cohere.command-a-reasoning-08-2025
oci · chat model
cohere.command-a-reasoning-08-2025 is listed here as a chat model from oci. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$1.5600 / 1M tokens
Output
$1.5600 / 1M tokens
Cached input
N/A
Context
4.0K
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 | $1.5600 / 1M tokens |
| Output | $1.5600 / 1M tokens |
| Embedding | $1.5600 / 1M tokens |
Token limits
Context window
4.0K
Max input tokens
256.0K
Max output tokens
4.0K
Max tokens
4.0K
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 |
|---|---|---|---|---|---|
| MMLU | 85.5 | accuracy | Base model: command-a (Command A) | 2026-05-31 | Link |
| MMLU-Pro | 69.6 | accuracy | Base model: command-a (Command A) | 2026-05-31 | Link |
| GPQA | 50.8 | accuracy | Base model: command-a (Command A) | 2026-05-31 | Link |
| IFEval | 90.9 | strict accuracy | Base model: command-a (Command A) | 2026-05-31 | Link |
| BFCL | 63.8 | score | Base model: command-a (Command A) | 2026-05-31 | Link |
| Taubench Retail | P@1 60.0 | pass@1 | Base model: command-a (Command A) | 2026-05-31 | Link |
| Taubench Airline | P@1 45.3 | pass@1 | Base model: command-a (Command A) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
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 |
|---|---|---|---|---|---|
| cohere.command-a-reasoning-08-2025 oci | In $1.5600 / 1M tokens Out $1.5600 / 1M tokens |
Output: unknown | Function calling | 4.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| cohere.command-latest oci | In $1.5600 / 1M tokens Out $1.5600 / 1M tokens |
Output: unknown | Function calling | 4.0K | Same provider Overall 60% |
| cohere.command-a-03-2025 oci | In $1.5600 / 1M tokens Out $1.5600 / 1M tokens |
Output: unknown | Function calling | 4.0K | Same provider Overall 60% |
| cohere.command-plus-latest oci | In $1.5600 / 1M tokens Out $1.5600 / 1M tokens |
Output: unknown | Function calling | 4.0K | Same provider Overall 60% |
| cohere.command-r-plus-08-2024 oci | In $1.5600 / 1M tokens Out $1.5600 / 1M tokens |
Output: unknown | Function calling | 4.0K | Same provider Overall 60% |
| eu.mistral.pixtral-large-2502-v1:0 bedrock_converse | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: image, text | Function calling | 4.1K | Partial I/O overlap Overall 50% |
| us.mistral.pixtral-large-2502-v1:0 bedrock_converse | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens |
Output: unknown | Function calling | 4.1K | Partial I/O overlap Overall 50% |
| meta.llama-3.3-70b-instruct oci | In $0.7200 / 1M tokens Out $0.7200 / 1M tokens |
Output: unknown | Function calling | 4.0K | Same provider Overall 49% |
| meta.llama-4-maverick-17b-128e-instruct-fp8 oci | In $0.7200 / 1M tokens Out $0.7200 / 1M tokens |
Output: unknown | Function calling | 4.0K | Same provider Overall 49% |
| mixtral-8x22b-instruct vercel_ai_gateway | In $1.2000 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | Function calling | 2.0K | Partial I/O overlap Overall 48% |
| cohere.command-a-vision-07-2025 oci | In $1.5600 / 1M tokens Out $1.5600 / 1M tokens |
Output: unknown | Function calling | 4.0K | Same provider Overall 48% |
| command-r-plus Azure | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | text
Output: text | Function calling | 4.1K | Partial I/O overlap Overall 45% |
| DeepSeek-V3 nebius | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens |
Output: unknown | Function calling | 128.0K | Partial I/O overlap Overall 39% |
| Mixtral-8x22B-Instruct-v0.1 anyscale | In $0.9000 / 1M tokens Out $0.9000 / 1M tokens |
Output: unknown | Function calling | 65.5K | Partial I/O overlap Overall 37% |
| Mistral-7B-Instruct-v0.1 anyscale | In $0.1500 / 1M tokens Out $0.1500 / 1M tokens |
Output: unknown | Function calling | 16.4K | Partial I/O overlap Overall 31% |
| Mixtral-8x7B-Instruct-v0.1 anyscale | In $0.1500 / 1M tokens Out $0.1500 / 1M tokens |
Output: unknown | Function calling | 16.4K | Partial I/O overlap Overall 31% |
| mistral-large-2402 Azure | In $8.0000 / 1M tokens Out $24.0000 / 1M tokens |
Output: unknown | Function calling | 32.0K | Partial I/O overlap Overall 29% |
| mistral-large-latest Azure | In $8.0000 / 1M tokens Out $24.0000 / 1M tokens |
Output: unknown | Function calling | 32.0K | Partial I/O overlap Overall 29% |
| DeepSeek-V3-0324 crusoe | In $1.5000 / 1M tokens Out $1.5000 / 1M tokens |
Output: unknown | Function calling | 163.8K | Partial I/O overlap Overall 26% |
No models match this filter.