TAO Synergies · Nasdaq: TAOX Powered by Bittensor
TAO-1
TAO-1 is a frontier-level AI system powered by Bittensor. It scored ahead of Kimi K3 on instruction following and coding in benchmarks re-run on Oct 19, 2026, at a fraction of the price. The API is open: get a key and start in two lines.
Updated
Price per million tokens
| Model | Input | Output |
|---|---|---|
TAO-1 tao-1 | $0.50 | $7.50 |
| Kimi K3 | $3.00 | $15.00 |
$0.50 / M input · $0.15 / M cached input · $7.50 / M output
TAO-1 and TAO-1 Best share this price; TAO-1 Fast costs $0.25 / M input, $0.075 / M cached input and $4.00 / M output. Kimi K3 at Moonshot AI's published price. OpenAI-compatible API.
How does TAO-1 compare with Kimi K3?
On three benchmarks re-run on Oct 19, 2026, TAO-1 scored ahead of Kimi K3. Both models ran on the same harness and were graded by the same grader.
| Benchmark | TAO-1 | Kimi K3 | Result |
|---|---|---|---|
| Instruction following | |||
| IFEval200 prompts, strict prompt-level scoring | 188/200 | 183/200 | Ahead |
| Coding | |||
| LiveCodeBench175 contest problems, one attempt each | 153/175 | 147/175 | Ahead |
| SWE-bench Verifiedall 500 real GitHub bug fixes | 427/500 | 408/500 | Ahead |
SWE-bench Verified: all 500 tasks, mini-swe-agent scaffold with a 100-step limit, official SWE-bench grader, run in batches across the day; TAO-1 leads by 3.8 points (95% interval +0.8 to +6.8). LiveCodeBench: the same 175 problems, one attempt each; two TAO-1 responses errored and 14 Kimi K3 responses hit the 32,000-token output limit, and these count as unsolved; TAO-1 leads by 3.4 points (95% interval -1.7 to +8.6, which includes zero). IFEval: the same 200 prompts as before, strict prompt-level scoring; TAO-1 leads by 2.5 points (95% interval -1.5 to +6.5, which includes zero); a repeat TAO-1 run scored 185/200. TAO-1 routes each request across several models: in the SWE-bench Verified run about 91% of TAO-1's model calls were served by DeepSeek V4.1 Flash and about 8% by Kimi K3. All three were run on Oct 19, 2026. More benchmarks will be added as they are re-run with full per-item results.