Curated models for your best work
Join the waitlistPhi-4
- JSON schema
- Streaming
- Open weights
- Runs on DeepInfra
- Context window
- 16K
- tokens
- Input price
- $0.07
- per 1M tokens
- Output price
- $0.14
- per 1M tokens
- Max output
- Provider
- no narrower limit
Provider list price
Pricing
USD / 1M tokens
| Input | $0.07 / M tokens |
| Output | $0.14 / M tokens |
| Context window | 16K tokens |
| Routing | Free |
Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.
Registry 2026-10-21.3 · effective 9/17/2026 · Private rate card. Source withheld.
Registry contract
Capabilities
- Protocols
- 3
- Chat · Responses · Messages · streaming
- Tools
- None
- Not supported
- JSON Schema
- 2
- Chat · Responses
- Vision
- No
- Not supported
- Reasoning
- None
- No public control
- Output limit
- Provider
- No narrower TokenSpend limit
canonical microsoft/phi-4 · revision microsoft/phi-4 · aliases phi-4
First request
Run it
from tokenspend import TokenSpend
client = TokenSpend()
resp = client.chat.completions.create(
model="microsoft/phi-4",
messages=[{"role": "user", "content": "hello"}],
)import { TokenSpend } from "@tokenspend/sdk";
const client = new TokenSpend();
const resp = await client.chat.completions.create({
model: "microsoft/phi-4",
messages: [{ role: "user", content: "hello" }]
});curl https://api.tokenspend.dev/v1/chat/completions \
-H "content-type: application/json" \
-H "Authorization: Bearer $TOKENSPEND_API_KEY" \
-d '{"model":"microsoft/phi-4","messages":[{"role":"user","content":"hello"}]}'export ANTHROPIC_BASE_URL=https://api.tokenspend.dev export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY export ANTHROPIC_MODEL=microsoft/phi-4
One request shape reaches every model. Claude Code connects as an integration with two environment variables. TokenSpend never stores prompts or responses.
Questions
Who runs Phi-4?
DeepInfra runs it, at the list price above. A request that fails there fails with an error, because there is no second provider to move to.
What does Phi-4 cost?
$0.07 per 1M input tokens and $0.14 per 1M output tokens. TokenSpend adds no markup and no per-request fee. If you pay with managed credits, buying them carries a 5% fee.
What can I do with Phi-4 through TokenSpend?
Chat and streaming, plus JSON schema output (Chat, Responses). It does not support tool calling and image input here. Tool calling and JSON schema are enabled per provider, only after that provider passes our tests, so a provider chosen by hand may lack them.
How long can my prompt be?
16K tokens of context, prompt and reply together.
How current is this pricing?
It follows rate card 2026-10-21.3, effective 9/17/2026. Source: Private rate card.