OpenAI: GPT-4o-mini

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more …

openai/gpt-4o-mini

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
128000
Published model ID
gpt-4o-mini-2024-07-18
Capabilities
fileInput, multimodal, promptCaching, structuredOutputs, toolCalling, visionInput, webSearch

Evaluations

1–7 / 7

OpenRouter Benchmarks

42.761%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · OpenAI
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
26
sample size
594
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
OpenAI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-02T23:19:57.879Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
594
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.4276093333333334
accuracy_std_dev
0.00629925838668507
cost_per_task_usd
0.0010292508417508418
output_tokens_per_task
1523.1902356902358
latency_seconds_per_task
16.725542087542085
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
26
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o-mini
source model id
openai/gpt-4o-mini
Original result ↗

OpenRouter Benchmarks

28.444%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · OpenAI
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
26
sample size
150
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
OpenAI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-02T23:13:47.090Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.2844446666666667
accuracy_std_dev
0.02997950740459592
cost_per_task_usd
0.025635820000000004
output_tokens_per_task
4107.166666666667
latency_seconds_per_task
67.80675333333333
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
27
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o-mini
source model id
openai/gpt-4o-mini
Original result ↗

OpenRouter Benchmarks

43.14%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Azure
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
43
sample size
792
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
4
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Azure
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:05:18.003Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
792
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.43139700000000003
accuracy_std_dev
0.012951914704011906
cost_per_task_usd
0.0010746982323232325
output_tokens_per_task
1509.2487373737374
latency_seconds_per_task
24.227715909090907
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
43
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o-mini
source model id
openai/gpt-4o-mini
Original result ↗

OpenRouter Benchmarks

30.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
125
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:04:58.075Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.30666649999999995
accuracy_std_dev
0.006666499999999992
cost_per_task_usd
0.01779966
output_tokens_per_task
3406.81
latency_seconds_per_task
55.49841000000001
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
128
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o-mini
source model id
openai/gpt-4o-mini
Original result ↗

OpenRouter Benchmarks

43.603%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
128
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:16:07.087Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.43602700000000005
accuracy_std_dev
0.006734000000000018
cost_per_task_usd
0.0010042146464646464
output_tokens_per_task
1481.030303030303
latency_seconds_per_task
21.558090909090907
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
132
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o-mini
source model id
openai/gpt-4o-mini
Original result ↗

Published prices

1–20 / 46

gpt-4o-mini ↗

$0.05

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cached input tokens (per 1M)

gpt-4o-mini ↗

$0.10

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gpt-4o-mini ↗

$0.39

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

openai/gpt-4o-mini ↗

$0.04

Inference provider
cloudflareWorkersAI
Platform
OpenAI
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

openai/gpt-4o-mini ↗

$0.08

Inference provider
cloudflareWorkersAI
Platform
OpenAI
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

openai/gpt-4o-mini ↗

$0.30

Inference provider
cloudflareWorkersAI
Platform
OpenAI
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)
Pricing via
Cloudflare AI Gateway

openai/gpt-4o-mini ↗

$0.08

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-4o-mini ↗

$0.15

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-4o-mini ↗

$0.60

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-4o-mini:batch ↗

$0.04

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-4o-mini:batch ↗

$0.08

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-4o-mini:batch ↗

$0.30

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-4o-mini ↗

$0.08

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-4o-mini
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o-mini ↗

$0.15

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-4o-mini
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o-mini ↗

$0.60

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-4o-mini
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o-mini ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
request
Currency
USD
Billing conditions
charge
web_search
endpoint
azure | openai/gpt-4o-mini
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Web search
Pricing via
Vercel AI Gateway

openai/gpt-4o-mini ↗

$0.08

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-4o-mini
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o-mini ↗

$0.13

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-4o-mini
model_type
language
service_tier
priority
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o-mini ↗

$0.08

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
region
scope
zone
geo_region
eu
endpoint
openai | openai/gpt-4o-mini
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–3 / 3

gpt-4o-mini ↗

source model id
gpt-4o-mini
hosting
gateway
platforms
  • Cheaper Inference
context length
128000
max output tokens
16384
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

GPT-4o mini ↗

source model id
openai/gpt-4o-mini
hosting
third-party
platforms
  • OpenAI
context length
128000
max output tokens
16384
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    GPT-4o mini ↗

    source model id
    openai/gpt-4o-mini
    hosting
    vercel-gateway
    platforms
    • Vercel AI Gateway
    context length
    128000
    max output tokens
    16384
    architecture
    input_modalities
    • text
    • image
    • pdf
    output_modalities
    • text
    capabilities
    • promptCaching
    • structuredOutputs
    • toolCalling
    • visionInput
    • webSearch
    regions
    • eu
    • us

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    35 / 100

    source id
    stanfordFMTI
    canonical model id
    openai/gpt-4o-mini
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    OpenAI
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    35 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Source specification observations

    1–11 / 11

    cloudflareWorkersAI ↗

    field
    context_length
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    context_length
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2023-10-31
    normalized value
    2023-10-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2023-10-31
    normalized value
    2023-10-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2023-10-01
    normalized value
    2023-10-01
    precision
    day
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    cloudflareWorkersAI ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    Original sources

    1–10 / 10

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Vercel AI Gateway · Model page ↗

    GitHub · Source snapshot ↗

    api.cheaperinference.com · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    GitHub · Catalog ↗

    OpenRouter · Catalog ↗

    OpenRouter · Catalog ↗

    Vercel AI Gateway · Catalog ↗

    Source links

    1–7 / 7

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace