--- title: "Microsoft: Phi 4 — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/microsoft__phi-4/ description: "Microsoft: Phi 4: $0.070/M in, $0.140/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # Microsoft: Phi 4 — price, capability and what beats it · Undominated.ai > Microsoft: Phi 4: $0.070/M in, $0.140/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/microsoft__phi-4/) [Cheaper alternatives](/alternatives/microsoft__phi-4/) [Family](/families/) [Compare models](https://undominated.ai/compare/?models=microsoft%2Fphi-4) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # Phi 4 Microsoft · 10 Jan 2025 · mit Balanced Summarise Chat Code gen Agentic BETTER VALUE OPTION ## A stored alternative has an equal-or-higher measured score and an equal-or-lower price. **$0.088** / 1M tokens Balanced · 3 tokens in per 1 out [gpt-oss-120b](/models/openai__gpt-oss-120b/) · Δ score 148.7 points · 26% lower measured price · $0.065 / 1M tokens Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [Vendor cross-check](https://openrouter.ai/api/v1/models) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,216.7 ± 4.58 · 24,126 votes Context window 16.38K Maximum output 14.75K Input modalities text Output modalities text Published input price $0.070 / 1M tokens Published output price $0.140 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from DeepInfra: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (bf16), at its standard rate. The maker’s own precision is not known. Every price dimension · USD per million tokens | Input | $0.070 /M | | --- | --- | | Output | $0.140 /M | | Cached input | Unknown /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. 1 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller DeepInfra deepinfra/bf16 Endpoint terms Cached input /M Unknown Context limit 16,384 tokens Output limit 14,745 tokens Tools Not listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.070 | Output $0.140 | Precision bf16 | Uptime (1d) 100.00% | ### Independent scores | LMArena Elo | 1216.7 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. ### Capability | Context window | 16K | | --- | --- | | Max output | 14K | | Input modes | text | | Tool use | no | | Reasoning | no | | Knowledge cutoff | 2024-06-30 | | Open weights | yes | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | | Cross-checked | [vendor page](https://openrouter.ai/api/v1/models) | [Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion... ## Questions this page answers What does Phi 4 cost? $0.070/M in, $0.140/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Phi 4 have an independent quality score? Phi 4 has an LMArena score in this catalogue. What beats Phi 4? gpt-oss-120b has an equal-or-higher measured score and an equal-or-lower price. Does this page use Artificial Analysis scores for Phi 4? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Microsoft: Phi 4. Balanced workload. Better value option available. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related - Both better and cheaper [gpt-oss-120b](/models/openai__gpt-oss-120b/) - Nearby on the capability axis [Command R+ (08-2024)](/models/cohere__command-r-plus-08-2024/) - Same vendor [WizardLM-2 8x22B](/models/microsoft__wizardlm-2-8x22b/) - Microsoft models [Microsoft](/providers/microsoft/) - Where this model appears [self-host](/self-host/) - Nearby on the capability axis [Command R (08-2024)](/models/cohere__command-r-08-2024/) - Where this model appears [significance](/significance/) - Nearby on the capability axis [Qwen2.5 Coder 32B Instruct](/models/qwen__qwen-2.5-coder-32b-instruct/) - Where this model appears [cheapest-at](/cheapest-at/) - Where this model appears [subscription vs API](/plans/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![Phi 4 — Undominated.ai dominance verdict](https://undominated.ai/badge/microsoft__phi-4.svg)](https://undominated.ai/models/microsoft__phi-4/) HTML Copy Phi 4 — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/microsoft__phi-4.svg](https://undominated.ai/badge/microsoft__phi-4.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)