devstral-small
vercel_ai_gateway · chat model
devstral-small is listed here as a chat model from vercel_ai_gateway. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.0700 / 1M tokens
Output
$0.2800 / 1M tokens
Cached input
N/A
Context
128.0K
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 | $0.0700 / 1M tokens |
| Output | $0.2800 / 1M tokens |
| Embedding | $0.0700 / 1M tokens |
Token limits
Context window
128.0K
Max input tokens
128.0K
Max output tokens
128.0K
Max tokens
128.0K
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 | 46.8% | SWE-Bench Verified | Base model: Devstral (devstral-small-2505) | 2026-05-31 | Link |
| SWE-bench Verified | 53.6% | SWE-Bench Verified | Base model: Devstral (devstral-small-2507) | 2026-05-31 | Link |
| SWE-bench Verified | 68.0% | score | Base model: Devstral (mistralai/Devstral-Small-2-24B-Instruct-2512) | 2026-05-31 | Link |
| SWE-bench Multilingual | 55.7% | score | Base model: Devstral (mistralai/Devstral-Small-2-24B-Instruct-2512) | 2026-05-31 | Link |
| Terminal-Bench 2.0 | 22.5% | score | Base model: Devstral (mistralai/Devstral-Small-2-24B-Instruct-2512) | 2026-05-31 | Link |
| SWE-bench Verified | 72.2% | score | Base model: Devstral (Devstral 2) | 2026-05-31 | Link |
| SWE-bench Multilingual | 61.3% | score | Base model: Devstral (Devstral 2) | 2026-05-31 | Link |
| Terminal-Bench 2.0 | 32.6% | score | Base model: Devstral (Devstral 2) | 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 |
|---|---|---|---|---|---|
| devstral-small vercel_ai_gateway | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 128.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| devstral-small-2505 Mistral | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 128.0K | Text covered Overall 97% |
| devstral-small-2507 Mistral | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 128.0K | Text covered Overall 97% |
| devstral-small-latest Mistral | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 256.0K | Text covered Overall 89% |
| labs-devstral-small-2512 Mistral | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 256.0K | Text covered Overall 89% |
| Meta-Llama-3.1-70B-Instruct-Turbo deepinfra | In $0.1000 / 1M tokens Out $0.2800 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Text covered Overall 89% |
| gpt-oss-20b fireworks_ai | In $0.0500 / 1M tokens Out $0.2000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 131.1K | Text covered Overall 88% |
| deepseek-r1-distill-llama-70b vercel_ai_gateway | In $0.7500 / 1M tokens Out $0.9900 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 131.1K | Same provider Overall 84% |
| mistral-small Mistral | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 8.2K | Text covered Overall 83% |
| llama-3.1-8b vercel_ai_gateway | In $0.0500 / 1M tokens Out $0.0800 / 1M tokens | text
Output: text | Function callingResponse schema | 131.1K | Same provider Overall 81% |
| grok-3-mini vercel_ai_gateway | In $0.3000 / 1M tokens Out $0.5000 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Same provider Overall 80% |
| minimax-m2p1 fireworks_ai | In $0.3000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 204.8K | Text covered Overall 79% |
| o3-mini vercel_ai_gateway | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 100.0K | Same provider Overall 78% |
| mixtral-8x22b-instruct-hf fireworks_ai | In $1.2000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 65.5K | Text covered Overall 76% |
| qwen-3-32b vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choice | 16.4K | Same provider Overall 75% |
| glm-4.5-air vercel_ai_gateway | In $0.2000 / 1M tokens Out $1.1000 / 1M tokens | text
Output: text | Function callingTool choice | 96.0K | Same provider Overall 74% |
| kimi-k2-instruct-0905 fireworks_ai | In $0.6000 / 1M tokens Out $2.5000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 32.8K | Text covered Overall 71% |
| ernie-4.5-21B-a3b novita | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: text | Function callingTool choice | 8.0K | Text covered Overall 71% |
| firefunction-v2 fireworks_ai | In $0.9000 / 1M tokens Out $0.9000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 8.2K | Text covered Overall 70% |
| mistral-small vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text image
Output: text | Function callingTool choiceResponse schema | 4.0K | Same provider Overall 70% |
| kimi-k2-instruct fireworks_ai | In $0.6000 / 1M tokens Out $2.5000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 16.4K | Text covered Overall 69% |
| llama-v3p1-405b-instruct fireworks_ai | In $3.0000 / 1M tokens Out $3.0000 / 1M tokens | text
Output: text | Function callingTool choiceResponse schema | 16.4K | Text covered Overall 68% |
| ernie-4.5-21B-a3b-thinking novita | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: text | Low overlap | 65.5K | Text covered Overall 68% |
| sonar-small-chat perplexity | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: unknown | Low overlap | 16.4K | Partial I/O overlap Overall 22% Missing text |
| pplx-7b-chat perplexity | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: unknown | Low overlap | 8.2K | Partial I/O overlap Overall 21% Missing text |
| mistral-7b-instruct perplexity | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: unknown | Low overlap | 4.1K | Partial I/O overlap Overall 20% Missing text |
| mixtral-8x7b-instruct perplexity | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: unknown | Low overlap | 4.1K | Partial I/O overlap Overall 20% Missing text |
No models match this filter.