Side-by-side comparison · models
Kimi K2.7 Code Highspeed vs Kimi K3
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Kimi K2.7 Code Highspeed
Lower-latency Kimi Code variant for interactive edits and coding-agent loops.
Models
Kimi K3
Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI.
Checked facts
Line by line
| Measure | Kimi K2.7 Code Highspeed | Kimi K3 |
|---|---|---|
| Input price | Not checked yet | $0.192 per million tokens |
| Output price | Not checked yet | $15.00 per million tokens |
| Price on akashml | Not checked yet | $1.20 per million cached input tokens |
| Price on akashml | Not checked yet | $1.20 per million input tokens |
| Price on akashml | Not checked yet | $14.00 per million output tokens |
| Price on amazon-bedrock | Not checked yet | $0.300 per million cached input tokens |
| Price on amazon-bedrock | Not checked yet | $3.00 per million input tokens |
| Price on amazon-bedrock | Not checked yet | $15.00 per million output tokens |
| Price on baseten | Not checked yet | $0.300 per million cached input tokens |
| Price on baseten | Not checked yet | $3.00 per million input tokens |
| Price on baseten | Not checked yet | $15.00 per million output tokens |
| Price on chutes | Not checked yet | $0.185 per million cached input tokens |
| Price on chutes | Not checked yet | $1.85 per million input tokens |
| Price on chutes | Not checked yet | $9.50 per million output tokens |
| Price on decart | Not checked yet | $0.195 per million cached input tokens |
| Price on decart | Not checked yet | $1.95 per million input tokens |
| Price on decart | Not checked yet | $9.75 per million output tokens |
| Price on deepinfra | Not checked yet | $0.285 per million cached input tokens |
| Price on deepinfra | Not checked yet | $2.85 per million input tokens |
| Price on deepinfra | Not checked yet | $14.25 per million output tokens |
| Price on digitalocean | Not checked yet | $0.255 per million cached input tokens |
| Price on digitalocean | Not checked yet | $2.55 per million input tokens |
| Price on digitalocean | Not checked yet | $12.95 per million output tokens |
| Price on fireworks | Not checked yet | $0.210 per million cached input tokens |
| Price on fireworks | Not checked yet | $2.10 per million input tokens |
| Price on fireworks | Not checked yet | $10.50 per million output tokens |
| Price on inference-net | Not checked yet | $0.195 per million cached input tokens |
| Price on inference-net | Not checked yet | $0.234 per million input tokens |
| Price on inference-net | Not checked yet | $15.00 per million output tokens |
| Price on makora | Not checked yet | $0.200 per million cached input tokens |
| Price on makora | Not checked yet | $0.500 per million input tokens |
| Price on makora | Not checked yet | $13.00 per million output tokens |
| Price on modal | Not checked yet | $0.300 per million cached input tokens |
| Price on modal | Not checked yet | $3.00 per million input tokens |
| Price on modal | Not checked yet | $15.00 per million output tokens |
| Price on moonshotai | Not checked yet | $0.300 per million cached input tokens |
| Price on moonshotai | Not checked yet | $3.00 per million input tokens |
| Price on moonshotai | Not checked yet | $15.00 per million output tokens |
| Price on morph | Not checked yet | $0.360 per million cached input tokens |
| Price on morph | Not checked yet | $1.28 per million input tokens |
| Price on morph | Not checked yet | $12.00 per million output tokens |
| Price on parasail | Not checked yet | $0.300 per million cached input tokens |
| Price on parasail | Not checked yet | $3.00 per million input tokens |
| Price on parasail | Not checked yet | $15.00 per million output tokens |
| Price on pareto-alpha | Not checked yet | $0.300 per million cached input tokens |
| Price on pareto-alpha | Not checked yet | $3.00 per million input tokens |
| Price on pareto-alpha | Not checked yet | $15.00 per million output tokens |
| Price on phala | Not checked yet | $0.255 per million cached input tokens |
| Price on phala | Not checked yet | $2.55 per million input tokens |
| Price on phala | Not checked yet | $12.75 per million output tokens |
| Price on qwen | Not checked yet | $0.345 per million cached input tokens |
| Price on qwen | Not checked yet | $3.45 per million input tokens |
| Latest version | Not checked yet | moonshotai/kimi-k3-20260715 |
| Time to first token (ms) | 1,870 | 3,300 |
| Output speed (tokens a second) | 54 | 52.4 |
| Time to first token (ms) on akashml | Not checked yet | 854 |
| Time to first token (ms) on amazon-bedrock | Not checked yet | 3,087 |
| Time to first token (ms) on baseten | Not checked yet | 3,657 |
| Time to first token (ms) on chutes | Not checked yet | 2,935 |
| Time to first token (ms) on decart | Not checked yet | 1,167 |
| Time to first token (ms) on deepinfra | Not checked yet | 1,803 |
| Time to first token (ms) on digitalocean | Not checked yet | 1,521 |
| Time to first token (ms) on fireworks | Not checked yet | 1,205 |
| Time to first token (ms) on inference-net | Not checked yet | 889 |
| Time to first token (ms) on makora | Not checked yet | 1,190 |
| Time to first token (ms) on modal | Not checked yet | 1,031 |
| Time to first token (ms) on moonshotai | Not checked yet | 9,469 |
| Time to first token (ms) on morph | Not checked yet | 1,429 |
| Time to first token (ms) on parasail | Not checked yet | 1,144 |
| Time to first token (ms) on pareto-alpha | Not checked yet | 6,303 |
| Time to first token (ms) on phala | Not checked yet | 4,689 |
| Time to first token (ms) on qwen | Not checked yet | 1,980 |
| Time to first token (ms) on relace | Not checked yet | 1,396 |
| Time to first token (ms) on sail-research | Not checked yet | 1,638 |
| Time to first token (ms) on together | Not checked yet | 2,467 |
| Time to first token (ms) on wafer | Not checked yet | 585 |
| Output speed (tokens a second) on akashml | Not checked yet | 51 |
| Output speed (tokens a second) on amazon-bedrock | Not checked yet | 58 |
| Output speed (tokens a second) on baseten | Not checked yet | 42.5 |
| Output speed (tokens a second) on chutes | Not checked yet | 15 |
| Output speed (tokens a second) on decart | Not checked yet | 57 |
| Output speed (tokens a second) on deepinfra | Not checked yet | 30 |
| Output speed (tokens a second) on digitalocean | Not checked yet | 35 |
| Output speed (tokens a second) on fireworks | Not checked yet | 61 |
| Output speed (tokens a second) on inference-net | Not checked yet | 68 |
| Output speed (tokens a second) on makora | Not checked yet | 58 |
| Output speed (tokens a second) on modal | Not checked yet | 71 |
| Output speed (tokens a second) on moonshotai | Not checked yet | 28 |
| Output speed (tokens a second) on morph | Not checked yet | 60 |
| Output speed (tokens a second) on parasail | Not checked yet | 48 |
| Output speed (tokens a second) on pareto-alpha | Not checked yet | 6 |
| Output speed (tokens a second) on phala | Not checked yet | 28 |
| Output speed (tokens a second) on qwen | Not checked yet | 37 |
| Tokens served on OpenRouter in a day | Not checked yet | 189.8B (for 31 Oct 2026) |
| Tool calls on OpenRouter in a day | Not checked yet | 2.1M (for 31 Oct 2026) |
| Artificial Analysis Intelligence Index | Not checked yet | 17.4 |
| Artificial Analysis Coding Index | Not checked yet | 76.2 |
| Artificial Analysis Agentic Index | Not checked yet | 50 |
| LMArena text rating (Elo) | Not checked yet | 1,476 |
| LMArena web development rating (Elo) | Not checked yet | 1,656 |
| Design Arena rating (Elo) | Not checked yet | 1,381 |
| Gpqa diamond | Not checked yet | 93.1% (for 16 July 2026) |
| Frontiermath tiers 1 3 v2 private | Not checked yet | 72.2% (for 16 July 2026) |
| Simpleqa verified | Not checked yet | 50.6% (for 16 July 2026) |
| Arc agi 2 | Not checked yet | 60.4% (for 16 July 2026) |
| Apex agents | Not checked yet | 47.8% (for 16 July 2026) |
| Arc agi | Not checked yet | 94.5% (for 16 July 2026) |
| Chess puzzles | Not checked yet | 37% (for 16 July 2026) |
| Dtbench | Not checked yet | 91.2% (for 16 July 2026) |
| Frontiercode | Not checked yet | 44.2% (for 16 July 2026) |
| Frontiermath tier 4 v2 private | Not checked yet | 39% (for 16 July 2026) |
| Frontierswe | Not checked yet | 25.9% (for 16 July 2026) |
| Furniture assembly | Not checked yet | 34.2% (for 16 July 2026) |
| Lmca | Not checked yet | 52.7% (for 16 July 2026) |
| Mystery game puzzles | Not checked yet | 26% (for 16 July 2026) |
| Posttrainbench | Not checked yet | 32% (for 16 July 2026) |
| Proofbench | Not checked yet | 87% (for 16 July 2026) |
| Simplebench | Not checked yet | 60.7% (for 16 July 2026) |
| Surface evolver bench | Not checked yet | 95% (for 16 July 2026) |
| Weirdml | Not checked yet | 82.6% (for 16 July 2026) |
| Weirdml v3 | Not checked yet | 15.4% (for 16 July 2026) |
| Otis mock aime 2024 2025 | Not checked yet | 97.2% (saturated benchmark: the top models all score near the ceiling) (for 16 July 2026) |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.