feat(deepinfra): update model YAMLs [bot] by models-bot[bot] · Pull Request #1672 · truefoundry/models

models-bot · 2026-07-02T09:48:03Z

Auto-generated by poc-agent for provider deepinfra.

Note

Low Risk
Metadata-only pricing updates in provider YAMLs; no runtime or security impact, though cost estimates may shift slightly for these models.

Overview
Updates DeepInfra model catalog pricing only—no feature, limit, or modality changes.

deepseek-ai/DeepSeek-V3-0324: raises input from 2e-7 to 2.4e-7 and output from 7.7e-7 to 9e-7 per token (cache read unchanged).

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B: lowers input from 1e-7 to 8.5e-8 and output from 5e-7 to 4e-7.

openai/gpt-oss-120b: lowers output from 1.9e-7 to 1.7e-7; input stays 3.9e-8.

These edits align stored costs with current DeepInfra list prices for billing/estimation downstream.

^{Reviewed by Cursor Bugbot for commit 2eaeea9. Bugbot is set up for automated code reviews on this repo. Configure here.}

github-actions · 2026-07-02T09:48:12Z

/test-models

harshiv-26 · 2026-07-02T09:50:34Z

Gateway test results

Total: 21
Passed: 20
Failed: 0
Validation failed: 0
Errored: 0
Skipped: 1
Success rate: 100.0%

Provider	Model	Scenarios
`deepinfra`	`deepseek-ai/DeepSeek-V3-0324`	success: tool-call, tool-call:stream, json-output, params:stream, params, json-output:stream
`deepinfra`	`nvidia/NVIDIA-Nemotron-3-Super-120B-A12B`	success: params, tool-call, tool-call:stream, json-output:stream, params:stream, json-output
`deepinfra`	`nvidia/NVIDIA-Nemotron-Nano-9B-v2`	skipped: skip-check
`deepinfra`	`openai/gpt-oss-120b`	success: tool-call:stream, params:stream, tool-call, json-output, json-output:stream, params, reasoning, reasoning:stream

Successes (20)

deepinfra/openai/gpt-oss-120b — tool-call:stream (success)

Output

{
  "location": "London"
}
VALIDATION: tool-call stream SUCCESS

deepinfra/openai/gpt-oss-120b — params:stream (success)

Output

The capital of France is **Paris**.

deepinfra/openai/gpt-oss-120b — tool-call (success)

Output

Function: get_weather
Arguments: {
  "location": "London"
}
VALIDATION: tool-call SUCCESS

deepinfra/openai/gpt-oss-120b — json-output (success)

Output

{
  "colors": [
    {
      "name": "Red",
      "hex": "#FF0000"
    },
    {
      "name": "Green",
      "hex": "#00FF00"
    },
    {
      "name"
... (truncated, 77 chars omitted)

deepinfra/openai/gpt-oss-120b — json-output:stream (success)

Output

{
  "colors": [
    {
      "name": "Red",
      "hex": "#FF0000"
    },
    {
      "name": "Green",
      "hex": "#00FF00"
    },
    {
      "name"
... (truncated, 84 chars omitted)

deepinfra/openai/gpt-oss-120b — params (success)

Output

The capital of France is **Paris**.

deepinfra/openai/gpt-oss-120b — reasoning (success)

Output

**The expression**

\[
3^{3^{3^{3}}}
\]

contains three “carats’’ (exponentiation symbols).  
When exponents are written next to each other without pa
... (truncated, 2435 chars omitted)

deepinfra/openai/gpt-oss-120b — reasoning:stream (success)

Output

### What does \(3^{3^{3^{3}}}\) mean ?

Exponentiation is **right‑associative** unless parentheses are written otherwise.  
So

\[
3^{3^{3^{3}}}=3^{\b
... (truncated, 2991 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — tool-call (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

deepinfra/deepseek-ai/DeepSeek-V3-0324 — tool-call:stream (success)

Output

{"location": "London"}
VALIDATION: tool-call stream SUCCESS

deepinfra/deepseek-ai/DeepSeek-V3-0324 — json-output (success)

Output

[
  {
    "color": "Red",
    "hex": "#FF0000"
  },
  {
    "color": "Green",
    "hex": "#00FF00"
  },
  {
    "color": "Blue",
    "hex": "#0000FF"

... (truncated, 38 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — params:stream (success)

Output

The capital of France is **Paris**. It is known for its iconic landmarks such as the Eiffel Tower, the Louvre Museum, and the Notre-Dame Cathedral.  

... (truncated, 74 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — params (success)

Output

The capital of France is **Paris**. It is known for its rich history, iconic landmarks like the Eiffel Tower, and vibrant culture. Let me know if you'
... (truncated, 21 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — json-output:stream (success)

Output

[
  {
    "name": "Red",
    "hex": "#FF0000"
  },
  {
    "name": "Green",
    "hex": "#00FF00"
  },
  {
    "name": "Blue",
    "hex": "#0000FF"
  }
... (truncated, 42 chars omitted)

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — params (success)

Output

The capital of France is **Paris**.

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — tool-call (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — tool-call:stream (success)

Output

{"location": "London"}

VALIDATION: tool-call stream SUCCESS

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — json-output:stream (success)

Output

{
  "red": "#FF0000",
  "green": "#00FF00",
  "blue": "#0000FF"
}
VALIDATION: json-output stream SUCCESS

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — params:stream (success)

Output

The capital of France is **Paris**.  

This has been the case since the 10th century (though historical capitals varied earlier, such as Lyon or Ver
... (truncated, 238 chars omitted)

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — json-output (success)

Output

[
  {
    "name": "Red",
    "hex": "#FF0000"
  },
  {
    "name": "Green",
    "hex": "#008000"
  },
  {
    "name": "Blue",
    "hex": "#0000FF"
  }
... (truncated, 35 chars omitted)

Skipped (1)

deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2 — skip-check (skipped)

Skip reason

deprecated or retired model

github-actions · 2026-07-07T07:50:47Z

/test-models

harshiv-26 · 2026-07-07T07:53:02Z

Gateway test results

Total: 20
Passed: 20
Failed: 0
Validation failed: 0
Errored: 0
Skipped: 0
Success rate: 100.0%

Provider	Model	Scenarios
`deepinfra`	`deepseek-ai/DeepSeek-V3-0324`	success: tool-call, tool-call:stream, params, params:stream, json-output, json-output:stream
`deepinfra`	`nvidia/NVIDIA-Nemotron-3-Super-120B-A12B`	success: params:stream, tool-call:stream, tool-call, json-output:stream, json-output, params
`deepinfra`	`openai/gpt-oss-120b`	success: params, tool-call, tool-call:stream, params:stream, json-output, json-output:stream, reasoning, reasoning:stream

Successes (20)

deepinfra/openai/gpt-oss-120b — params (success)

Output

The capital of France is **Paris**.

deepinfra/openai/gpt-oss-120b — tool-call (success)

Output

Function: get_weather
Arguments: {
  "location": "London"
}
VALIDATION: tool-call SUCCESS

deepinfra/openai/gpt-oss-120b — tool-call:stream (success)

Output

{
  "location": "London"
}
VALIDATION: tool-call stream SUCCESS

deepinfra/openai/gpt-oss-120b — params:stream (success)

Output

The capital of France is **Paris**.

deepinfra/openai/gpt-oss-120b — json-output (success)

Output

{
  "colors": [
    {
      "name": "Crimson",
      "hex": "#DC143C"
    },
    {
      "name": "Royal Blue",
      "hex": "#4169E1"
    },
    {
   
... (truncated, 92 chars omitted)

deepinfra/openai/gpt-oss-120b — json-output:stream (success)

Output

{
  "colors": [
    {
      "name": "Red",
      "hex": "#FF0000"
    },
    {
      "name": "Green",
      "hex": "#00FF00"
    },
    {
      "name"
... (truncated, 84 chars omitted)

deepinfra/openai/gpt-oss-120b — reasoning (success)

Output

### What “\(3^{3^{3^{3}}}\)” actually means  

When you see a tower of exponents  

\[
3^{3^{3^{3}}}
\]

the convention is **right‑associative**:  

\
... (truncated, 2814 chars omitted)

deepinfra/openai/gpt-oss-120b — reasoning:stream (success)

Output

**Step 1 – Understand the notation**  

When exponentiation is written without parentheses, it is *right‑associative*.  

\[
3^{3^{3^{3}}}=3^{\bigl(3^
... (truncated, 2229 chars omitted)

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — params:stream (success)

Output

The capital of France is Paris.

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — tool-call:stream (success)

Output

{"location": "London"}

VALIDATION: tool-call stream SUCCESS

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — tool-call (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — json-output:stream (success)

Output

[
  {"color": "Red", "hex": "#FF0000"},
  {"color": "Green", "hex": "#00FF00"},
  {"color": "Blue", "hex": "#0000FF"}
]
VALIDATION: json-output stream
... (truncated, 9 chars omitted)

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — json-output (success)

Output

{
  "colors": [
    {"name": "Red", "hex": "#FF0000"},
    {"name": "Green", "hex": "#008000"},
    {"name": "Blue", "hex": "#0000FF"}
  ]
}
VALIDATIO
... (truncated, 23 chars omitted)

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — params (success)

Output

The capital of France is **Paris**.  
This has been the case since the 10th century, and Paris remains the political, cultural, and economic center 
... (truncated, 132 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — tool-call (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

deepinfra/deepseek-ai/DeepSeek-V3-0324 — tool-call:stream (success)

Output

{"location": "London"}
VALIDATION: tool-call stream SUCCESS

deepinfra/deepseek-ai/DeepSeek-V3-0324 — params (success)

Output

The capital of France is **Paris**.  

Would you like any additional information about Paris or France? 😊

deepinfra/deepseek-ai/DeepSeek-V3-0324 — params:stream (success)

Output

The capital of France is **Paris**. It is known for its rich history, iconic landmarks like the Eiffel Tower, and cultural significance. Let me know i
... (truncated, 26 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — json-output (success)

Output

[
  {
    "color": "Red",
    "hex": "#FF0000"
  },
  {
    "color": "Green",
    "hex": "#00FF00"
  },
  {
    "color": "Blue",
    "hex": "#0000FF"

... (truncated, 38 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — json-output:stream (success)

Output

[
  {
    "name": "Red",
    "hex": "#FF0000"
  },
  {
    "name": "Green",
    "hex": "#00FF00"
  },
  {
    "name": "Blue",
    "hex": "#0000FF"
  }
... (truncated, 42 chars omitted)

github-actions · 2026-07-07T07:57:10Z

/test-models

harshiv-26 · 2026-07-07T07:58:47Z

Gateway test results

Total: 20
Passed: 18
Failed: 0
Validation failed: 0
Errored: 0
Skipped: 2
Success rate: 100.0%

Provider	Model	Scenarios
`deepinfra`	`deepseek-ai/DeepSeek-V3-0324`	success: tool-call:stream, tool-call, params, json-output:stream, json-output, params:stream
`deepinfra`	`nvidia/NVIDIA-Nemotron-3-Super-120B-A12B`	success: params:stream, tool-call, json-output:stream, json-output skipped: tool-call:stream, params
`deepinfra`	`openai/gpt-oss-120b`	success: params:stream, tool-call, params, tool-call:stream, json-output:stream, json-output, reasoning, reasoning:stream

Successes (18)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — tool-call:stream (success)

Output

{"location": "London"}
VALIDATION: tool-call stream SUCCESS

deepinfra/deepseek-ai/DeepSeek-V3-0324 — tool-call (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

deepinfra/deepseek-ai/DeepSeek-V3-0324 — params (success)

Output

The capital of France is **Paris**. It is known for its rich history, iconic landmarks like the Eiffel Tower, and vibrant culture. Let me know if you'
... (truncated, 21 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — json-output:stream (success)

Output

[
  {
    "color": "Red",
    "hex": "#FF0000"
  },
  {
    "color": "Green",
    "hex": "#00FF00"
  },
  {
    "color": "Blue",
    "hex": "#0000FF"

... (truncated, 45 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — json-output (success)

Output

[
  {
    "color": "Red",
    "hex": "#FF0000"
  },
  {
    "color": "Green",
    "hex": "#00FF00"
  },
  {
    "color": "Blue",
    "hex": "#0000FF"

... (truncated, 38 chars omitted)

deepinfra/deepseek-ai/DeepSeek-V3-0324 — params:stream (success)

Output

The capital of France is **Paris**. It is one of the most famous cities in the world, known for its rich history, culture, and landmarks like the Eiff
... (truncated, 112 chars omitted)

deepinfra/openai/gpt-oss-120b — params:stream (success)

Output

The capital of France is **Paris**.

deepinfra/openai/gpt-oss-120b — tool-call (success)

Output

Function: get_weather
Arguments: {
  "location": "London"
}
VALIDATION: tool-call SUCCESS

deepinfra/openai/gpt-oss-120b — params (success)

Output

The capital of France is **Paris**.

deepinfra/openai/gpt-oss-120b — tool-call:stream (success)

Output

{
  "location": "London"
}
VALIDATION: tool-call stream SUCCESS

deepinfra/openai/gpt-oss-120b — json-output:stream (success)

Output

{
  "colors": [
    {
      "name": "Red",
      "hex": "#FF0000"
    },
    {
      "name": "Forest Green",
      "hex": "#228B22"
    },
    {
     
... (truncated, 97 chars omitted)

deepinfra/openai/gpt-oss-120b — json-output (success)

Output

{
  "colors": [
    {
      "name": "Crimson",
      "hex": "#DC143C"
    },
    {
      "name": "RoyalBlue",
      "hex": "#4169E1"
    },
    {
    
... (truncated, 89 chars omitted)

deepinfra/openai/gpt-oss-120b — reasoning (success)

Output

**Step‑by‑step evaluation of the tower  

\[
3^{3^{3^{3}}}
\]

The convention for repeated exponentiation (a “power tower”) is **right‑association**:

... (truncated, 2685 chars omitted)

deepinfra/openai/gpt-oss-120b — reasoning:stream (success)

Output

### 1.  What does the notation \(3^{3^{3^{3}}}\) mean?

In ordinary mathematics exponentiation is **right‑associative**:

\[
a^{b^{c}} \;=\; a^{\;(b^{
... (truncated, 3224 chars omitted)

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — params:stream (success)

Output

The capital of France is Paris.

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — tool-call (success)

Output

Function: get_weather
Arguments: {"location": "London"}
VALIDATION: tool-call SUCCESS

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — json-output:stream (success)

Output

{
  "red": "#FF0000",
  "green": "#008000",
  "blue": "#0000FF"
}
VALIDATION: json-output stream SUCCESS

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — json-output (success)

Output

[
  {
    "name": "Red",
    "hex": "#FF0000"
  },
  {
    "name": "Green",
    "hex": "#008000"
  },
  {
    "name": "Blue",
    "hex": "#0000FF"
  }
... (truncated, 35 chars omitted)

Skipped (2)

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — tool-call:stream (skipped)

Skip reason

Upstream rate limited the request

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B — params (skipped)

Skip reason

Upstream rate limited the request

feat(deepinfra): update model YAMLs [bot]

0586f18

Update NVIDIA-Nemotron-Nano-9B-v2.yaml

31ebad6

Merge branch 'main' into bot/update-deepinfra-20260702-094801

2eaeea9

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(deepinfra): update model YAMLs [bot]#1672

feat(deepinfra): update model YAMLs [bot]#1672
models-bot[bot] wants to merge 3 commits into
mainfrom
bot/update-deepinfra-20260702-094801

models-bot Bot commented Jul 2, 2026 •

edited by cursor Bot

Loading

Uh oh!

github-actions Bot commented Jul 2, 2026

Uh oh!

harshiv-26 commented Jul 2, 2026

Uh oh!

github-actions Bot commented Jul 7, 2026

Uh oh!

harshiv-26 commented Jul 7, 2026

Uh oh!

github-actions Bot commented Jul 7, 2026

Uh oh!

harshiv-26 commented Jul 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

models-bot Bot commented Jul 2, 2026 • edited by cursor Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Jul 2, 2026

Uh oh!

harshiv-26 commented Jul 2, 2026

Gateway test results

Uh oh!

github-actions Bot commented Jul 7, 2026

Uh oh!

harshiv-26 commented Jul 7, 2026

Gateway test results

Uh oh!

github-actions Bot commented Jul 7, 2026

Uh oh!

harshiv-26 commented Jul 7, 2026

Gateway test results

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

models-bot Bot commented Jul 2, 2026 •

edited by cursor Bot

Loading