Kimi K3 vs Kimi K2.7 Code Highspeed vs GPT-5.4
Too close to call on our weighted score (Kimi K2.7 Code Highspeed 44, GPT-5.4 43, Kimi K3 43). The right pick depends on what you value most.
Moonshot AIKimi K3
43/100- ECI157.6
- Price$3.00 / $15.00
- Context1.05M
- Moonshot AI
Kimi K2.7 Code Highspeed
44/100- ECI—
- Price$1.90 / $8.00
- Context262K
OpenAIGPT-5.4
43/100- ECI156.9
- Price$2.50 / $15.00
- Context1.05M
Too close to call
It is close. Our weighted score puts them within a point (Kimi K2.7 Code Highspeed 44/100, GPT-5.4 43/100, Kimi K3 43/100), so choose by what matters most for your work: Kimi K2.7 Code Highspeed on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceKimi K2.7 Code HighspeedKimi K2.7 Code Highspeed $3.42 · GPT-5.4 $5.63 · Kimi K3 $6.00 per 1M tokens (3:1 blend)
- Longest contextGPT-5.4 and Kimi K3GPT-5.4 1,050,000 · Kimi K3 1,048,576 · Kimi K2.7 Code Highspeed 262,144 tokens
- Widest inputsSame inputsKimi K3: Text, Images, Video · Kimi K2.7 Code Highspeed: Text, Images, Video · GPT-5.4: Text, Images, PDFs
- Self-hostingKimi K3 and Kimi K2.7 Code HighspeedPublishes downloadable weights
| Measure | Weight | Kimi K3 | Kimi K2.7 Code Highspeed | GPT-5.4 |
|---|---|---|---|---|
| Price | 50% | 13 | 25 | 14 |
| Inputs & features | 30% | 80 | 80 | 80 |
| Context window | 20% | 61 | 37 | 61 |
| Overall | 100% | 43/100 | 44/100 | 43/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Kimi K3Moonshot AI | Kimi K2.7 Code HighspeedMoonshot AI | GPT-5.4OpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 157.6 (best) | — | 156.9 |
| ECI rank | #13 of 148 (best) | — | #16 of 148 |
| GPQA DiamondGraduate-level science questions | 93.1% | — | 93.3% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 72.2% | — | 78.6% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 97.2% | — | 97.8% (best) |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 76.9% |
| SimpleQA VerifiedShort factual questions | 50.6% (best) | — | 45.1% |
| Price per million tokens | |||
| Input | $3.00 | $1.90 (best) | $2.50 |
| Output | $15.00 | $8.00 (best) | $15.00 |
| Cached input | $0.30 | — | $0.25 (best) |
| Blended (3:1) | $6.00 | $3.42 (best) | $5.63 |
| Long-context rate | Same rate | Same rate | Over 272K: $5.00 / $22.50 |
| Price source | Official Moonshot AI API | Median of 11 providers | Official OpenAI API |
| Limits | |||
| Context window | 1,048,576 tokens | 262,144 tokens | 1,050,000 tokens (best) |
| Max output | 131,072 tokens | 262,144 tokens (best) | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | Yes | Yes | No |
| Reasoning | Yeslow · high · max | Yes | Yeslow · medium · high · xhigh |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | kimi-k3 | — | gpt-5.4 |
| API providers | 68 (best) | 11 | 36 |
| Released | Jul 16, 2026 | Jun 12, 2026 | Mar 5, 2026 |
| Knowledge cutoff | — | Jan 2025 | Aug 31, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Kimi K3$60.00
- Kimi K2.7 Code Highspeed$35.00
- GPT-5.4$55.00
Which should you choose?
Which is better: Kimi K3, Kimi K2.7 Code Highspeed or GPT-5.4?
It is close. Our weighted score puts them within a point (Kimi K2.7 Code Highspeed 44/100, GPT-5.4 43/100, Kimi K3 43/100), so choose by what matters most for your work: Kimi K2.7 Code Highspeed on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Kimi K3, Kimi K2.7 Code Highspeed or GPT-5.4?
Kimi K2.7 Code Highspeed is cheaper at $1.90 input / $8.00 output per million tokens (median across 11 API providers). GPT-5.4 costs $2.50 input / $15.00 output per million tokens (official OpenAI API price); Kimi K3 costs $3.00 input / $15.00 output per million tokens (official Moonshot AI API price). At a typical mix of three input tokens to one output token, that is $3.42 per million tokens for Kimi K2.7 Code Highspeed versus $5.63 for GPT-5.4 (1.6× as much) and $6.00 for Kimi K3 (1.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Kimi K3 has an ECI of 157.6, Kimi K2.7 Code Highspeed has not been scored yet and GPT-5.4 has an ECI of 156.9.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K3 and Kimi K2.7 Code Highspeed yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
GPT-5.4 and Kimi K3 have the largest context windows (1,050,000 and 1,048,576 tokens), against 262,144 for Kimi K2.7 Code Highspeed. Maximum output per response: Kimi K3 up to 131,072, Kimi K2.7 Code Highspeed up to 262,144, GPT-5.4 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Kimi K3 accepts text, images and video; Kimi K2.7 Code Highspeed accepts text, images and video; GPT-5.4 accepts text, images and PDFs. They handle the same number of input types.
Are any of these open source?
Kimi K3 and Kimi K2.7 Code Highspeed publishes its weights and can be self-hosted; GPT-5.4 is proprietary.
Which is newer?
Kimi K3 is the newest, released Jul 16, 2026. Kimi K2.7 Code Highspeed came out Jun 12, 2026; GPT-5.4 came out Mar 5, 2026. Knowledge cutoff: Kimi K2.7 Code Highspeed Jan 2025, GPT-5.4 Aug 31, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
