OpenAI GPT-5 Nano API Pricing: Rock-Bottom Token Costs for Utility
Explore OpenAI GPT-5 Nano API pricing ($0.05/M input, $0.40/M output), lowest token costs in the OpenAI catalog, high-speed classification, and batch rates.
Legacy — superseded by GPT-5.4 series See GPT-6 Luna pricing.
No announced shutdown date. Source · Full retirement tracker
How much does GPT-5 Nano cost per million tokens?
OpenAI GPT-5 Nano charges $0.05 per million input tokens and $0.40 per million output tokens ($0.1375/M blended at 3:1). Provides the most affordable token rates in the OpenAI ecosystem for high-volume text utility. Verified 2026-09-08.
Verified 2026-09-08 — source
How much does GPT-5 Nano cost per 1,000 requests?
Computed from generated token pricing. Each row assumes the listed input and output tokens per request; this model has no measured verbosity factor, so the unadjusted output estimate is shown.
| Request shape | Input tokens | Output tokens | Cost / 1,000 requests |
|---|---|---|---|
| Short | 100 | 50 | $0.0250 |
| Medium | 1,000 | 500 | $0.2500 |
| Long | 4,000 | 2,000 | $1.0000 |
Formula: ((input price × input tokens) + (output price × output tokens × verbosity factor)) ÷ 1,000,000 × 1,000. Assumptions: short 100/50, medium 1,000/500, long 4,000/2,000 input/output tokens per request. Unadjusted — no measured verbosity factor is available.
Three model-specific legacy pricing decisions
GPT-5 Nano owns the ultra-low-rate tagging, routing, and constrained-generation bill; quality and delivery assumptions remain user-supplied.
1. Fixed model-specific workload bills
| Workload | Input / output | 100K requests | Evidence boundary |
|---|---|---|---|
| Tagging | 300 / 30 | $2.70 | 100K / 1M / 10M ladder |
| Routing | 500 / 80 | $5.70 | 100K / 1M / 10M ladder |
| Constrained generation | 1,000 / 250 | $15.00 | Text tokens |
Formula: requests × (input tokens × input $/M + output tokens × output $/M × output expansion) ÷ 1,000,000. Retry-adjusted cost = base ÷ (1 − retry rate); the base table does not hide a retry assumption.
2. Nano → Luna break-even uplift
| Fixed shape | GPT-5 Nano | GPT-6 Luna | Numeric decision boundary |
|---|---|---|---|
| Tagging · 300 / 30 | $2.87 | $4.69 | 63% accepted-result uplift required after fixed retry assumptions (6% → 4%) |
| Routing · 500 / 80 | $6.06 | $9.38 | 63% accepted-result uplift required after fixed retry assumptions (6% → 4%) |
This is a cost-per-accepted-result threshold, not a measured quality claim. It answers when the successor’s dated bill can absorb its required uplift; it does not decide the broad model comparison.
3. Migration-risk ledger
| Traffic / evidence | Result | Safe treatment |
|---|---|---|
| 100K requests | $2.87 | Fixed first workload; text-token units |
| 1M requests | $27.00 | Linear token spend only; no volume discount inferred |
| 10M requests | $270.00 | Budget exposure; quota and latency remain unavailable |
| Quality, latency, cache, batch, and quota: Unavailable | Unavailable | Do not infer, zero-price, or import a neighboring model’s mechanic |
| Shutdown date: Unavailable | Unavailable | Do not infer, zero-price, or import a neighboring model’s mechanic |
| No image/audio unit is converted from text tokens | Unavailable | Do not infer, zero-price, or import a neighboring model’s mechanic |
| Lifecycle | legacy; no sourced announcement date | No sourced shutdown date; revalidate before current claims |
Nano-to-Luna multiplier and break-even
| Workload | Nano cost | Luna cost | Luna / Nano multiplier | Break-even accepted-result uplift |
|---|---|---|---|---|
| Tagging | $2.70 | $4.50 | 1.67× | 66.7% |
| Routing | $5.70 | $9.00 | 1.58× | 57.9% |
| Constrained generation | $15.00 | $22.50 | 1.50× | 50.0% |
Break-even uplift = (Luna cost ÷ Nano cost − 1) × 100; all three fixed shapes, including constrained generation, are included.
Price verified 2026-04-06; lifecycle verified 2026-08-14. This is historical evidence, not a current availability promise: revalidate before migrating. “Unavailable” means no compatible dated evidence was found; it is never treated as zero. First-party price source · lifecycle source · Test this model in All AI Ask.
Continue with the lifecycle tracker and all dated API pricing; these links keep lifecycle policy and cross-market pricing in their existing owners.
All three decisions below are computed for GPT-5 Nano; fixed inputs, formulas, dated provenance, successor boundary, lifecycle state, and missing-data treatment remain visible.
Exact-model pricing guide · verified 2026-09-08
Exact model boundary: OpenAI gpt-5-nano (slug gpt-5-nano). First-party provider pricing and API documentation remain fact owners.
Rock-bottom token pricing and high-volume utility spend matrix
Frozen scenario board. Formula / deterministic rule: monthly_spend = calls * ((in_tokens * 0.05 + out_tokens * 0.40) / 1M) Boundary: Owns GPT-5 Nano token tariff modeling and high-volume utility spend.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| 200K text classification passes | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=200K text classification passes; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 200K text classification passes is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 1M automated customer triage calls | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=1M automated customer triage calls; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 1M automated customer triage calls is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 5M high-concurrency log filtering events | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=5M high-concurrency log filtering events; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 5M high-concurrency log filtering events is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| prompt caching reuse (50% input discount) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=prompt caching reuse (50% input discount); workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — prompt caching reuse (50% input discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| batch processing API queue (50% discount) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=batch processing API queue (50% discount); workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — batch processing API queue (50% discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unresolved billing currency | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unresolved billing currency; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unresolved billing currency has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: OpenAI API pricing; verification date 2026-09-08. Missing or conflicting joins fail closed.
High-throughput log analysis and streaming UX latency audit
Frozen scenario board. Formula / deterministic rule: turnaround = ttft + (tokens_out / tps); optimized for high throughput Boundary: Owns turnaround time benchmarks and user experience responsiveness.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| real-time telemetry log anomaly detection (<90ms) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=real-time telemetry log anomaly detection (<90ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — real-time telemetry log anomaly detection (<90ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| instant search query normalization (<100ms) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=instant search query normalization (<100ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — instant search query normalization (<100ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| high-speed spam filter check (<80ms) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=high-speed spam filter check (<80ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — high-speed spam filter check (<80ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| high-concurrency request surge | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=high-concurrency request surge; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — high-concurrency request surge is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| network transit buffer | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=network transit buffer; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — network transit buffer is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unmeasured speed fixture | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unmeasured speed fixture; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unmeasured speed fixture is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
First-party provenance: OpenAI API documentation; verification date 2026-09-08. Missing or conflicting joins fail closed.
Model generation upgrade path: GPT-5 Nano to GPT-5.4 Nano
Frozen scenario board. Formula / deterministic rule: migration_roi = accuracy_gain_value - cost_delta Boundary: Owns generational migration economics between GPT-5 Nano and GPT-5.4 Nano.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| 100% GPT-5 Nano baseline ($0.05/$0.40) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=100% GPT-5 Nano baseline ($0.05/$0.40); deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 100% GPT-5 Nano baseline ($0.05/$0.40) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| hybrid deployment (70% Nano / 30% 5.4 Nano) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=hybrid deployment (70% Nano / 30% 5.4 Nano); deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — hybrid deployment (70% Nano / 30% 5.4 Nano) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| full upgrade to GPT-5.4 Nano ($0.20/$1.25) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=full upgrade to GPT-5.4 Nano ($0.20/$1.25); deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — full upgrade to GPT-5.4 Nano ($0.20/$1.25) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| batch offline processing on GPT-5 Nano | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=batch offline processing on GPT-5 Nano; deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — batch offline processing on GPT-5 Nano is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unresolved migration test regression | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unresolved migration test regression; deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unresolved migration test regression has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
| unsupported prompt structure | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unsupported prompt structure; deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unsupported prompt structure has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: OpenAI API pricing; verification date 2026-09-08. Missing or conflicting joins fail closed.
Method and limitations: formulas are deterministic; observed and assumed inputs are labeled; no missing provider, host, account, region, realm, alias, snapshot, revision, weight, artifact, control, tool, modality, workload, rate-period, timestamp, or result is transferred. Run this scenario →
Verified Model Pricing Intelligence•Audit date: 2026-09-08
OpenAI GPT-5 Nano API Pricing: Rock-Bottom Token Costs for Utility
OpenAI GPT-5 Nano charges $0.05 per million input tokens and $0.40 per million output tokens ($0.1375/M blended at 3:1). Provides the most affordable token rates in the OpenAI ecosystem for high-volume text utility. Verified 2026-09-08.
Rock-bottom token pricing and high-volume utility spend matrix
Frozen scenario board. Formula / deterministic rule: monthly_spend = calls * ((in_tokens * 0.05 + out_tokens * 0.40) / 1M) Boundary: Owns GPT-5 Nano token tariff modeling and high-volume utility spend.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| 200K text classification passes | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=200K text classification passes; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 200K text classification passes is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 1M automated customer triage calls | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=1M automated customer triage calls; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 1M automated customer triage calls is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| 5M high-concurrency log filtering events | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=5M high-concurrency log filtering events; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 5M high-concurrency log filtering events is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| prompt caching reuse (50% input discount) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=prompt caching reuse (50% input discount); workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — prompt caching reuse (50% input discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| batch processing API queue (50% discount) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=batch processing API queue (50% discount); workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — batch processing API queue (50% discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unresolved billing currency | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unresolved billing currency; workload; prompt tokens; completion tokens; standard spend; cached spend; batch spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unresolved billing currency has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: OpenAI API pricing; verification date 2026-09-08. Missing or conflicting joins fail closed.
High-throughput log analysis and streaming UX latency audit
Frozen scenario board. Formula / deterministic rule: turnaround = ttft + (tokens_out / tps); optimized for high throughput Boundary: Owns turnaround time benchmarks and user experience responsiveness.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| real-time telemetry log anomaly detection (<90ms) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=real-time telemetry log anomaly detection (<90ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — real-time telemetry log anomaly detection (<90ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| instant search query normalization (<100ms) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=instant search query normalization (<100ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — instant search query normalization (<100ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| high-speed spam filter check (<80ms) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=high-speed spam filter check (<80ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — high-speed spam filter check (<80ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| high-concurrency request surge | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=high-concurrency request surge; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — high-concurrency request surge is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| network transit buffer | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=network transit buffer; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — network transit buffer is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unmeasured speed fixture | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unmeasured speed fixture; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness champion; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unmeasured speed fixture is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
First-party provenance: OpenAI API documentation; verification date 2026-09-08. Missing or conflicting joins fail closed.
Model generation upgrade path: GPT-5 Nano to GPT-5.4 Nano
Frozen scenario board. Formula / deterministic rule: migration_roi = accuracy_gain_value - cost_delta Boundary: Owns generational migration economics between GPT-5 Nano and GPT-5.4 Nano.
| Frozen scenario | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
| 100% GPT-5 Nano baseline ($0.05/$0.40) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=100% GPT-5 Nano baseline ($0.05/$0.40); deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 100% GPT-5 Nano baseline ($0.05/$0.40) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| hybrid deployment (70% Nano / 30% 5.4 Nano) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=hybrid deployment (70% Nano / 30% 5.4 Nano); deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — hybrid deployment (70% Nano / 30% 5.4 Nano) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| full upgrade to GPT-5.4 Nano ($0.20/$1.25) | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=full upgrade to GPT-5.4 Nano ($0.20/$1.25); deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — full upgrade to GPT-5.4 Nano ($0.20/$1.25) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| batch offline processing on GPT-5 Nano | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=batch offline processing on GPT-5 Nano; deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — batch offline processing on GPT-5 Nano is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
| unresolved migration test regression | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unresolved migration test regression; deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unresolved migration test regression has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
| unsupported prompt structure | model=gpt-5-nano; slug=gpt-5-nano; provider=OpenAI; scenario=unsupported prompt structure; deployment strategy; monthly query volume; monthly spend; quality uplift; regression risk; migration recommendation; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unsupported prompt structure has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: OpenAI API pricing; verification date 2026-09-08. Missing or conflicting joins fail closed.
Exact-Model Pricing Evidence•Verified 2026-04-06
GPT-5 Nano pricing evidence
Source-backed rate shape: input=$0.050000/M; output=$0.400000/M. Historical registry snapshot; revalidate before any current-price claim. Nano dated token spend and migration risk only; cheapest-model rankings, Luna economics, and user-entered calculators retain ownership.
Module 1 of 3
100K/1M/10M request bills
Novel contribution boundary: Owns dated Nano bills for fixed high-volume request shapes. Formula / deterministic rule: spend = requests × (inputTokens × inputRate + outputTokens × outputRate) / 1,000
| Scenario | Exact model, provider, and fixed inputs | Result | State |
|---|---|---|---|
| 100K utility requests | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; requests=100,000; inputTokens/request=300; outputTokens/request=80; perRequest=$0.000047; fixed inputs only; measurement versus assumption=explicit | Deterministic spend = $4.700000 for 100,000 requests; no outcome or benchmark asserted. | VERIFIED_DETERMINISTIC — arithmetic only |
| 1M utility requests | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; requests=1,000,000; inputTokens/request=600; outputTokens/request=120; perRequest=$0.000078; fixed inputs only; measurement versus assumption=explicit | Deterministic spend = $78.000000 for 1,000,000 requests; no outcome or benchmark asserted. | VERIFIED_DETERMINISTIC — arithmetic only |
| 10M utility requests | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; requests=10,000,000; inputTokens/request=1,000; outputTokens/request=200; perRequest=$0.000130; fixed inputs only; measurement versus assumption=explicit | Deterministic spend = $1300.000000 for 10,000,000 requests; no outcome or benchmark asserted. | VERIFIED_DETERMINISTIC — arithmetic only |
First-party registry provenance: https://openai.com/api/pricing; registry provider openai; verified 2026-04-06. Revalidate before any current-price claim.
Module 2 of 3
Nano→Luna break-even accepted-result uplift
Novel contribution boundary: Owns dated Nano/Luna break-even arithmetic with explicit retry input; accepted-result uplift is not sourced. Formula / deterministic rule: requiredAcceptedRate = Luna attempt-plus-retry cost / Nano attempt cost; observed uplift = Unavailable
| Scenario | Exact model, provider, and fixed inputs | Result | State |
|---|---|---|---|
| Short utility request; 10% retry share; 100 retry-input tokens | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; ownerAttempt=$0.000047; comparisonAttempt=$0.000780; retryInputTokens=100; retryShare=10%; fixed inputs only; measurement versus assumption=explicit | Deterministic comparison cost with explicit retry input = $0.000790; required accepted-result rate = 1680.85%; observed acceptance/quality = Unavailable. | VERIFIED_DETERMINISTIC — arithmetic only |
| Medium utility request; 20% retry share; 250 retry-input tokens | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; ownerAttempt=$0.000078; comparisonAttempt=$0.001320; retryInputTokens=250; retryShare=20%; fixed inputs only; measurement versus assumption=explicit | Deterministic comparison cost with explicit retry input = $0.001370; required accepted-result rate = 1756.41%; observed acceptance/quality = Unavailable. | VERIFIED_DETERMINISTIC — arithmetic only |
| Long utility request; 30% retry share; 500 retry-input tokens | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; ownerAttempt=$0.000130; comparisonAttempt=$0.002200; retryInputTokens=500; retryShare=30%; fixed inputs only; measurement versus assumption=explicit | Deterministic comparison cost with explicit retry input = $0.002350; required accepted-result rate = 1807.69%; observed acceptance/quality = Unavailable. | VERIFIED_DETERMINISTIC — arithmetic only |
First-party registry provenance: https://openai.com/api/pricing; registry provider openai; verified 2026-04-06. Revalidate before any current-price claim.
Module 3 of 3
Token-budget exposure ledger with evidence gaps visible
Novel contribution boundary: Owns dated Nano token exposure only; quality, latency, cache, batch, quota, and shutdown evidence are not inferred. Formula / deterministic rule: exposure = fixed token volume × sourced rate; quality/latency/cache/batch/quota/shutdown = Unavailable
| Scenario | Exact model, provider, and fixed inputs | Result | State |
|---|---|---|---|
| Sourced dated token rates | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; FAIL CLOSED — no sourced observation or provider guarantee; measurement versus assumption=explicit | Unavailable — the registry does not publish cache evidence for this exact model. | FAIL CLOSED — no sourced observation or provider guarantee |
| Quality or latency observation | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; FAIL CLOSED — no sourced observation or provider guarantee; measurement versus assumption=explicit | Unavailable — the registry does not publish context evidence for this exact model. | FAIL CLOSED — no sourced observation or provider guarantee |
| Cache, batch, quota, or shutdown terms | model=gpt-5-nano; provider=openai; registryRates=input=$0.050000/M; output=$0.400000/M; comparisonModel=gpt-5.6-luna; FAIL CLOSED — no sourced observation or provider guarantee; measurement versus assumption=explicit | Unavailable — the registry does not publish batch evidence for this exact model. | FAIL CLOSED — no sourced observation or provider guarantee |
First-party registry provenance: https://openai.com/api/pricing; registry provider openai; verified 2026-04-06. Revalidate before any current-price claim.
How fast is GPT-5 Nano?
Not yet measured — see the speed benchmark leaderboard for models we do track.
How much does GPT-5 Nano cost at scale?
| Tokens / month | Est. cost (blended 3:1) |
|---|---|
| 100,000 | $0.01 |
| 1,000,000 | $0.14 |
| 10,000,000 | $1.38 |
| 100,000,000 | $13.75 |
How does GPT-5 Nano compare with other models?
GPT-6 Luna — $0.20/MGPT-6 Luna Pro — $0.20/MGPT-4o Mini — $0.26/MGPT-5.4 Nano — $0.46/MGPT-5 Mini — $0.69/MGPT-OSS 20B — $0.13/MMinistral 8B — $0.15/MMuse Spark 1.3 Contributor — $0.13/M
What should you explore next for GPT-5 Nano?
What are common questions about GPT-5 Nano?
Is GPT-5 Nano cheaper than GPT-OSS 20B?
GPT-5 Nano costs $0.14/M blended tokens, GPT-OSS 20B costs $0.13/M — GPT-OSS 20B is cheaper.
How much does 1 million tokens cost with GPT-5 Nano?
At a 3:1 input:output ratio, 1 million blended tokens costs approximately $0.14. Pure input costs $0.05/M; pure output costs $0.40/M.
What does GPT-5 Nano cost at high volume?
At 100 million blended tokens a month, GPT-5 Nano costs approximately $13.75. See the cost-at-scale table below for other volumes.