Model comparison
Claude Haiku 4.5 vs Kimi K2.7 Code
Anthropic against Moonshot AI, compared on context, price, and verified benchmark results.
Catalog record checked August 19, 2026; individual provider fields may change.
Anthropic
Claude Haiku 4.5
Budget
Moonshot AI
Kimi K2.7 Code
Budget
| Specification | Claude Haiku 4.5 | Kimi K2.7 Code |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Tier | Budget | Budget |
| Context window | 200K | Winner: 262K |
| Max output | 64K | Not verified |
| Input / 1M tokens | $1 | Winner: $0.95 |
| Output / 1M tokens | $5 | Winner: $4 |
| Weights | Closed | Closed |
| Parameters | Not disclosed | Not disclosed |
| Reasoning levels | Not verified | Not verified |
| Modalities | text, image | text |
| Released | October 15, 2025 | July 22, 2026 |
| Artificial Analysis Intelligence Index (2026-08-14) | 24 | Winner: 43 |
Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Pricing tiers: Kimi K2.7 Code: Moonshot coding SKU `kimi-k2.7-code`: cache-hit input $0.19 / MTok, cache-miss $0.95 / MTok, output $4.00 / MTok. Highspeed sibling `kimi-k2.7-code-highspeed` is $1.90 / $8.00 (cache-hit $0.38) — not this row.
Claude Haiku 4.5
Anthropic's cheapest tier for high-volume classification and routine extraction.
Best for
- High-volume classification
- Routine extraction
- Cost-sensitive Anthropic stacks
Watch out
A generation behind the 5-series models it sits alongside in the lineup.
Kimi K2.7 Code
Moonshot's dedicated coding API identity — same $0.95/$4.00 miss/output band as Kimi K2.6, but a distinct product buyers pick for coding agents.
Best for
- Hosted coding agents
- Moonshot coding workloads
- Cost-sensitive code completion
Watch out
Not a drop-in for Kimi K3 or K2.6 general chat. Highspeed is a separate, higher-priced id. Do not invent open-weight status — this row is the hosted coding API.
Benchmark
DeepSWE 1.1 in context
Only Kimi K2.7 Code has a published DeepSWE 1.1 result. It is shown against the wider field, with cost per completed task alongside the score.
Local leader
Claude Opus 5 [max]
74%
Rows shown
24
Highest published reasoning effort per model (not best Pass@1)
Snapshot date
2026-08-13
Mirrored from deepswe.datacurve.ai
Better is toward the top-right (higher pass rate, lower cost). X-axis is reversed to match DeepSWE’s public chart. v1.1 uses average cost / tokens / steps; v1 uses published medians.
| # | Model | Pass@1 | Cost / task | Tokens / task | Steps / task |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 [max] | 74% | $11.84 | 118k | 99 |
| 2 | GPT-5.6 Sol [max] | 73% | $8.39 | 60k | 61 |
| 3 | Claude Fable 5 [max] | 70% | $21.63 | 119k | 88 |
| 4 | GPT-5.6 Terra [max] | 70% | $4.95 | 72k | 76 |
| 5 | Kimi K3 [max] | 69% | $4.65 | 82k | 98 |
| 6 | GPT-5.6 Luna [max] | 67% | $3.03 | 73k | 102 |
| 7 | GPT-5.5 [xhigh] | 67% | $7.23 | 46k | 82 |
| 8 | Grok 4.6 [xhigh] | 67% | $5.50 | 71k | 87 |
| 9 | Gemini 3.7 Flash [high] | 65% | $2.18 | 107k | 125 |
| 10 | DeepSeek V4-Pro [max] | 63% | $0.24 | 106k | 155 |
| 11 | Claude Opus 4.8 [max] | 59% | $13.22 | 135k | 120 |
| 12 | Qwen3.8-Max [xhigh] | 58% | $3.73 | 95k | 111 |
| 13 | Muse Spark 1.2 [xhigh] | 55% | $3.70 | 99k | 101 |
| 14 | Claude Sonnet 5 [max] | 54% | $26.40 | 214k | 268 |
| 15 | Grok 4.5 [high] | 54% | $2.42 | 36k | 61 |
| 16 | DeepSeek V4-Flash [max] | 53% | $0.10 | 108k | 153 |
| 17 | Muse Spark 1.1 [xhigh] | 53% | $2.36 | 74k | 96 |
| 18 | GPT-5.4 [xhigh] | 52% | $5.65 | 71k | 70 |
| 19 | Gemini 3.6 Flash [high] | 47% | $4.42 | 96k | 117 |
| 20 | GLM 5.2 [max] | 44% | $3.92 | 78k | 129 |
| 21 | Gemini 3.5 Flash [high] | 36% | $3.45 | 76k | 105 |
| 22 | Kimi K2.7 Code | 31% | $2.82 | 59k | 149 |
| 23 | Claude Sonnet 4.6 [high] | 30% | $5.52 | 76k | 134 |
| 24 | Gemini 3.1 Pro [high] | 12% | $2.14 | 28k | 76 |
DeepSWE “Best” picks the highest published reasoning effort per model (not the highest pass rate). Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.
When the cheaper one wins
Kimi K2.7 Code is cheaper on output at $4 per million tokens against $5 for Claude Haiku 4.5 — about 1.3×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.
Run the model pickerCommon questions
Claude Haiku 4.5 vs Kimi K2.7 Code
Answered from the verified figures on this page rather than general guidance.
Is Claude Haiku 4.5 or Kimi K2.7 Code cheaper for input?
Kimi K2.7 Code is cheaper at $0.95 per million input tokens, against $1 for Claude Haiku 4.5 — roughly 1.1× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Kimi K2.7 Code has tiered pricing: Moonshot coding SKU `kimi-k2.7-code`: cache-hit input $0.19 / MTok, cache-miss $0.95 / MTok, output $4.00 / MTok. Highspeed sibling `kimi-k2.7-code-highspeed` is $1.90 / $8.00 (cache-hit $0.38) — not this row.
Is Claude Haiku 4.5 or Kimi K2.7 Code cheaper for output?
Kimi K2.7 Code is cheaper at $4 per million output tokens, against $5 for Claude Haiku 4.5 — roughly 1.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Kimi K2.7 Code has tiered pricing: Moonshot coding SKU `kimi-k2.7-code`: cache-hit input $0.19 / MTok, cache-miss $0.95 / MTok, output $4.00 / MTok. Highspeed sibling `kimi-k2.7-code-highspeed` is $1.90 / $8.00 (cache-hit $0.38) — not this row.
Which has the larger context window, Claude Haiku 4.5 or Kimi K2.7 Code?
Kimi K2.7 Code accepts 262K tokens against 200K for Claude Haiku 4.5. This only matters if you routinely send very long documents or large codebases.
Should I use Claude Haiku 4.5 or Kimi K2.7 Code?
Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. Claude Haiku 4.5 suits high-volume classification; Kimi K2.7 Code suits hosted coding agents.
Next step
Choosing between them
Tier and workload decide this more reliably than a leaderboard position does.
If both sit in the same tier, the decision usually comes down to context window and output price rather than headline capability — output tokens dominate real bills.
If one is a step up within the same provider, the useful question is whether your hardest task actually fails on the cheaper tier. Most production volume — classification, extraction, summarization — does not.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Muse Code, or Lovable? Compare agentic harnesses · Latest releases.