The Known Good Updated 9 Sep 2026 Subscribe
Providers· Inference host· 13 tracked models

Morph — pricing & performance

Compare models All providers Data sources
Models served
13
of 1,111 tracked models
Mean output speed
412
tokens per second, averaged over
12 measured endpoints
Mean latency
2.4s
time to first token, averaged over
12 measured endpoints
Cheapest blended
$0.17
per 1M tokens at a 3:1
input:output blend
Output speed on Morph

Output tokens per second for the 12 of 13 models on Morph with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 13, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
4646
56
53
52
51
19
18
11
11
10
6
5
The Known Good
13 models on Morph
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.14 $0.28 $0.17 18 1.2s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.12 $0.35 $0.18 5 2.1s 1.05M
Google: Gemma 4 31B Google $0.14 $0.40 $0.20 11 7.4s 175k
MiniMax: MiniMax M3 MiniMax $0.26 $1.02 $0.45 10 6.4s 256k
MoonshotAI: Kimi K3 Moonshot AI $2.80 $14.00 $5.60 6 3.5s 1.05M
Morph: Morph V3 Fast morph $0.80 $1.20 $0.90 4,646 0.3s 82k
Morph: Morph V3 Large morph $0.90 $1.90 $1.15 11 0.2s 262k
Qwen: Qwen3.5 397B A17B Alibaba $0.50 $3.50 $1.25 52 0.7s 262k
Qwen: Qwen3.6 27B Alibaba $0.29 $2.40 $0.82 — — 131k
Qwen: Qwen3.8 27B Alibaba $0.29 $2.40 $0.82 53 1.2s 131k
Z.ai: GLM 5.2 Z.ai $0.84 $3.14 $1.42 19 2.5s 1.05M
Z.ai: GLM 5.3 Z.ai $1.25 $4.40 $2.04 56 1.1s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.39 $1.36 $0.63 51 2.4s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Morph are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.