Models / voxtral_realtime

Voxtral-Mini-4B-Realtime-2602: GPU memory to fine-tune

Fine-tuning Voxtral-Mini-4B-Realtime-2602 at batch 1 and 2048 tokens takes about 85.3 GB of GPU memory for a full fine-tune (fits one H200 141 GB), and 16.1 GB with LoRA r=16 on a bf16 base (borderline on one L4 24 GB). Estimated from the model's structure, for the towers the graph reconstructs, not measured. What fits on which card.

Reconstructed from its own config.json with no weights read. 2.2M downloads on Hugging Face.

Our count against the checkpoint

The left number comes from the graph. The right one is the number of scalars in the published weight files. Nothing on this page was tuned to make them agree.

Derived from structure

4.06B

4,062,699,776 parameters

In the published checkpoint

4.43B

4,429,679,360 scalars · safetensors.total, read 2026-09-06

Delta

-8.28%

multi-tower The config declares 2 sub-models (audio_config, text_config). The published checkpoint carries all of them; the graph below carries the towers the reader reconstructs. A gap here is a statement about what we read, not about the checkpoint.

What it costs to run

Cost is a roofline estimate on the priced GPU for 10 epochs at batch 32, 2048 tokens over 50,000 samples (assumed; no dataset attached).

Layers

290

Will it forward-pass

Yes

Priced on

A10G (24GB)

Est. one run

$285.24

Memory: what fits on which card

Largest batch per card. Training is sized at 2048 tokens per sample, serving at 4096 tokens per sequence.

Full fine-tune, batch 1 at 2048 tokens

85.3 GB

LoRA r=16, batch 1 at 2048 tokens

16.1 GB

Serve: bf16 weights

8.13 GB

Serve: KV cache, 4096 tokens

1.11 GB

Card	Full fine-tune	LoRA r=16	Serve bf16, 4096 tokens
T4 16 GB	does not fit at batch 1	does not fit at batch 1	batch 5
L4 24 GB	does not fit at batch 1	batch 1, borderline	batch 11
A100 40 GB	does not fit at batch 1	batch 3	batch 24
A100 / H100 80 GB	2 cards at batch 1 (252 + 38 layers)	batch 8	batch 55
H200 141 GB	batch 6	batch 15	batch 103

Training: 2048 tokens per sample (2048, or the model's context when shorter; the structure table is at the config's maximum, 131072), AdamW with bf16 autocast, SDPA attention (no score matrix stored), 1.15x headroom on every card. Full fine-tune holds weights, gradients and optimizer state (1.2 x 16 bytes per parameter) plus activations. LoRA is r=16 on every linear layer but the head, base frozen in bf16 (2 bytes per parameter), adapters at full AdamW state, same activations. A two-card split is a contiguous layer cut (pipeline parallel), computed only where one card cannot hold batch 1. "Borderline" means the card holds batch 1 on the estimate but not on the conservative peak (the estimate x 1.43, at or above the measured peak on 95% of held-out runs): measure one step before reserving it. Serving: bf16 weights plus the KV cache of 4096 tokens per sequence; prefill working set, CUDA context and framework reserve not counted.

These are estimates from the graph, not measurements. Against measured runs, held out by architecture, the estimate flagged 113 of the 131 jobs that did not fit their card and said "fits" on the other 18. Every measured run.

Structure

293 nodes. Output shapes are propagated from the input shape, batch dimension excluded, at 131072 tokens: the config's maximum context, not the 2048 the memory above is sized at.

	Layer	Type	Output shape
1	Input	Input	1 × 131072
2	Embedding	Embedding	1 × 131072 × 3072
3	RoPE	RoPE	1 × 131072 × 3072
4	Audio input	Input	1 × 128 × 1
5	Audio feature embed	Projection	1 × 128 × 1280
6	Audio_LN_1	LayerNorm	1 × 128 × 1280
7	Audio_Attn_1	Multi-Head Attention	1 × 128 × 1280
8	Audio_Add_1	Add	1 × 128 × 1280
9	Audio_FFN_1	Feed Forward	1 × 128 × 1280
10	Audio_LN_2	LayerNorm	1 × 128 × 1280
11	Audio_Attn_2	Multi-Head Attention	1 × 128 × 1280
12	Audio_Add_2	Add	1 × 128 × 1280
13	Audio_FFN_2	Feed Forward	1 × 128 × 1280
14	Audio_LN_3	LayerNorm	1 × 128 × 1280
15	Audio_Attn_3	Multi-Head Attention	1 × 128 × 1280
16	Audio_Add_3	Add	1 × 128 × 1280
17	Audio_FFN_3	Feed Forward	1 × 128 × 1280
18	Audio_LN_4	LayerNorm	1 × 128 × 1280
19	Audio_Attn_4	Multi-Head Attention	1 × 128 × 1280
20	Audio_Add_4	Add	1 × 128 × 1280
21	Audio_FFN_4	Feed Forward	1 × 128 × 1280
22	Audio_LN_5	LayerNorm	1 × 128 × 1280
23	Audio_Attn_5	Multi-Head Attention	1 × 128 × 1280
24	Audio_Add_5	Add	1 × 128 × 1280
25	Audio_FFN_5	Feed Forward	1 × 128 × 1280
26	Audio_LN_6	LayerNorm	1 × 128 × 1280
27	Audio_Attn_6	Multi-Head Attention	1 × 128 × 1280
28	Audio_Add_6	Add	1 × 128 × 1280
29	Audio_FFN_6	Feed Forward	1 × 128 × 1280
30	Audio_LN_7	LayerNorm	1 × 128 × 1280
31	Audio_Attn_7	Multi-Head Attention	1 × 128 × 1280
32	Audio_Add_7	Add	1 × 128 × 1280
33	Audio_FFN_7	Feed Forward	1 × 128 × 1280
34	Audio_LN_8	LayerNorm	1 × 128 × 1280
35	Audio_Attn_8	Multi-Head Attention	1 × 128 × 1280
36	Audio_Add_8	Add	1 × 128 × 1280
37	Audio_FFN_8	Feed Forward	1 × 128 × 1280
38	Audio_LN_9	LayerNorm	1 × 128 × 1280
39	Audio_Attn_9	Multi-Head Attention	1 × 128 × 1280
40	Audio_Add_9	Add	1 × 128 × 1280
41	Audio_FFN_9	Feed Forward	1 × 128 × 1280
42	Audio_LN_10	LayerNorm	1 × 128 × 1280
43	Audio_Attn_10	Multi-Head Attention	1 × 128 × 1280
44	Audio_Add_10	Add	1 × 128 × 1280
45	Audio_FFN_10	Feed Forward	1 × 128 × 1280
46	Audio_LN_11	LayerNorm	1 × 128 × 1280
47	Audio_Attn_11	Multi-Head Attention	1 × 128 × 1280
48	Audio_Add_11	Add	1 × 128 × 1280
49	Audio_FFN_11	Feed Forward	1 × 128 × 1280
50	Audio_LN_12	LayerNorm	1 × 128 × 1280
51	Audio_Attn_12	Multi-Head Attention	1 × 128 × 1280
52	Audio_Add_12	Add	1 × 128 × 1280
53	Audio_FFN_12	Feed Forward	1 × 128 × 1280
54	Audio_LN_13	LayerNorm	1 × 128 × 1280
55	Audio_Attn_13	Multi-Head Attention	1 × 128 × 1280
56	Audio_Add_13	Add	1 × 128 × 1280
57	Audio_FFN_13	Feed Forward	1 × 128 × 1280
58	Audio_LN_14	LayerNorm	1 × 128 × 1280
59	Audio_Attn_14	Multi-Head Attention	1 × 128 × 1280
60	Audio_Add_14	Add	1 × 128 × 1280
61	Audio_FFN_14	Feed Forward	1 × 128 × 1280
62	Audio_LN_15	LayerNorm	1 × 128 × 1280
63	Audio_Attn_15	Multi-Head Attention	1 × 128 × 1280
64	Audio_Add_15	Add	1 × 128 × 1280
65	Audio_FFN_15	Feed Forward	1 × 128 × 1280
66	Audio_LN_16	LayerNorm	1 × 128 × 1280
67	Audio_Attn_16	Multi-Head Attention	1 × 128 × 1280
68	Audio_Add_16	Add	1 × 128 × 1280
69	Audio_FFN_16	Feed Forward	1 × 128 × 1280
70	Audio_LN_17	LayerNorm	1 × 128 × 1280
71	Audio_Attn_17	Multi-Head Attention	1 × 128 × 1280
72	Audio_Add_17	Add	1 × 128 × 1280
73	Audio_FFN_17	Feed Forward	1 × 128 × 1280
74	Audio_LN_18	LayerNorm	1 × 128 × 1280
75	Audio_Attn_18	Multi-Head Attention	1 × 128 × 1280
76	Audio_Add_18	Add	1 × 128 × 1280
77	Audio_FFN_18	Feed Forward	1 × 128 × 1280
78	Audio_LN_19	LayerNorm	1 × 128 × 1280
79	Audio_Attn_19	Multi-Head Attention	1 × 128 × 1280
80	Audio_Add_19	Add	1 × 128 × 1280
81	Audio_FFN_19	Feed Forward	1 × 128 × 1280
82	Audio_LN_20	LayerNorm	1 × 128 × 1280
83	Audio_Attn_20	Multi-Head Attention	1 × 128 × 1280
84	Audio_Add_20	Add	1 × 128 × 1280
85	Audio_FFN_20	Feed Forward	1 × 128 × 1280
86	Audio_LN_21	LayerNorm	1 × 128 × 1280
87	Audio_Attn_21	Multi-Head Attention	1 × 128 × 1280
88	Audio_Add_21	Add	1 × 128 × 1280
89	Audio_FFN_21	Feed Forward	1 × 128 × 1280
90	Audio_LN_22	LayerNorm	1 × 128 × 1280
91	Audio_Attn_22	Multi-Head Attention	1 × 128 × 1280
92	Audio_Add_22	Add	1 × 128 × 1280
93	Audio_FFN_22	Feed Forward	1 × 128 × 1280
94	Audio_LN_23	LayerNorm	1 × 128 × 1280
95	Audio_Attn_23	Multi-Head Attention	1 × 128 × 1280
96	Audio_Add_23	Add	1 × 128 × 1280
97	Audio_FFN_23	Feed Forward	1 × 128 × 1280
98	Audio_LN_24	LayerNorm	1 × 128 × 1280
99	Audio_Attn_24	Multi-Head Attention	1 × 128 × 1280
100	Audio_Add_24	Add	1 × 128 × 1280
101	Audio_FFN_24	Feed Forward	1 × 128 × 1280
102	Audio_LN_25	LayerNorm	1 × 128 × 1280
103	Audio_Attn_25	Multi-Head Attention	1 × 128 × 1280
104	Audio_Add_25	Add	1 × 128 × 1280
105	Audio_FFN_25	Feed Forward	1 × 128 × 1280
106	Audio_LN_26	LayerNorm	1 × 128 × 1280
107	Audio_Attn_26	Multi-Head Attention	1 × 128 × 1280
108	Audio_Add_26	Add	1 × 128 × 1280
109	Audio_FFN_26	Feed Forward	1 × 128 × 1280
110	Audio_LN_27	LayerNorm	1 × 128 × 1280
111	Audio_Attn_27	Multi-Head Attention	1 × 128 × 1280
112	Audio_Add_27	Add	1 × 128 × 1280
113	Audio_FFN_27	Feed Forward	1 × 128 × 1280
114	Audio_LN_28	LayerNorm	1 × 128 × 1280
115	Audio_Attn_28	Multi-Head Attention	1 × 128 × 1280
116	Audio_Add_28	Add	1 × 128 × 1280
117	Audio_FFN_28	Feed Forward	1 × 128 × 1280
118	Audio_LN_29	LayerNorm	1 × 128 × 1280
119	Audio_Attn_29	Multi-Head Attention	1 × 128 × 1280
120	Audio_Add_29	Add	1 × 128 × 1280
121	Audio_FFN_29	Feed Forward	1 × 128 × 1280
122	Audio_LN_30	LayerNorm	1 × 128 × 1280
123	Audio_Attn_30	Multi-Head Attention	1 × 128 × 1280
124	Audio_Add_30	Add	1 × 128 × 1280
125	Audio_FFN_30	Feed Forward	1 × 128 × 1280
126	Audio_LN_31	LayerNorm	1 × 128 × 1280
127	Audio_Attn_31	Multi-Head Attention	1 × 128 × 1280
128	Audio_Add_31	Add	1 × 128 × 1280
129	Audio_FFN_31	Feed Forward	1 × 128 × 1280
130	Audio_LN_32	LayerNorm	1 × 128 × 1280
131	Audio_Attn_32	Multi-Head Attention	1 × 128 × 1280
132	Audio_Add_32	Add	1 × 128 × 1280
133	Audio_FFN_32	Feed Forward	1 × 128 × 1280
134	Audio projector	Projection	1 × 128 × 3072
135	Audio tokens	Reshape	1 × 256 × 3072
136	Multimodal fusion (concat tokens)	Concatenate	1 × 131328 × 3072
137	RMSNorm_1_1	RMSNorm	1 × 131328 × 3072
138	Attention_1	Grouped Query Attn	1 × 131328 × 3072
139	Add_1_attn	Add	1 × 131328 × 3072
140	RMSNorm_1_2	RMSNorm	1 × 131328 × 3072
141	FFN_1	SwiGLU	1 × 131328 × 3072
142	Add_1_ffn	Add	1 × 131328 × 3072
143	RMSNorm_2_1	RMSNorm	1 × 131328 × 3072
144	Attention_2	Grouped Query Attn	1 × 131328 × 3072
145	Add_2_attn	Add	1 × 131328 × 3072
146	RMSNorm_2_2	RMSNorm	1 × 131328 × 3072
147	FFN_2	SwiGLU	1 × 131328 × 3072
148	Add_2_ffn	Add	1 × 131328 × 3072
149	RMSNorm_3_1	RMSNorm	1 × 131328 × 3072
150	Attention_3	Grouped Query Attn	1 × 131328 × 3072
151	Add_3_attn	Add	1 × 131328 × 3072
152	RMSNorm_3_2	RMSNorm	1 × 131328 × 3072
153	FFN_3	SwiGLU	1 × 131328 × 3072
154	Add_3_ffn	Add	1 × 131328 × 3072
155	RMSNorm_4_1	RMSNorm	1 × 131328 × 3072
156	Attention_4	Grouped Query Attn	1 × 131328 × 3072
157	Add_4_attn	Add	1 × 131328 × 3072
158	RMSNorm_4_2	RMSNorm	1 × 131328 × 3072
159	FFN_4	SwiGLU	1 × 131328 × 3072
160	Add_4_ffn	Add	1 × 131328 × 3072
161	RMSNorm_5_1	RMSNorm	1 × 131328 × 3072
162	Attention_5	Grouped Query Attn	1 × 131328 × 3072
163	Add_5_attn	Add	1 × 131328 × 3072
164	RMSNorm_5_2	RMSNorm	1 × 131328 × 3072
165	FFN_5	SwiGLU	1 × 131328 × 3072
166	Add_5_ffn	Add	1 × 131328 × 3072
167	RMSNorm_6_1	RMSNorm	1 × 131328 × 3072
168	Attention_6	Grouped Query Attn	1 × 131328 × 3072
169	Add_6_attn	Add	1 × 131328 × 3072
170	RMSNorm_6_2	RMSNorm	1 × 131328 × 3072
171	FFN_6	SwiGLU	1 × 131328 × 3072
172	Add_6_ffn	Add	1 × 131328 × 3072
173	RMSNorm_7_1	RMSNorm	1 × 131328 × 3072
174	Attention_7	Grouped Query Attn	1 × 131328 × 3072
175	Add_7_attn	Add	1 × 131328 × 3072
176	RMSNorm_7_2	RMSNorm	1 × 131328 × 3072
177	FFN_7	SwiGLU	1 × 131328 × 3072
178	Add_7_ffn	Add	1 × 131328 × 3072
179	RMSNorm_8_1	RMSNorm	1 × 131328 × 3072
180	Attention_8	Grouped Query Attn	1 × 131328 × 3072
181	Add_8_attn	Add	1 × 131328 × 3072
182	RMSNorm_8_2	RMSNorm	1 × 131328 × 3072
183	FFN_8	SwiGLU	1 × 131328 × 3072
184	Add_8_ffn	Add	1 × 131328 × 3072
185	RMSNorm_9_1	RMSNorm	1 × 131328 × 3072
186	Attention_9	Grouped Query Attn	1 × 131328 × 3072
187	Add_9_attn	Add	1 × 131328 × 3072
188	RMSNorm_9_2	RMSNorm	1 × 131328 × 3072
189	FFN_9	SwiGLU	1 × 131328 × 3072
190	Add_9_ffn	Add	1 × 131328 × 3072
191	RMSNorm_10_1	RMSNorm	1 × 131328 × 3072
192	Attention_10	Grouped Query Attn	1 × 131328 × 3072
193	Add_10_attn	Add	1 × 131328 × 3072
194	RMSNorm_10_2	RMSNorm	1 × 131328 × 3072
195	FFN_10	SwiGLU	1 × 131328 × 3072
196	Add_10_ffn	Add	1 × 131328 × 3072
197	RMSNorm_11_1	RMSNorm	1 × 131328 × 3072
198	Attention_11	Grouped Query Attn	1 × 131328 × 3072
199	Add_11_attn	Add	1 × 131328 × 3072
200	RMSNorm_11_2	RMSNorm	1 × 131328 × 3072
201	FFN_11	SwiGLU	1 × 131328 × 3072
202	Add_11_ffn	Add	1 × 131328 × 3072
203	RMSNorm_12_1	RMSNorm	1 × 131328 × 3072
204	Attention_12	Grouped Query Attn	1 × 131328 × 3072
205	Add_12_attn	Add	1 × 131328 × 3072
206	RMSNorm_12_2	RMSNorm	1 × 131328 × 3072
207	FFN_12	SwiGLU	1 × 131328 × 3072
208	Add_12_ffn	Add	1 × 131328 × 3072
209	RMSNorm_13_1	RMSNorm	1 × 131328 × 3072
210	Attention_13	Grouped Query Attn	1 × 131328 × 3072
211	Add_13_attn	Add	1 × 131328 × 3072
212	RMSNorm_13_2	RMSNorm	1 × 131328 × 3072
213	FFN_13	SwiGLU	1 × 131328 × 3072
214	Add_13_ffn	Add	1 × 131328 × 3072
215	RMSNorm_14_1	RMSNorm	1 × 131328 × 3072
216	Attention_14	Grouped Query Attn	1 × 131328 × 3072
217	Add_14_attn	Add	1 × 131328 × 3072
218	RMSNorm_14_2	RMSNorm	1 × 131328 × 3072
219	FFN_14	SwiGLU	1 × 131328 × 3072
220	Add_14_ffn	Add	1 × 131328 × 3072
221	RMSNorm_15_1	RMSNorm	1 × 131328 × 3072
222	Attention_15	Grouped Query Attn	1 × 131328 × 3072
223	Add_15_attn	Add	1 × 131328 × 3072
224	RMSNorm_15_2	RMSNorm	1 × 131328 × 3072
225	FFN_15	SwiGLU	1 × 131328 × 3072
226	Add_15_ffn	Add	1 × 131328 × 3072
227	RMSNorm_16_1	RMSNorm	1 × 131328 × 3072
228	Attention_16	Grouped Query Attn	1 × 131328 × 3072
229	Add_16_attn	Add	1 × 131328 × 3072
230	RMSNorm_16_2	RMSNorm	1 × 131328 × 3072
231	FFN_16	SwiGLU	1 × 131328 × 3072
232	Add_16_ffn	Add	1 × 131328 × 3072
233	RMSNorm_17_1	RMSNorm	1 × 131328 × 3072
234	Attention_17	Grouped Query Attn	1 × 131328 × 3072
235	Add_17_attn	Add	1 × 131328 × 3072
236	RMSNorm_17_2	RMSNorm	1 × 131328 × 3072
237	FFN_17	SwiGLU	1 × 131328 × 3072
238	Add_17_ffn	Add	1 × 131328 × 3072
239	RMSNorm_18_1	RMSNorm	1 × 131328 × 3072
240	Attention_18	Grouped Query Attn	1 × 131328 × 3072
241	Add_18_attn	Add	1 × 131328 × 3072
242	RMSNorm_18_2	RMSNorm	1 × 131328 × 3072
243	FFN_18	SwiGLU	1 × 131328 × 3072
244	Add_18_ffn	Add	1 × 131328 × 3072
245	RMSNorm_19_1	RMSNorm	1 × 131328 × 3072
246	Attention_19	Grouped Query Attn	1 × 131328 × 3072
247	Add_19_attn	Add	1 × 131328 × 3072
248	RMSNorm_19_2	RMSNorm	1 × 131328 × 3072
249	FFN_19	SwiGLU	1 × 131328 × 3072
250	Add_19_ffn	Add	1 × 131328 × 3072
251	RMSNorm_20_1	RMSNorm	1 × 131328 × 3072
252	Attention_20	Grouped Query Attn	1 × 131328 × 3072
253	Add_20_attn	Add	1 × 131328 × 3072
254	RMSNorm_20_2	RMSNorm	1 × 131328 × 3072
255	FFN_20	SwiGLU	1 × 131328 × 3072
256	Add_20_ffn	Add	1 × 131328 × 3072
257	RMSNorm_21_1	RMSNorm	1 × 131328 × 3072
258	Attention_21	Grouped Query Attn	1 × 131328 × 3072
259	Add_21_attn	Add	1 × 131328 × 3072
260	RMSNorm_21_2	RMSNorm	1 × 131328 × 3072
261	FFN_21	SwiGLU	1 × 131328 × 3072
262	Add_21_ffn	Add	1 × 131328 × 3072
263	RMSNorm_22_1	RMSNorm	1 × 131328 × 3072
264	Attention_22	Grouped Query Attn	1 × 131328 × 3072
265	Add_22_attn	Add	1 × 131328 × 3072
266	RMSNorm_22_2	RMSNorm	1 × 131328 × 3072
267	FFN_22	SwiGLU	1 × 131328 × 3072
268	Add_22_ffn	Add	1 × 131328 × 3072
269	RMSNorm_23_1	RMSNorm	1 × 131328 × 3072
270	Attention_23	Grouped Query Attn	1 × 131328 × 3072
271	Add_23_attn	Add	1 × 131328 × 3072
272	RMSNorm_23_2	RMSNorm	1 × 131328 × 3072
273	FFN_23	SwiGLU	1 × 131328 × 3072
274	Add_23_ffn	Add	1 × 131328 × 3072
275	RMSNorm_24_1	RMSNorm	1 × 131328 × 3072
276	Attention_24	Grouped Query Attn	1 × 131328 × 3072
277	Add_24_attn	Add	1 × 131328 × 3072
278	RMSNorm_24_2	RMSNorm	1 × 131328 × 3072
279	FFN_24	SwiGLU	1 × 131328 × 3072
280	Add_24_ffn	Add	1 × 131328 × 3072
281	RMSNorm_25_1	RMSNorm	1 × 131328 × 3072
282	Attention_25	Grouped Query Attn	1 × 131328 × 3072
283	Add_25_attn	Add	1 × 131328 × 3072
284	RMSNorm_25_2	RMSNorm	1 × 131328 × 3072
285	FFN_25	SwiGLU	1 × 131328 × 3072
286	Add_25_ffn	Add	1 × 131328 × 3072
287	RMSNorm_26_1	RMSNorm	1 × 131328 × 3072
288	Attention_26	Grouped Query Attn	1 × 131328 × 3072
289	Add_26_attn	Add	1 × 131328 × 3072
290	RMSNorm_26_2	RMSNorm	1 × 131328 × 3072
291	FFN_26	SwiGLU	1 × 131328 × 3072
292	Add_26_ffn	Add	1 × 131328 × 3072
293	Output	Output	1 × 131328 × 3072

What the verifier says

warn"RoPE" receives input but its output is not connected. This layer will be unreachable in the forward pass. Fix: Connect the output forward, or add an Output node if this is the final layer.
dead-end

infoAt 58 stacked attention layers, residual-branch outputs add up; unscaled init lets activation variance grow with depth. GPT-2/LLaMA-family models scale the residual projections by depth (N(0, 0.02 / √(2L))). Fix: Scale residual output projections by depth: nn.init.normal_(w, std=0.02 / math.sqrt(2 * n_layers))
deep-attention-default-init

What changed upstream

The change tracker follows mistralai/Voxtral-Mini-4B-Realtime-2602: every revision it has read, what changed in the config, tokenizer, chat template or weights between them, and an OSV advisory per change.

Revision history and changes Badge JSON OSV advisories All tracked changes

Do this to your own model

Same numbers, on a model in your repo, in one command. No account.

pip install neurarch-trace
neurarch-trace mistralai/Voxtral-Mini-4B-Realtime-2602 --plan --share

Paste a model instead Markdown twin Index JSON POST /api/v1/plan