gpt-4.1
Azure · chat model
gpt-4.1 is listed here as a chat model from Azure. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$2.0000 / 1M tokens
Output
$8.0000 / 1M tokens
Cached input
$0.5000 / 1M tokens
Context
32.8K
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 | $2.0000 / 1M tokens |
| Output | $8.0000 / 1M tokens |
| Cached input | $0.5000 / 1M tokens |
| Embedding | $2.0000 / 1M tokens |
| Batch input | $1.0000 / 1M tokens |
| Batch output | $4.0000 / 1M tokens |
Token limits
Context window
32.8K
Max input tokens
1.0M
Max output tokens
32.8K
Max tokens
32.8K
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 | 54.6% | accuracy (%) | Base model: gpt-4.1 (GPT-4.1) | 2026-05-31 | Link |
| Aider Polyglot | 51.6% | accuracy (%) | Base model: gpt-4.1 (GPT-4.1) | 2026-05-31 | Link |
| Aider Polyglot | 52.9% | accuracy (%) | Base model: gpt-4.1 (GPT-4.1) | 2026-05-31 | Link |
| IFEval | 87.4% | accuracy (%) | Base model: gpt-4.1 (GPT-4.1) | 2026-05-31 | Link |
| OpenAI-MRCR: 2 needle 128k | 57.2% | accuracy (%) | Base model: gpt-4.1 (GPT-4.1) | 2026-05-31 | Link |
| SWE-bench Verified | 54.6% | accuracy | Base model: GPT-4.1 (gpt-4.1) | 2026-05-31 | Link |
| MultiChallenge | 38.3% | accuracy | Base model: GPT-4.1 (gpt-4.1) | 2026-05-31 | Link |
| Video-MME | 72.0% | accuracy | Base model: GPT-4.1 (gpt-4.1) | 2026-05-31 | Link |
| Aider Polyglot Diff | 52.9% | pass rate | Base model: GPT-4.1 (gpt-4.1) | 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-4.1 Azure | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gpt-4.1-2025-04-14 Azure | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Same provider Overall 100% |
| GPT-4.1 OpenAI | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext pdf
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Text + image covered Overall 94% |
| gpt-4.1-2025-04-14 OpenAI | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext pdf
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Text + image covered Overall 94% |
| gpt-4.1 OpenRouter | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext file
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Text + image covered Overall 92% |
| gpt-4.1 vercel_ai_gateway | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choiceResponse schema | 32.8K | Text + image covered Overall 89% |
| gpt-4o OpenAI | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | imagetext pdf
Output: text | VisionFunction callingParallel function callingTool choice | 16.4K | Text + image covered Overall 85% |
| gpt-4o-2024-08-06 Azure | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 16.4K | Same provider Overall 85% |
| gpt-4o-2024-08-06 Azure | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 16.4K | Same provider Overall 85% |
| gpt-4o-2024-11-20 Azure | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 16.4K | Same provider Overall 85% |
| gpt-4o Azure | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 16.4K | Same provider Overall 85% |
| gpt-4o-2024-08-06 Azure | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 16.4K | Same provider Overall 85% |
| gpt-4.1-mini Azure | In $0.4000 / 1M tokens Out $1.6000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Same provider Overall 84% |
| gpt-4.1-mini-2025-04-14 Azure | In $0.4000 / 1M tokens Out $1.6000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Same provider Overall 84% |
| gpt-4.1-nano Azure | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Same provider Overall 81% |
| gpt-4.1-nano-2025-04-14 Azure | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 32.8K | Same provider Overall 81% |
| claude-4-sonnet replicate | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | N/A | Text + image covered Overall 77% |
| claude-3.7-sonnet replicate | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | N/A | Text + image covered Overall 77% |
| claude-4.5-sonnet replicate | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | N/A | Text + image covered Overall 77% |
| claude-4.5-haiku replicate | In $1.0000 / 1M tokens Out $5.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | N/A | Text + image covered Overall 76% |
| gpt-4.5-preview Azure | In $75.0000 / 1M tokens Out $150.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingParallel function callingTool choice | 16.4K | Same provider Overall 73% |
| azure Azure | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Same provider Overall 57% Missing text, image |
| o3-2025-04-16 Azure | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Same provider Overall 57% Missing text, image |
| ai21.jamba-1-5-large-v1:0 Bedrock | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext
Output: text | Low overlap | 256.0K | Partial I/O overlap Overall 50% Missing image |
No models match this filter.