MODEL PROOF
Kimi K2.5
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
deal-only price: No offer passes the like-for-like test, so this price is a fallback: precision not disclosed. · precision not disclosed: The seller whose offer sets this price does not declare its serving precision. It is not read as full precision. · Serving precision differs between offers.
DeepSeek V4.1 Flash · Δ score 18.3 points · 81% lower measured price · $0.227 / 1M tokens
MiMo-V2.6-Pro is a further stored option with these losses: 236K → 131K max output
- Independent LMArena score
- 1,444.7 ± 3.26 · 73,661 votes
- Context window
- 262.14K
- Maximum output
- 235.93K
- Input modalities
- text, image
- Output modalities
- text
- Published input price
- $0.600 / 1M tokens
- Published output price
- $3.00 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Novita: no serving offer passes the like-for-like test, so this is a fallback. deal-only price precision not disclosed The seller whose offer sets this price does not declare its serving precision. It is not read as full precision.
Cheaper right now: $0.570 in · $2.85 out per million tokens at Novita, a promotion of 5%. The price on this page is Novita’s standard rate: the ranking uses the standard rate, never a promotion.
Every price dimension · USD per million tokens
| Input | $0.600/M |
|---|---|
| Output | $3.00/M |
| Cached input | $0.100/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.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.500/M from SiliconFlow.
3 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) |
|---|---|---|---|---|
| SiliconFlowsiliconflow/int4 Endpoint terms
| $0.500 | $2.50 | int4 | 99.08% |
| Novitanovita Endpoint terms
| $0.570 | $2.85 | undeclared | 100.00% |
| Amazon Bedrockamazon-bedrock/us-east-2 Endpoint terms
| $0.600 | $3.00 | undeclared | 100.00% |
Independent scores
| LMArena Elo | 1444.7thinking |
|---|---|
| LMArena row | kimi-k2.5-thinking |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- Godot games #8 1219
- Full-stack apps #33 1088
- Native Android apps #33 1103
- Web apps #35 1104
- Mobile apps #37 1139
- ASCII art #42 1151
- Websites #52 1236
- Code categories #56 1218
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 262K |
|---|---|
| Max output | 235K |
| Input modes | text, image |
| Tool use | yes |
| Reasoning | optional |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-11-22 |
| Quality data | verified |
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
Questions this page answers
What does Kimi K2.5 cost?
$0.600/M in, $3.00/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Kimi K2.5 have an independent quality score?
Kimi K2.5 has an LMArena score in this catalogue.
What beats Kimi K2.5?
DeepSeek V4.1 Flash has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for Kimi K2.5?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Is the cheapest Kimi K2.5 endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.500/M from SiliconFlow.
MODEL MONUMENT