Answer: Kiro offers a range of models including GPT-5.6 (Sol, Terra, Luna), Claude models (Fable 5.1, Opus 5.5 through 4.5, Sonnet 5.5 through 4.0, Haiku 5.5 and 4.5), Auto, Grok 4.7, Kimi K3, DeepSeek 3.2, MiniMax M2.5 and M2.1, GLM-5, and Qwen3 Coder Next. They compare by context window, cost relative to Auto (1.0x baseline), and available regions, with costs ranging from 0.05x for Qwen3 Coder Next to 6x for Claude Fable 5.1. Status: Check failed Entry: tool/kiro/models/available-models-comparison Revision: 2 Digest: sha256:7f5383674cb192af (changes whenever the content changes) Timeline: Created: 2026-11-13T03:43:51Z Last changed: 2026-11-18T13:25:49Z Last verified: 2026-11-19T13:22:17Z Last attempt: 2026-11-20T13:31:03Z (failed) Next check: 2026-11-20T14:31:03Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Unit | Source | As of GPT-5.6 Sol cost | 4.4x* | x Auto baseline | [1] | 2026-11-19 Claude Fable 5.1 cost | 6x | x Auto baseline | [1] | 2026-11-19 Claude Haiku 5.5 cost | 0.06x* | x Auto baseline | [1] | 2026-11-19 Qwen3 Coder Next cost | 0.05x | x Auto baseline | [1] | 2026-11-19 Claude Opus 4.5 context | 200K | tokens | [1] | 2026-11-19 DeepSeek 3.2 context | 128K | tokens | [1] | 2026-11-19 Auto cost baseline | 1.0x | x Auto baseline | [1] | 2026-11-19 Sources: [1] Amazon Web Services. "Models - Docs - Kiro". https://kiro.dev/docs/models/ Role: primary. Accessed: 2026-11-19T13:22:17Z Quote: "GPT-5.6 Sol 1M 4.4x* US, EU" (Supports: GPT-5.6 Sol cost) Quote: "Claude Fable 5.1 † 1M 6x US East only" (Supports: Claude Fable 5.1 cost) Quote: "Claude Haiku 5.5 1M 0.06x* US, EU" (Supports: Claude Haiku 5.5 cost) Quote: "Qwen3 Coder Next 256K 0.05x US, EU" (Supports: Qwen3 Coder Next cost) Quote: "Claude Opus 4.5 200K 2.2x US, EU" (Supports: Claude Opus 4.5 context) Quote: "DeepSeek 3.2 128K 0.25x US" (Supports: DeepSeek 3.2 context) Quote: "Cost is relative to Auto (1.0x baseline)." (Supports: Auto cost baseline) Published: 2026-11-19T00:21:04Z Snapshot SHA-256: 9431acfc3eb290a786731c8fd099490437b37e08dfec75c25d9e13fbca8266cb (captured 2026-11-19T13:22:18Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-17T13:53:49Z, so the values verified then were kept. Cross-check: not-available at 2026-11-19T13:22:17Z. No independent second source is configured for this entry Last successful check: 2026-11-19T13:22:17Z Last attempt: 2026-11-20T13:31:03Z (failed) Notes and limitations: Extracted automatically from a single official source (section "Quick comparison"). Related: https://latestn.com/tool/kiro/models/available-models-list Which models are available in Kiro? https://latestn.com/tool/kiro/models/choose-fallback-model How do I choose a fallback model for the Kiro web agent? https://latestn.com/tool/kiro/models/choose-models-per-step How do I choose models, providers, and reasoning effort per step in a Kiro workflow? https://latestn.com/tool/kiro/memory-and-context/trigger-compaction How do I trigger compaction in Kiro? https://latestn.com/tool/kiro/memory-and-context/view-context-usage How do I view my current context usage in Kiro CLI? https://latestn.com/tool/kiro/models/auto-model-recommended What is Kiro's Auto model and why is it recommended? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T13:31:03Z | check-failed | Extraction did not pass verification: answer does not contain any extracted value | — 2026-11-18T13:25:49Z | changed | Auto cost baseline: — → 1.0x | [1] 2026-11-18T13:25:49Z | changed | GPT-5.6 Sol cost: — → 4.4x* | [1] 2026-11-18T13:25:49Z | changed | Grok 4.7 context: 500K → — | [1] 2026-11-18T13:25:49Z | changed | Auto baseline: 1.0x → — | [1] 2026-11-18T13:25:49Z | changed | GPT-5.6 Sol context: 1M → — | [1] 2026-11-13T03:43:51Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/kiro/models/available-models-comparison/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/kiro/models/available-models-comparison POST: https://latestn.com/dispute/tool/kiro/models/available-models-comparison with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/kiro/models/available-models-comparison?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). Which models are available in Kiro and how do they compare? Revision 2, last verified 2026-11-19T13:22:17Z. https://latestn.com/tool/kiro/models/available-models-comparison (accessed 2026-11-21T10:00:45Z). @misc{LatestN_tool_kiro_models_available_models_comparison_r2, title = {Which models are available in Kiro and how do they compare?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/kiro/models/available-models-comparison}}, note = {Revision 2; digest sha256:7f5383674cb192af; last verified 2026-11-19T13:22:17Z; accessed 2026-11-21T10:00:45Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/kiro/models/available-models-comparison