Phi 4
MicrosoftReleased Dec 11, 2024phi-4
- Intelligence (Epoch)
- 130 · 95th of 111
- Reasoning
- no
- Context
- 16k tokens
- API features
- structured outputs, JSON mode, seed
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Microsoft
Intelligence for the price
6 models score higher for the same price or less; it ranks 7 of the 11 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 130 with an interval of 125 to 132.
Against its rivals
The best of its price range and the top score
- Phi 4this model$0.21130
- Claude Opus 5.5top score$24.00169
- DeepSeek V4 Flash 0731same price range$0.21155
- GLM-5.3-Flashsame price range$0.19153
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| DeepInfra | $0.07 | $0.14 | — | 79 | 0.24 s | 100% | Oct 23 |
1 provider · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| DeepInfra | bf16 | 16K | — | no | yes | no |
As served by each host and declared to OpenRouter; not verified by us · weights: the precision the host declares
Phi 4 spec sheet, field by field, with sources
Phi 4 spec sheetmaker-declared
What the maker declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- to verify
- Parameters
- to verify
- Active experts
- to verify
- Weight precision
- to verify
- License
- to verifyScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- to verify
- Modalities
- to verify
- Max output (official)
- to verify
- Release date
- to verify≈ December 11, 2024 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
no maker source read yet · 0 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Oct 22 | DeepInfra | $0.056 → $0.07 | $0.11 → $0.14 | +25% |
| Oct 16 | DeepInfra | $0.07 → $0.056 | $0.14 → $0.11 | −20% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $0.14 | $0.63 | $0.42 |
What each host bills for 1,000 requests of a representative job