AI models comparison
Kimi K2 vs Step 3.5 Flash
Prices, documented capabilities and limits from dated official sources, side by side. Unknowns remain unknown; different billing units do not establish a cost winner.
Latest evidence check Nov 10, 2026
Who it is forMoonshot AI describes Kimi K2 as a mixture-of-experts language model with 1 trillion total and 32 billion activated parameters.
Latest evidence check Nov 11, 2026
Who it is forStep 3.5 Flash is an open-source foundation model aimed at reasoning and agentic tasks, built as a sparse Mixture of Experts that activates 11B of its 196B parameters per token.
What the evidence answers
A reading of reviewed official documentation for Kimi K2 and Step 3.5 Flash. It is not a hands-on test, a ranking or a recommendation of one product.
- Common buyer questions answered
- 3 requirements
- Documented for one
- 1 requirement
- Not verified for either
- 4 requirements
- Prices
- Not like-for-like yet
Price
Kimi K2
Free plan · paid prices not verified ·
- Self-hosted open weights: no subscription charge ·
Step 3.5 Flash
Free plan · paid prices not verified ·
- Self-hosted: no subscription charge ·
A complete like-for-like price comparison is not established; the next steps say what is missing.
Common buyer questions answered
Even when labels match, check each source for differences in plans, units and scope.
- API model identifier
- Kimi K2 Kimi-K2-Instruct
- Step 3.5 Flash step-3.5-flash
- Context window
- Kimi K2 128K tokens in the context window
- Step 3.5 Flash 256K tokens in the context window
- Availability
- Kimi K2 Block-fp8 checkpoints of Kimi-K2-Instruct are published on Hugging Face.
- Step 3.5 Flash Local inference is documented with vLLM, SGLang, Hugging Face Transformers and llama.cpp.
Limits to check
- Kimi K2 The project identifies a Modified MIT License for code and model weights.
- Step 3.5 Flash The README says Step 3.5 Flash is tailored for coding and work-centric tasks and may be less stable in specialized domains or long multi-turn dialogues, with repetitive reasoning or mixed-language outputs.
- Step 3.5 Flash The llama.cpp guide lists int4 GGUF weights of 111.5 GB, about 7 GB of runtime overhead and a minimum of 120 GB VRAM, with 128 GB of unified memory recommended.
Not verified yet
No reviewed evidence for either product on modalities, maximum output, input token rate and output token rate.
Documented for one product only, shown in the table below: Kimi K2: provider.
Not verified means our reviewed sources do not establish it. It does not mean a product lacks the capability or that it costs nothing.
Side-by-side evidence
Documented values with their sources and check dates; requirements the sources do not establish stay marked.
- Documented as supported
- Documented as unsupported
- Not verified Sources do not establish it
- Not applicable
| Requirement | Kimi K2 | Step 3.5 Flash |
|---|---|---|
| Pricing | Free plan · paid prices not verified | Free plan · paid prices not verified |
| Who it is for | Moonshot AI describes Kimi K2 as a mixture-of-experts language model with 1 trillion total and 32 billion activated parameters. Verified Nov 4, 2026 · Kimi K2: kimi-source | Step 3.5 Flash is an open-source foundation model aimed at reasoning and agentic tasks, built as a sparse Mixture of Experts that activates 11B of its 196B parameters per token. Verified Nov 8, 2026 · Step 3.5 Flash: step-3-5-flash-project |
| Coverage limits | The project identifies a Modified MIT License for code and model weights. Verified Nov 4, 2026 · Kimi K2: kimi-source | The README says Step 3.5 Flash is tailored for coding and work-centric tasks and may be less stable in specialized domains or long multi-turn dialogues, with repetitive reasoning or mixed-language outputs. Verified Nov 8, 2026 · Step 3.5 Flash: step-3-5-flash-project
|
| Provider | Moonshot AI Publisher repository README at the pinned commit, captured on 9 November 2026; supplier description, not a deployment or independent test. The README links the publisher homepage under the name Moonshot AI; no hosted service or account was used. Verified Nov 10, 2026 · Kimi K2: kimi-k2-project | Not verified |
| API model identifier | Kimi-K2-Instruct Verified Nov 4, 2026 · Kimi K2: kimi-source | step-3.5-flash Dated publisher project README captured on 9 November 2026 (commit 21d85a5f); supplier description, not a deployment or independent test. API model ID used in the README's agent-platform guides; OpenRouter uses stepfun/step-3.5-flash. Verified Nov 11, 2026 · Step 3.5 Flash: step-3-5-flash-project |
| Context window | 128K tokens in the context window Publisher repository README at the pinned commit, captured on 9 November 2026; supplier description, not a deployment or independent test. Context length from the README model summary table, which describes the model architecture; a hosted service may apply other limits. No model inference, API call, account, benchmark or performance test was performed. Verified Nov 10, 2026 · Kimi K2: kimi-k2-project | 256K tokens in the context window Dated publisher project README captured on 9 November 2026 (commit 21d85a5f); supplier description, not a deployment or independent test. Supplier statement of the supported context window; no long-context test was run. Verified Nov 11, 2026 · Step 3.5 Flash: step-3-5-flash-project |
| Availability | Block-fp8 checkpoints of Kimi-K2-Instruct are published on Hugging Face. Publisher repository README at the pinned commit, captured on 9 November 2026; supplier description, not a deployment or independent test. Checkpoint availability only. The README also points to a hosted API at platform.moonshot.ai; that service, its current model lineup, prices and terms were not verified here. No model inference, API call, account, benchmark or performance test was performed. Verified Nov 10, 2026 · Kimi K2: kimi-k2-project | Local inference is documented with vLLM, SGLang, Hugging Face Transformers and llama.cpp. Dated publisher project README captured on 9 November 2026 (commit 21d85a5f); supplier description, not a deployment or independent test. Documentation of local backends, not a performance claim or a hosted-service entitlement; cloud API access through OpenRouter and the StepFun platform is described separately. Verified Nov 11, 2026 · Step 3.5 Flash: step-3-5-flash-project |
| Coverage note | Publisher repository README at the captured revision, 4 November 2026. A named variant is evidence within the model family, not a separate product. No model inference, API call, account, benchmark or performance test. Current availability and terms require separate review. | Dated publisher project README captured on 7 November 2026; supplier description, not a deployment or independent test. Infrastructure, accounts, third-party services and managed offerings have separate costs and terms. |
4 requirements without reviewed evidence here
Not verified means the reviewed sources do not establish it; it does not mean a product lacks it or that it costs nothing.
- Modalities Kimi K2: not verified · Step 3.5 Flash: not verified
- Maximum output Kimi K2: not verified · Step 3.5 Flash: not verified
- Input token rate Kimi K2: not verified · Step 3.5 Flash: not verified
- Output token rate Kimi K2: not verified · Step 3.5 Flash: not verified
Next steps
- Confirm Kimi K2's paid plan prices, billing term and taxes on its official pricing page; only its free plan is verified here.
- Confirm Step 3.5 Flash's paid plan prices, billing term and taxes on its official pricing page; only its free plan is verified here.
- Ask Kimi K2 about modalities, maximum output and input token rate; our sources do not establish them yet.
- Ask Step 3.5 Flash about modalities, maximum output and input token rate; our sources do not establish them yet.
- Kimi K2Visit Kimi K2Profile and plans
- Step 3.5 FlashVisit Step 3.5 FlashProfile and plans
Commissions never change costs, eligibility or rankings.