adopt, no proxy to run, no config format to learn.
01Create a key
One key per project or tool, with its own usage history.
02Paste the base URL
Point your agent at inferaft.com. Claude Code, Codex, OpenCode and Cline each have a ready-made block.
03Pick a model and ship
Change models by name whenever you like. The endpoint and key stay the same.
export ANTHROPIC_BASE_URL="https://inferaft.com"
export ANTHROPIC_API_KEY="$INFERAFT_API_KEY"
unset ANTHROPIC_AUTH_TOKEN
export ANTHROPIC_MODEL="custom/kimi-k3"
export ANTHROPIC_CUSTOM_MODEL_OPTION="$ANTHROPIC_MODEL"
export CLAUDE_CODE_MAX_OUTPUT_TOKENS=8192
export ANTHROPIC_DEFAULT_SONNET_MODEL="$ANTHROPIC_MODEL"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="$ANTHROPIC_MODEL"
export ANTHROPIC_DEFAULT_OPUS_MODEL="$ANTHROPIC_MODEL"
export ANTHROPIC_SMALL_FAST_MODEL="custom/glm-5.3-flash"
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
claude --model "$ANTHROPIC_MODEL"Pick a size. Every model is included.
Every plan uses the same model catalog and agent setup. Choose the amount of included usage that fits your workflow.
Lite
≈365 Kimi K3 / 30d
5-hour pace: ≈73 Kimi · ≈246 GLM
100 Z-Image Turbo images / 30 days
Pro
≈912 Kimi K3 / 30d
5-hour pace: ≈182 Kimi · ≈614 GLM
250 Z-Image Turbo images / 30 days
Max
≈2,280 Kimi K3 / 30d
5-hour pace: ≈684 Kimi · ≈2,302 GLM
800 Z-Image Turbo images / 30 days
Ultra
≈4,561 Kimi K3 / 30d
5-hour pace: ≈1,368 Kimi · ≈4,604 GLM
2,000 Z-Image Turbo images / 30 days
5 free images daily, resetting at midnight KST. Further images use $0.005 each from the same plan allowance as text, subject to the image caps above and your remaining allowance. No additional charge. Image model details
Every plan includes one shared usage allowance across the catalog. Published token rates are safety ceilings. Included usage cannot be withdrawn, and purchases are final. Refund policy
Questions, answered plainly.
Billing questions are answered on the pricing page. Anything else: support@inferaft.com.
Can I keep my current coding agent?
Yes. Inferaft speaks OpenAI Chat Completions, Anthropic Messages and OpenAI Responses, so most agents need one base URL and one key. The docs carry a copy-paste block for each supported client.
Which models can I use today?
The live catalog is the source of truth for what is available now. You can change models without changing the endpoint or API key.
Do I need Inferaft Code?
No. It is one more client, included in every plan and tuned for the catalog. Any agent that speaks one of the three API formats works just as well.
What do you keep from my requests?
Request history stores metadata and token counts so you can see what each turn cost. Prompt and response bodies are not retained.
Where do I get help?
Email support@inferaft.com with the request ID from the console. Never send your API key or password.
Bring your next idea. Keep your tools.
Create a key, paste one base URL, and your agent is running on open models in under a minute.
Card handled by Paddle