gpt-5-nano
replicate · chat model
gpt-5-nano is listed here as a chat model from replicate. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.0500 / 1M tokens
Output
$0.4000 / 1M tokens
Cached input
N/A
Context
N/A
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $0.0500 / 1M tokens |
| Output | $0.4000 / 1M tokens |
| Embedding | $0.0500 / 1M tokens |
Token limits
Capabilities
| Capability | Supported |
|---|---|
| Vision | — |
| Function calling | ✅ |
| Parallel function calling | — |
| Tool choice | — |
| Prompt caching | — |
| Reasoning | — |
| Response schema | — |
| System messages | ✅ |
| Audio input | — |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| SWE-bench Verified | 74.9% | accuracy (%) | Base model: gpt-5 (GPT-5 (high)) | 2026-05-31 | Link |
| Aider Polyglot | 88.0% | accuracy (%) | Base model: gpt-5 (GPT-5 (high)) | 2026-05-31 | Link |
| GPQA Diamond | 85.7% | accuracy (%) | Base model: gpt-5 (GPT-5 (high)) | 2026-05-31 | Link |
| AIME 2025 | 94.6% | accuracy (%) | Base model: gpt-5 (GPT-5 (high)) | 2026-05-31 | Link |
| Tau2-bench Telecom | 96.7% | accuracy (%) | Base model: gpt-5 (GPT-5 (high)) | 2026-05-31 | Link |
| Aider Polyglot | 88.0% | percent correct | Base model: GPT-5 (openai/gpt-5) | 2026-05-31 | Link |
| Aider Polyglot | 86.7% | percent correct | Base model: GPT-5 (openai/gpt-5) | 2026-05-31 | Link |
| Aider Polyglot | 81.3% | percent correct | Base model: GPT-5 (openai/gpt-5) | 2026-05-31 | Link |
| AIME 2025 | 85.2% | accuracy (%) | Base model: gpt-5-nano (GPT-5 nano (high)) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gpt-5-nano replicate | In $0.0500 / 1M tokens Out $0.4000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | N/A | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gpt-4.1-nano replicate | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | N/A | Same provider Overall 81% |
| mistral.ministral-3-14b-instruct bedrock_converse | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | 8.2K | Text + image covered Overall 73% |
| mistral.ministral-3-3b-instruct bedrock_converse | In $0.1000 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | 8.2K | Text + image covered Overall 72% |
| mistral.ministral-3-8b-instruct bedrock_converse | In $0.1500 / 1M tokens Out $0.1500 / 1M tokens | imagetext
Output: text | Function callingSystem messages | 8.2K | Text + image covered Overall 72% |
| mistral.mistral-large-3-675b-instruct bedrock_converse | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | 8.2K | Text + image covered Overall 69% |
| gpt-oss-20b replicate | In $0.0900 / 1M tokens Out $0.3600 / 1M tokens | imagetext
Output: text | Function callingSystem messages | N/A | Same provider Overall 68% Missing image |
| gpt-5-nano Azure | In $0.0500 / 1M tokens Out $0.4000 / 1M tokens | imagetext pdf
Output: text | Function callingSystem messages | 128.0K | Text + image covered Overall 66% |
| gpt-5-nano-2025-08-07 Azure | In $0.0500 / 1M tokens Out $0.4000 / 1M tokens | imagetext pdf
Output: text | Function callingSystem messages | 128.0K | Text + image covered Overall 66% |
| granite-3.3-8b-instruct replicate | In $0.0300 / 1M tokens Out $0.2500 / 1M tokens | imagetext
Output: text | Function callingSystem messages | N/A | Same provider Overall 65% Missing image |
| gpt-5-nano OpenAI | In $0.0500 / 1M tokens Out $0.4000 / 1M tokens | imagetext pdf
Output: text | Function callingSystem messages | 128.0K | Text + image covered Overall 65% |
| gpt-5-nano-2025-08-07 OpenAI | In $0.0500 / 1M tokens Out $0.4000 / 1M tokens | imagetext pdf
Output: text | Function callingSystem messages | 128.0K | Text + image covered Overall 65% |
| gpt-oss-120b replicate | In $0.1800 / 1M tokens Out $0.7200 / 1M tokens | imagetext
Output: text | Function callingSystem messages | N/A | Same provider Overall 62% Missing image |
| mistral.magistral-small-2509 bedrock_converse | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | 8.2K | Text + image covered Overall 61% |
| mistral.devstral-2-123b bedrock_converse | In $0.4000 / 1M tokens Out $2.0000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | 8.2K | Text + image covered Overall 60% |
| qwen3-235b-a22b-instruct-2507 replicate | In $0.2640 / 1M tokens Out $1.0600 / 1M tokens | imagetext
Output: text | Function callingSystem messages | N/A | Same provider Overall 59% Missing image |
| gpt-4o-mini replicate | In $0.1500 / 1M tokens Out $0.6000 / 1M tokens | imagetext
Output: text | Function callingSystem messages | N/A | Same provider Overall 59% |
| gpt-5-nano OpenRouter | In $0.0500 / 1M tokens Out $0.4000 / 1M tokens | imagetext file
Output: text | Low overlap | 128.0K | Text + image covered Overall 52% |
| databricks-gpt-5-nano databricks | In $0.0500 / 1M tokens Out $0.4000 / 1M tokens | imagetext
Output: unknown | Low overlap | 128.0K | Partial I/O overlap Overall 20% Missing text, image |
No models match this filter.