Logo SVG copied to clipboard

Use OpenAI SDK with Manifest

1.4B tokens / 30 days
App AI SDK

The OpenAI Python and TypeScript SDKs talk to any OpenAI-compatible endpoint. Point them at Manifest by setting OPENAI_BASE_URL and every chat completion, response, tool call, or Agents SDK loop routes through the cheapest capable model.

70 models routed through Manifest over the last 30 days.

Why use the OpenAI SDK with Manifest

Chatty workloads (Agents SDK loops, tool retries, chain-of-thought reasoning) burn tokens fast. Manifest intercepts each call, picks the right model, and keeps your code identical. Same SDK, same shapes, lower bill.

  • One env var change: OPENAI_BASE_URL
  • Slash token spend by 50–70% on chatty agent loops
  • Works for the OpenAI SDK and the OpenAI Agents SDK
  • Tool calling, structured outputs, and streaming all pass through
  • Per-app spend caps and audit logs in the dashboard
  • Open source: inspect and self-host the router

Setup in 60 seconds

Set two environment variables and the OpenAI SDK picks them up on the next run, no code changes required.

Point the SDK at Manifest by setting these env vars in your shell or .env file: 

export OPENAI_BASE_URL="https://api.manifest.build/v1"
export OPENAI_API_KEY="mnfst_YOUR_KEY"

Then use the SDK exactly as you would normally. Just point at "auto" to let Manifest pick the model: 

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello"}],
)
OPENAI_BASE_URL https://api.manifest.build/v1
OPENAI_API_KEY mnfst_YOUR_KEY
model auto

OpenAI SDK tokens processed on Manifest

Models in use

# Model
 Auth type Tokens / last 30 days
1.Glm 5.1
Subscription677 M
2.Gpt 5.4 Mini
Subscription241 M
3.Minimax M3
Subscription156 M
4.Kimi K2.6
Subscription55 M
5.Claude Opus 4 8
Subscription47 M
6.Glm 5
Subscription46 M
7.Gpt 5.4
Subscription42 M
8.Gpt 5.5
Subscription28 M
9.Gemma 4 31b It
API Key25 M
10.Glm 4.7
Subscription22 M
11.Deepseek V4 Pro
Subscription16 M
12.Gpt 5.3 Codex Spark
Subscription14 M
13.Nex N2 Pro
API Key11 M
14.Claude Sonnet 4 6
Subscription10 M
15.Openrouter Free
API Key6 M
16.Gpt 4o Mini
API Key5 M
17.Kimi K2.7 Code
Subscription4 M
18.Minimax M2.7
API Key4 M
19.Owl Alpha
API Key4 M
20.Gpt 5.4 Mini
API Key3 M
21.Mistral Large Latest
API Key3 M
22.Gemma 4 26b A4b It
API Key2 M
23.Deepseek V4 Pro
Subscription2 M
24.Qwen3.5 397b A17b
API Key2 M
25.Llama 4 Scout 17b 16e Instruct
API Key2 M
26.Qwen3.5:397b
Subscription1 M
27.Glm 5.1
API Key1 M
28.Kimi K2.6
API Key1 M
29.Deepseek V4 Flash
API Key923 K
30.Mistral Medium Latest
API Key763 K
31.Step 3.7 Flash
API Key625 K
32.Qwen3 Coder 480b A35b Instruct
API Key454 K
33.Gemini 3.1 Pro Preview
Subscription453 K
34.Gemma4:31b
Subscription358 K
35.Mimo V2.5 Pro
API Key248 K
36.Gpt 5 Mini
Subscription231 K
37.Gpt 5.3 Codex
Subscription219 K
38.Gpt 4o
Subscription218 K
39.Qwen3.7 Plus
Subscription126 K
40.Seed Oss 36b Instruct
API Key83 K
41.Gpt 5.4
API Key82 K
42.Gpt 5.2
Subscription14 K
43.Gemini 3.1 Flash Lite
API Key7 K
44.Gpt 5.4 Nano
API Key6 K
45.Deepseek V4 Flash
API Key3 K
46.Deepseek V4 Pro
API Key3 K
47.Gemini 2.5 Pro
Subscription2 K
48.Llama 3.3 Nemotron Super 49b V1
API Key2 K
49.MiniMax M2.5 Highspeed
Subscription856
50.Grok 4.3
Subscription828
51.Gpt Oss 120b
API Key783
52.Glm 4.5 Air
API Key777
53.Gemini 2.5 Flash
API Key603
54.Ministral 14b Latest
API Key354
55.Llama 3.3 70b Versatile
API Key314
56.Gpt Oss Safeguard 20b
API Key226
57.Nemotron Mini 4b Instruct
API Key135
58.Mistral Small Latest
API Key132
59.Claude Haiku 4.5
Subscription82
60.Gpt 4.1
Subscription81
61.Devstral 2512
API Key75
62.Hermes 3 Llama 3.1 405b
API Key71
63.Llama 3 70b Instruct
API Key64
64.Mistral Medium 3 5
API Key60
65.Gpt 4o Mini
Subscription57
66.Mistral Medium 2604
API Key53
67.Llama 3.1 8b Instant
API Key41
68.Ministral 3b 2512
API Key20
69.Gemini Flash Lite Latest
API Key17
70.Gemini 2.5 Flash Lite
API Key11

Explore more